HCI Bibliography Home | HCI Conferences | RecSys Archive | Detailed Records | RefWorks | EndNote | Hide Abstracts
RecSys Tables of Contents: 070809101112131415

Proceedings of the 2014 ACM Conference on Recommender Systems

Fullname:RecSys'14: Eighth ACM Conference on Recommender Systems
Editors:Alfred Kobsa; Michelle Zhou; Martin Ester; Yehuda Koren
Location:Foster City, Silicon Valley, California
Dates:2014-Oct-06 to 2014-Oct-10
Standard No:ISBN: 978-1-4503-2668-1; ACM DL: Table of Contents; hcibib: RecSys14
Links:Conference Website
  1. Novel applications
  2. Novel setups -- context aware
  3. Novel setups -- privacy & security
  4. Cold start and hybrid recommenders
  5. Metrics and evaluation
  6. Diversity, novelty and serendipity
  7. Recommendation methods and theory
  8. Ranking and Top-N recommendation
  9. Matrix factorization
  10. Short papers
  11. Demonstrations
  12. Workshops
  13. Tutorials
  14. Doctoral consortium

Novel applications

LinkedIn skills: large-scale topic extraction and inference BIBAFull-Text 1-8
  Mathieu Bastian; Matthew Hayes; William Vaughan; Sam Shah; Peter Skomoroch; Hyungjin Kim; Sal Uryasev; Christopher Lloyd
"Skills and Expertise" is a data-driven feature on LinkedIn, the world's largest professional online social network, which allows members to tag themselves with topics representing their areas of expertise. In this work, we present our experiences developing this large-scale topic extraction pipeline, which includes constructing a folksonomy of skills and expertise and implementing an inference and recommender system for skills. We also discuss a consequent set of applications, such as Endorsements, which allows members to tag themselves with topics representing their areas of expertise and for their connections to provide social proof, via an "endorse" action, of that member's competence in that topic.
Automating readers' advisory to make book recommendations for K-12 readers BIBAFull-Text 9-16
  Maria Soledad Pera; Yiu-Kai Ng
The academic performance of students is affected by their reading ability, which explains why reading is one of the most important aspects of school curriculums. Promoting good reading habits among K-12 students is essential, given the enormous influence of reading on students' development as learners and members of society. In doing so, it is indispensable to provide readers with engaging and motivating reading selections. Unfortunately, existing book recommenders have failed to offer adequate choices for K-12 readers, since they either ignore the reading abilities of their users or cannot acquire the much-needed information to make recommendations due to privacy issues. To address these problems, we have developed Rabbit, a book recommender that emulates the readers' advisory service offered at school/public libraries. Rabbit considers the readability levels of its readers and determines the facets, i.e., appeal factors, of books that evoke subconscious, emotional reactions on a reader. The design of Rabbit is unique, since it adopts a multi-dimensional approach to capture the reading abilities, preferences, and interests of its readers, which goes beyond the traditional book content/topical analysis. Conducted empirical studies have shown that Rabbit outperforms a number of (readability-based) book recommenders.
Exploiting sentiment homophily for link prediction BIBAFull-Text 17-24
  Guangchao Yuan; Pradeep K. Murukannaiah; Zhe Zhang; Munindar P. Singh
Link prediction on social media is an important problem for recommendation systems. Understanding the interplay of users' sentiments and social relationships can be potentially valuable. Specifically, we study how to exploit sentiment homophily for link prediction. We evaluate our approach on a dataset gathered fro Twitter that consists of tweets sent in one month during U.S. 2012 political campaign along with the "follows" relationship between users. Our first contribution is defining a set of sentiment-based features that help predict the likelihood of two users becoming "friends" (i.e., mutually mentioning or following each other) based on their sentiments toward topics of mutual interest. Our evaluation in a supervised learning framework demonstrates the benefits of sentiment-based features in link prediction. We find that Adamic-Adar and Euclidean distance measures are the best predictors. Our second contribution is proposing a factor graph model that incorporates a sentiment-based variant of cognitive balance theory. Our evaluation shows that, when tie strength is not too weak, our model is more effective in link prediction than traditional machine learning techniques.
A robust model for paper reviewer assignment BIBAFull-Text 25-32
  Xiang Liu; Torsten Suel; Nasir Memon
Automatic expert assignment is a common problem encountered in both industry and academia. For example, for conference program chairs and journal editors, in order to collect "good" judgments for a paper, it is necessary for them to assign the paper to the most appropriate reviewers. Choosing appropriate reviewers of course includes a number of considerations such as expertise and authority, but also diversity and avoiding conflicts. In this paper, we explore the expert retrieval problem and implement an automatic paper-reviewer recommendation system that considers aspects of expertise, authority, and diversity. In particular, a graph is first constructed on the possible reviewers and the query paper, incorporating expertise and authority information. Then a Random Walk with Restart (RWR) [1] model is employed on the graph with a sparsity constraint, incorporating diversity information. Extensive experiments on two reviewer recommendation benchmark datasets show that the proposed method obtains performance gains over state-of-the-art reviewer recommendation systems in terms of expertise, authority, diversity, and, most importantly, relevance as judged by human experts.

Novel setups -- context aware

Factored MDPs for detecting topics of user sessions BIBAFull-Text 33-40
  Maryam Tavakol; Ulf Brefeld
Recommender systems aim to capture interests of users to provide tailored recommendations. User interests are however often unique and depend on many unobservable factors including a user's mood and the local weather. We take a contextual session-based approach and propose a sequential framework using factored Markov decision processes (fMDPs) to detect the user's goal (the topic) of a session. We show that an independence assumption on the attributes of items leads to a set of independent models that can be optimised efficiently. Our approach results in interpretable topics that can be effectively turned into recommendations. Empirical results on a real world click log from a large e-commerce company exhibit highly accurate topic prediction rates of about 90%. Translating our approach into a topic-driven recommender system outperforms several baseline competitors.
Context adaptation in interactive recommender systems BIBAFull-Text 41-48
  Negar Hariri; Bamshad Mobasher; Robin Burke
Contextual factors can greatly influence the utility of recommendations for users. In many recommendation and personalization applications, particularly in domains where user context changes dynamically, it is difficult to represent and model contextual factors directly, but it is often possible to observe their impact on user preferences during the course of users' interactions with the system. In this paper, we introduce an interactive recommender system that can detect and adapt to changes in context based on the user's ongoing behavior. The system, then, dynamically tailors its recommendations to match the user's most recent preferences. We formulate this problem as a multi-armed bandit problem and use Thompson sampling heuristic to learn a model for the user. Following the Thompson sampling approach, the user model is updated after each interaction as the system observes the corresponding rewards for the recommendations provided during that interaction. To generate contextual recommendations, the user's preference model is monitored for changes at each step of interaction with the user and is updated incrementally. We will introduce a mechanism for detecting significant changes in the user's preferences and will describe how it can be used to improve the performance of the recommender system.
Question recommendation with constraints for massive open online courses BIBAFull-Text 49-56
  Diyi Yang; David Adamson; Carolyn Penstein Rosé
Massive Open Online Courses (MOOCs) have experienced a recent boom in interest. Problems students struggle with in the discussion forums, such as difficultly in finding interesting discussion opportunities or attracting helpers to address posted problems, provide new opportunities for recommender systems. In contrast to traditional product recommendation, question recommendation in discussion forums should simultaneously consider constraints on both students and questions. These considerations include (1) Load Balancing -- students should not be over-burdened with too many requests; and (2) Expertise Matching -- students should not be requested to address problems they are not capable of addressing. In this work, we formulate a novel constrained question recommendation problem to address the above considerations. We design a context-aware matrix factorization model to predict students' preferences over questions, then build a max cost flow model to manage the constraints. Experimental results conducted on three MOOC datasets demonstrate that our method significantly outperforms baseline methods in optimizing overall forum welfare, and in predicting which specific questions students might be interested in.

Novel setups -- privacy & security

Attacking item-based recommender systems with power items BIBAFull-Text 57-64
  Carlos E. Seminario; David C. Wilson
Recommender Systems (RS) are vulnerable to attack by malicious users who intend to bias the recommendations for their own benefit. Research in this area has developed attack models, detection methods, and mitigation schemes to understand and protect against such attacks. For Collaborative Filtering RSs, model-based approaches such as item-based and matrix-factorization were found to be more robust to many types of attack. Advice in designing for system robustness has thus been to employ model-based approaches. Our recent work with the Power User Attack (PUA), however, determined that attackers disguised as influential users can successfully attack (from the attacker's viewpoint) SVD-based recommenders, as well as user-based. But item-based systems remained robust to the PUA. In this paper we investigate a new, complementary attack model, the Power Item Attack (PIA), that uses influential items to successfully attack RSs. We show that the PIA is able to impact not only user-based and SVD-based recommenders but also the heretofore highly robust item-based approach, using a novel multi-target attack vector.
Recommending with an agenda: active learning of private attributes using matrix factorization BIBAFull-Text 65-72
  Smriti Bhagat; Udi Weinsberg; Stratis Ioannidis; Nina Taft
Recommender systems leverage user demographic information, such as age, gender, etc., to personalize recommendations and better place their targeted ads. Oftentimes, users do not volunteer this information due to privacy concerns, or due to a lack of initiative in filling out their online profiles. We illustrate a new threat in which a recommender learns private attributes of users who do not voluntarily disclose them. We design both passive and active attacks that solicit ratings for strategically selected items, and could thus be used by a recommender system to pursue this hidden agenda. Our methods are based on a novel usage of Bayesian matrix factorization in an active learning setting. Evaluations on multiple datasets illustrate that such attacks are indeed feasible and use significantly fewer rated items than static inference methods. Importantly, they succeed without sacrificing the quality of recommendations to users.

Cold start and hybrid recommenders

Ensemble contextual bandits for personalized recommendation BIBAFull-Text 73-80
  Liang Tang; Yexi Jiang; Lei Li; Tao Li
The cold-start problem has attracted extensive attention among various online services that provide personalized recommendation. Many online vendors employ contextual bandit strategies to tackle the so-called exploration/exploitation dilemma rooted from the cold-start problem. However, due to high-dimensional user/item features and the underlying characteristics of bandit policies, it is often difficult for service providers to obtain and deploy an appropriate algorithm to achieve acceptable and robust economic profit.
   In this paper, we explore ensemble strategies of contextual bandit algorithms to obtain robust predicted click-through rate (CTR) of web objects. The ensemble is acquired by aggregating different pulling policies of bandit algorithms, rather than forcing the agreement of prediction results or learning a unified predictive model. To this end, we employ a meta-bandit paradigm that places a hyper bandit over the base bandits, to explicitly explore/exploit the relative importance of base bandits based on user feedbacks. Extensive empirical experiments on two real-world data sets (news recommendation and online advertising) demonstrate the effectiveness of our proposed approach in terms of CTR.
Cold-start news recommendation with domain-dependent browse graph BIBAFull-Text 81-88
  Michele Trevisiol; Luca Maria Aiello; Rossano Schifanella; Alejandro Jaimes
Online social networks and mash-up services create opportunities to connect different web services otherwise isolated. Specifically in the case of news, users are very much exposed to news articles while performing other activities, such as social networking or web searching. Browsing behavior aimed at the consumption of news, especially in relation to the visits coming from other domains, has been mainly overlooked in previous work. To address that, we build a BrowseGraph out of the collective browsing traces extracted from a large viewlog of Yahoo News (0.5B entries), and we define the ReferrerGraph as its subgraph induced by the sessions with the same referrer domain. The structural and temporal properties of the graph show that browsing behavior in news is highly dependent on the referrer URL of the session, in terms of type of content consumed and time of consumption. We build on this observation and propose a news recommender that addresses the cold-start problem: given a user landing on a page of the site for the first time, we aim to predict the page she will visit next. We compare 24 flavors of recommenders belonging to the families of content-based, popularity-based, and browsing-based models. We show that the browsing-based recommender that takes into account the referrer URL is the best performing, achieving a prediction accuracy of 48% in conditions of heavy data sparsity.
Item cold-start recommendations: learning local collective embeddings BIBAFull-Text 89-96
  Martin Saveski; Amin Mantrach
Recommender systems suggest to users items that they might like (e.g., news articles, songs, movies) and, in doing so, they help users deal with information overload and enjoy a personalized experience. One of the main problems of these systems is the item cold-start, i.e., when a new item is introduced in the system and no past information is available, then no effective recommendations can be produced. The item cold-start is a very common problem in practice: modern online platforms have hundreds of new items published every day. To address this problem, we propose to learn Local Collective Embeddings: a matrix factorization that exploits items' properties and past user preferences while enforcing the manifold structure exhibited by the collective embeddings. We present a learning algorithm based on multiplicative update rules that are efficient and easy to implement. The experimental results on two item cold-start use cases: news recommendation and email recipient recommendation, demonstrate the effectiveness of this approach and show that it significantly outperforms six state-of-the-art methods for item cold-start.
Improving the discriminative power of inferred content information using segmented virtual profile BIBAFull-Text 97-104
  Haishan Liu; Anuj Goyal; Trevor Walker; Anmol Bhasin
We present a novel component of a hybrid recommender system at LinkedIn, where item features are augmented by a virtual profile based on observed user-item interactions. A virtual profile is generated by representing an item in the user feature space and leveraging the overrepresented user features from users who interacted with the item. It is a way to think about Collaborative Filtering with content features. The core principle is that if the feature occurs with high probability for the users who interacted with an item (henceforth termed as relevant users) versus those who did not (henceforth termed as non-relevant users), then that feature is a good candidate to be included in the virtual profile of the item in question. However, this scheme suffers from the data imbalance problem because observed relevant users are usually an extremely small minority group compared to the whole user base. Feature selection in this skewed setting is prone to noise from the overwhelming non-relevant examples that belong to the majority group. To alleviate the problem, we propose a method to select the most relevant non-relevant examples from the majority group by segmenting users on certain intelligently selected feature dimensions. The resulting virtual profile from the method is called the segmented virtual profile. Empirical evaluation on a real-world large scale recommender system at LinkedIn shows that our strategies for segmentation yield significantly better results.
Ratings meet reviews, a combined approach to recommend BIBAFull-Text 105-112
  Guang Ling; Michael R. Lyu; Irwin King
Most existing recommender systems focus on modeling the ratings while ignoring the abundant information embedded in the review text. In this paper, we propose a unified model that combines content-based filtering with collaborative filtering, harnessing the information of both ratings and reviews. We apply topic modeling techniques on the review text and align the topics with rating dimensions to improve prediction accuracy. With the information embedded in the review text, we can alleviate the cold-start problem. Furthermore, our model is able to learn latent topics that are interpretable. With these interpretable topics, we can explore the prior knowledge on items or users and recommend completely "cold"' items. Empirical study on 27 classes of real-life datasets show that our proposed model lead to significant improvement compared with strong baseline methods, especially for datasets which are extremely sparse where rating-only methods cannot make accurate predictions.

Metrics and evaluation

Beyond clicks: dwell time for personalization BIBAFull-Text 113-120
  Xing Yi; Liangjie Hong; Erheng Zhong; Nanthan Nan Liu; Suju Rajan
Many internet companies, such as Yahoo, Facebook, Google and Twitter, rely on content recommendation systems to deliver the most relevant content items to individual users through personalization. Delivering such personalized user experiences is believed to increase the long term engagement of users. While there has been a lot of progress in designing effective personalized recommender systems, by exploiting user interests and historical interaction data through implicit (item click) or explicit (item rating) feedback, directly optimizing for users' satisfaction with the system remains challenging. In this paper, we explore the idea of using item-level dwell time as a proxy to quantify how likely a content item is relevant to a particular user. We describe a novel method to compute accurate dwell time based on client-side and server-side logging and demonstrate how to normalize dwell time across different devices and contexts. In addition, we describe our experiments in incorporating dwell time into state-of-the-art learning to rank techniques and collaborative filtering models that obtain competitive performances in both offline and online settings.
Evaluating recommender behavior for new users BIBAFull-Text 121-128
  Daniel Kluver; Joseph A. Konstan
The new user experience is one of the important problems in recommender systems. Past work on recommending for new users has focused on the process of gathering information from the user. Our work focuses on how different algorithms behave for new users. We describe a methodology that we use to compare representatives of three common families of algorithms along eleven different metrics. We find that for the first few ratings a baseline algorithm performs better than three common collaborative filtering algorithms. Once we have a few ratings, we find that Funk's SVD algorithm has the best overall performance. We also find that ItemItem, a very commonly deployed algorithm, performs very poorly for new users. Our results can inform the design of interfaces and algorithms for new users.
Comparative recommender system evaluation: benchmarking recommendation frameworks BIBAFull-Text 129-136
  Alan Said; Alejandro Bellogín
Recommender systems research is often based on comparisons of predictive accuracy: the better the evaluation scores, the better the recommender. However, it is difficult to compare results from different recommender systems due to the many options in design and implementation of an evaluation strategy. Additionally, algorithmic implementations can diverge from the standard formulation due to manual tuning and modifications that work better in some situations.
   In this work we compare common recommendation algorithms as implemented in three popular recommendation frameworks. To provide a fair comparison, we have complete control of the evaluation dimensions being benchmarked: dataset, data splitting, evaluation strategies, and metrics. We also include results using the internal evaluation mechanisms of these frameworks. Our analysis points to large differences in recommendation accuracy across frameworks and strategies, i.e. the same baselines may perform orders of magnitude better or worse across frameworks. Our results show the necessity of clear guidelines when reporting evaluation of recommender systems to ensure reproducibility and comparison of results.
A methodology for learning, analyzing, and mitigating social influence bias in recommender systems BIBAFull-Text 137-144
  Sanjay Krishnan; Jay Patel; Michael J. Franklin; Ken Goldberg
The seminal 2003 paper by Cosley, Lab, Albert, Konstan, and Reidl, demonstrated the susceptibility of recommender systems to rating biases. To facilitate browsing and selection, almost all recommender systems display average ratings before accepting ratings from users which has been shown to bias ratings. This effect is called Social Influence Bias (SIB); the tendency to conform to the perceived \norm" in a community. We propose a methodology to 1) learn, 2) analyze, and 3) mitigate the effect of SIB in recommender systems. In the Learning phase, we build a baseline dataset by allowing users to rate twice: before and after seeing the average rating. In the Analysis phase, we apply a new non-parametric significance test based on the Wilcoxon statistic to test whether the data is consistent with SIB. If significant, we propose a Mitigation phase using polynomial regression and the Bayesian Information Criterion (BIC) to predict unbiased ratings. We evaluate our approach on a dataset of 9390 ratings from the California Report Card (CRC), a rating-based system designed to encourage political engagement. We found statistically significant evidence of SIB. Mitigating models were able to predict changed ratings with a normalized RMSE of 12.8% and reduce bias by 76.3%. The CRC, our data, and experimental code are available at: http://californiareportcard.org/data/

Diversity, novelty and serendipity

Improving sales diversity by recommending users to items BIBAFull-Text 145-152
  Saúl Vargas; Pablo Castells
Sales diversity is considered a key feature of Recommender Systems from a business perspective. Sales diversity is also linked with the long-tail novelty of recommendations, a quality dimension from the user perspective. We explore the inversion of the recommendation task as a means to enhance sales diversity -- and indirectly novelty -- by selecting which users an item should be recommended to instead of the other way around. We address the inverted task by two approaches: a) inverting the rating matrix, and b) defining a probabilistic reformulation which isolates the popularity component of arbitrary recommendation algorithms. We find that the first approach gives rise to interesting reformulations of nearest-neighbor algorithms, which essentially introduce a new neighbor selection policy. The second approach, as well as the first, ultimately result in substantial sales diversity enhancements, and improved trade-offs with recommendation precision and novelty. Two experiments on movie and music recommendation datasets show the effectiveness of the resulting approach, even when compared to direct optimization approaches of the target metrics proposed in prior work.
On over-specialization and concentration bias of recommendations: probabilistic neighborhood selection in collaborative filtering systems BIBAFull-Text 153-160
  Panagiotis Adamopoulos; Alexander Tuzhilin
Focusing on the problems of over-specialization and concentration bias, this paper presents a novel probabilistic method for recommending items in the neighborhood-based collaborative filtering framework. For the probabilistic neighborhood selection phase, we use an efficient method for weighted sampling of k neighbors that takes into consideration the similarity levels between the target user (or item) and the candidate neighbors. We conduct an empirical study showing that the proposed method increases the coverage, dispersion, and diversity reinforcement of recommendations by selecting diverse sets of representative neighbors. We also demonstrate that the proposed approach outperforms popular methods in terms of item prediction accuracy, utility-based ranking, and other popular measures, across various experimental settings. This performance improvement is in accordance with ensemble learning theory and the phenomenon of "hubness" in recommender systems.
User perception of differences in recommender algorithms BIBAFull-Text 161-168
  Michael D. Ekstrand; F. Maxwell Harper; Martijn C. Willemsen; Joseph A. Konstan
Recent developments in user evaluation of recommender systems have brought forth powerful new tools for understanding what makes recommendations effective and useful. We apply these methods to understand how users evaluate recommendation lists for the purpose of selecting an algorithm for finding movies. This paper reports on an experiment in which we asked users to compare lists produced by three common collaborative filtering algorithms on the dimensions of novelty, diversity, accuracy, satisfaction, and degree of personalization, and to select a recommender that they would like to use in the future. We find that satisfaction is negatively dependent on novelty and positively dependent on diversity in this setting, and that satisfaction predicts the user's final selection. We also compare users' subjective perceptions of recommendation properties with objective measures of those same characteristics. To our knowledge, this is the first study that applies modern survey design and analysis techniques to a within-subjects, direct comparison study of recommender algorithms.
Offline and online evaluation of news recommender systems at swissinfo.ch BIBAFull-Text 169-176
  Florent Garcin; Boi Faltings; Olivier Donatsch; Ayar Alazzawi; Christophe Bruttin; Amr Huber
We report on the live evaluation of various news recommender systems conducted on the website swissinfo.ch. We demonstrate that there is a major difference between offline and online accuracy evaluations. In an offline setting, recommending most popular stories is the best strategy, while in a live environment this strategy is the poorest. For online setting, context-tree recommender systems which profile the users in real-time improve the click-through rate by up to 35%. The visit length also increases by a factor of 2.5. Our experience holds important lessons for the evaluation of recommender systems with offline data as well as for the use of the click-through rate as a performance indicator.

Recommendation methods and theory

Unifying nearest neighbors collaborative filtering BIBAFull-Text 177-184
  Koen Verstrepen; Bart Goethals
We study collaborative filtering for applications in which there exists for every user a set of items about which the user has given binary, positive-only feedback (one-class collaborative filtering). Take for example an on-line store that knows all past purchases of every customer. An important class of algorithms for one-class collaborative filtering are the nearest neighbors algorithms, typically divided into user-based and item-based algorithms. We introduce a reformulation that unifies user- and item-based nearest neighbors algorithms and use this reformulation to propose a novel algorithm that incorporates the best of both worlds and outperforms state-of-the-art algorithms. Additionally, we propose a method for naturally explaining the recommendations made by our algorithm and show that this method is also applicable to existing user-based nearest neighbors methods.
Recommending user generated item lists BIBAFull-Text 185-192
  Yidan Liu; Min Xie; Laks V. S. Lakshmanan
Existing recommender systems mostly focus on recommending individual items which users may be interested in. User-generated item lists on the other hand have become a popular feature in many applications. E.g., Goodreads provides users with an interface for creating and sharing interesting book lists. These user-generated item lists complement the main functionality of the corresponding application, and intuitively become an alternative way for users to browse and discover interesting items to be consumed. Unfortunately, existing recommender systems are not designed for recommending user-generated item lists. In this work, we study properties of these user-generated item lists and propose a Bayesian ranking model, called LIRE for recommending them. The proposed model takes into consideration users' previous interactions with both item lists and with individual items. Furthermore, we propose in LIRE a novel way of weighting items within item lists based on both position of items, and personalized list consumption pattern. Through extensive experiments on a real item list dataset from Goodreads, we demonstrate the effectiveness of our proposed LIRE model.
Question recommendation for collaborative question answering systems with RankSLDA BIBAFull-Text 193-200
  Jose San Pedro; Alexandros Karatzoglou
Collaborative question answering (CQA) communities rely on user participation for their success. This paper presents a supervised Bayesian approach to model expertise in on-line CQA communities with application to question recommendation, aimed at reducing waiting times for responses and avoiding question starvation. We propose a novel algorithm called RankSLDA which extends the supervised Latent Dirichlet Allocation model by considering a learning-to-rank paradigm. This allows us to exploit the inherent collaborative effects that are present in CQA communities where users tend to answer questions in their topics of expertise. Users can thus be modeled on the basis of the topics in which they demonstrate expertise. In the supervised stage of the method we model the pairwise order of expertise of users on a given question. We compare RankSLDA against several alternative methods on data from the Cross Validate community, part of the Stack Exchange network. RankSLDA outperforms all alternative methods by a significant margin.
Bayesian binomial mixture model for collaborative prediction with non-random missing data BIBAFull-Text 201-208
  Yong-Deok Kim; Seungjin Choi
Collaborative prediction involves filling in missing entries of a user-item matrix to predict preferences of users based on their observed preferences. Most of existing models assume that the data is missing at random (MAR), which is often violated in recommender systems in practice. Incorrect assumption on missing data ignores the missing data mechanism, leading to biased inferences and prediction. In this paper we present a Bayesian binomial mixture model for collaborative prediction, where the generative process for data and missing data mechanism are jointly modeled to handle non-random missing data. Missing data mechanism is modeled by three factors, each of which is related to users, items, and rating values. Each factor is modeled by Bernoulli random variable, and the observation of rating value is determined by the Boolean OR operation of three binary variables. We develop computationally-efficient variational inference algorithms, where variational parameters have closed-form update rules and the computational complexity depends on the number of observed ratings, instead of the size of the rating data matrix. We also discuss implementation issues on hyperparameter tuning and estimation based on empirical Bayes. Experiments on Yahoo! Music and MovieLens datasets confirm the useful behavior of our model by demonstrating that: (1) it outperforms state-of-the-art methods in yielding higher predictive performance; (2) it finds meaningful solutions instead of undesirable boundary solutions; (3) it provides rating trend analysis on why ratings are observed.

Ranking and Top-N recommendation

Coverage, redundancy and size-awareness in genre diversity for recommender systems BIBAFull-Text 209-216
  Saúl Vargas; Linas Baltrunas; Alexandros Karatzoglou; Pablo Castells
There is increasing awareness in the Recommender Systems field that diversity is a key property that enhances the usefulness of recommendations. Genre information can serve as a means to measure and enhance the diversity of recommendations and is readily available in domains such as movies, music or books. In this work we propose a new Binomial framework for defining genre diversity in recommender systems that takes into account three key properties: genre coverage, genre redundancy and recommendation list size-awareness. We show that methods previously proposed for measuring and enhancing recommendation diversity -- including those adapted from search result diversification -- fail to address adequately these three properties. We also propose an efficient greedy optimization technique to optimize Binomial diversity. Experiments with the Netflix dataset show the properties of our framework and comparison with state of the art methods.
Towards a dynamic top-N recommendation framework BIBAFull-Text 217-224
  Xin Liu; Karl Aberer
Real world large-scale recommender systems are always dynamic: new users and items continuously enter the system, and the status of old ones (e.g., users' preference and items' popularity) evolve over time. In order to handle such dynamics, we propose a recommendation framework consisting of an online component and an offline component, where the newly arrived items are processed by the online component such that users are able to get suggestions for fresh information, and the influence of longstanding items is captured by the offline component. Based on individual users' rating behavior, recommendations from the two components are combined to provide top-N recommendation. We formulate recommendation problem as a ranking problem where learning to rank is applied to extend upon matrix factorization to optimize item rankings by minimizing a pairwise loss function. Furthermore, to better model interactions between users and items, Latent Dirichlet Allocation is incorporated to fuse rating information and textual information. Real data based experiments demonstrate that our approach outperforms the state-of-the-art models by at least 61.21% and 50.27% in terms of mean average precision (MAP) and normalized discounted cumulative gain (NDCG) respectively.
Explore-exploit in top-N recommender systems via Gaussian processes BIBAFull-Text 225-232
  Hastagiri P. Vanchinathan; Isidor Nikolic; Fabio De Bona; Andreas Krause
We address the challenge of ranking recommendation lists based on click feedback by efficiently encoding similarities among users and among items. The key challenges are threefold: (1) combinatorial number of lists; (2) sparse feedback and (3) context dependent recommendations. We propose the CGPRank algorithm, which exploits prior information specified in terms of a Gaussian process kernel function, which allows to share feedback in three ways: Between positions in a list, between items, and between contexts. Under our model, we provide strong performance guarantees and empirically evaluate our algorithm on data from two large scale recommendation tasks: Yahoo! news article recommendation, and Google books. In our experiments, CGPRank significantly outperforms state-of-the-art multi-armed bandit and learning-to-rank methods, with an 18% increase in clicks.
A parameter-free algorithm for an optimized tag recommendation list size BIBAFull-Text 233-240
  Modou Gueye; Talel Abdessalem; Hubert Naacke
Tag recommendation is a major aspect of collaborative tagging systems. It aims to recommend suitable tags to a user for tagging an item. One of its main challenges is the effectiveness of its recommendations. Existing works focus on techniques for retrieving the most relevant tags to give beforehand, with a fixed number of tags in each recommended list. In this paper, we try to optimize the number of recommended tags in order to improve the efficiency of the recommendations. We propose a parameter-free algorithm for determining the optimal size of the recommended list. Thus we introduced some relevance measures to find the most relevant sublist from a given list of recommended tags. More precisely, we improve the quality of our recommendations by discarding some unsuitable tags and thus adjusting the list size.
   Our solution is an add-on one, which can be implemented on top of many kinds of tag recommenders. The experiments we did on five datasets, using four categories of tag recommenders, demonstrate the efficiency of our technique. For instance, the algorithm we propose outperforms the results of the task 2 of the ECML PKDD Discovery Challenge 20091. By using the same tag recommender than the winners of the contest, we reach a F1 measure of 0.366 while the latter got 0.356. Thus, our solution yields significant improvements on the lists obtained from the tag recommenders.

Matrix factorization

GASGD: stochastic gradient descent for distributed asynchronous matrix completion via graph partitioning BIBAFull-Text 241-248
  Fabio Petroni; Leonardo Querzoni
Matrix completion latent factors models are known to be an effective method to build recommender systems. Currently, stochastic gradient descent (SGD) is considered one of the best latent factor-based algorithm for matrix completion. In this paper we discuss GASGD, a distributed asynchronous variant of SGD for large-scale matrix completion, that (i) leverages data partitioning schemes based on graph partitioning techniques, (ii) exploits specific characteristics of the input data and (iii) introduces an explicit parameter to tune synchronization frequency among the computing nodes. We empirically show how, thanks to these features, GASGD achieves a fast convergence rate incurring in smaller communication cost with respect to current asynchronous distributed SGD implementations.
A framework for matrix factorization based on general distributions BIBAFull-Text 249-256
  Josef Bauer; Alexandros Nanopoulos
In this paper we extend the current state-of-the-art matrix factorization method for recommendations to general probability distributions. As shown in previous work, the standard method called "Probabilistic Matrix Factorization" is based on a normal distribution assumption. While there exists work in which this method is extended to other distributions, these extensions are restrictive and we experimentally show on the basis of a real data set that it is worthwhile considering more general distributions which have not been used in the literature. Our contribution lies in providing a flexible and easy-to-use framework for matrix factorization with almost no limitation on the form of the distribution used. Our approach is based on maximum likelihood estimation and a key ingredient of our proposed method is automatic differentiation. This allows for the automatic derivation of the corresponding optimization algorithm, without the need to derive it manually for each distributional assumption while simultaneously being computationally efficient. Thus, with our method it is very easy to use a wide range of even complicated distributions for any data set.
Speeding up the Xbox recommender system using a euclidean transformation for inner-product spaces BIBAFull-Text 257-264
  Yoram Bachrach; Yehuda Finkelstein; Ran Gilad-Bachrach; Liran Katzir; Noam Koenigstein; Nir Nice; Ulrich Paquet
A prominent approach in collaborative filtering based recommender systems is using dimensionality reduction (matrix factorization) techniques to map users and items into low-dimensional vectors. In such systems, a higher inner product between a user vector and an item vector indicates that the item better suits the user's preference. Traditionally, retrieving the most suitable items is done by scoring and sorting all items. Real world online recommender systems must adhere to strict response-time constraints, so when the number of items is large, scoring all items is intractable.
   We propose a novel order preserving transformation, mapping the maximum inner product search problem to Euclidean space nearest neighbor search problem. Utilizing this transformation, we study the efficiency of several (approximate) nearest neighbor data structures. Our final solution is based on a novel use of the PCA-Tree data structure in which results are augmented using paths one hamming distance away from the query (neighborhood boosting). The end result is a system which allows approximate matches (items with relatively high inner product, but not necessarily the highest one). We evaluate our techniques on two large-scale recommendation datasets, Xbox Movies and Yahoo~Music, and show that this technique allows trading off a slight degradation in the recommendation quality for a significant improvement in the retrieval time.
Gradient boosting factorization machines BIBAFull-Text 265-272
  Chen Cheng; Fen Xia; Tong Zhang; Irwin King; Michael R. Lyu
Recommendation techniques have been well developed in the past decades. Most of them build models only based on user item rating matrix. However, in real world, there is plenty of auxiliary information available in recommendation systems. We can utilize these information as additional features to improve recommendation performance. We refer to recommendation with auxiliary information as context-aware recommendation. Context-aware Factorization Machines (FM) is one of the most successful context-aware recommendation models. FM models pairwise interactions between all features, in such way, a certain feature latent vector is shared to compute the factorized parameters it involved. In practice, there are tens of context features and not all the pairwise feature interactions are useful. Thus, one important challenge for context-aware recommendation is how to effectively select "good" interaction features. In this paper, we focus on solving this problem and propose a greedy interaction feature selection algorithm based on gradient boosting. Then we propose a novel Gradient Boosting Factorization Machine (GBFM) model to incorporate feature selection algorithm with Factorization Machines into a unified framework. The experimental results on both synthetic and real datasets demonstrate the efficiency and effectiveness of our algorithm compared to other state-of-the-art methods.
Exploiting temporal influence in online recommendation BIBAFull-Text 273-280
  Róbert Pálovics; András A. Benczúr; Levente Kocsis; Tamás Kiss; Erzsébet Frigó
In this paper we give methods for time-aware music recommendation in a social media service with the potential of exploiting immediate temporal influences between users. We consider events when a user listens to an artist the first time and this event follows some friend listening to the same artist short time before. We train a blend of matrix factorization methods that model the relation of the influencer, the influenced and the artist, both the individual factor decompositions and their weight learned by variants of stochastic gradient descent (SGD). Special care is taken since events of influence form a subset of the positive implicit feedback data and hence we have to cope with two different definitions of the positive and negative implicit training data. In addition, in the time-aware setting we have to use online learning and evaluation methods. While SGD can easily be trained online, evaluation is cumbersome by traditional measures since we will have potentially different top recommendations at different times. Our experiments are carried over the two-year "scrobble" history of 70,000 Last.fm users and show a 5% increase in recommendation quality by predicting temporal influences.

Short papers

'Free lunch' enhancement for collaborative filtering with factorization machines BIBAFull-Text 281-284
  Babak Loni; Alan Said; Martha Larson; Alan Hanjalic
The advantage of Factorization Machines over other factorization models is their ability to easily integrate and efficiently exploit auxiliary information to improve Collaborative Filtering. Until now, this auxiliary information has been drawn from external knowledge sources beyond the user-item matrix. In this paper, we demonstrate that Factorization Machines can exploit additional representations of information inherent in the user-item matrix to improve recommendation performance. We refer to our approach as 'Free Lunch' enhancement since it leverages clusters that are based on information that is present in the user-item matrix, but not otherwise directly exploited during matrix factorization. Borrowing clustering concepts from codebook sharing, our approach can also make use of 'Free Lunch' information inherent in a user-item matrix from a auxiliary domain that is different from the target domain of the recommender. Our approach improves performance both in the joint case, in which the auxiliary and target domains share users, and in the disjoint case, in which they do not. Although 'Free Lunch' enhancement does not apply equally well to any given domain or domain combination, our overall conclusion is that Factorization Machines present an opportunity to exploit information that is ubiquitously present, but commonly under-appreciated by Collaborative Filtering algorithms.
An analysis of users' propensity toward diversity in recommendations BIBAFull-Text 285-288
  Tommaso Di Noia; Vito Claudio Ostuni; Jessica Rosati; Paolo Tomeo; Eugenio Di Sciascio
Providing very accurate recommendations to end users has been nowadays recognized to be just one of the main tasks a recommender systems must be able to perform. While predicting relevant suggestions, attention needs to be paid to their diversification in order to avoid monotony in recommendation. In this paper we focus on modeling users' inclination toward selecting diverse items, where diversity is computed by means of content-based item attributes. We then exploit such modeling to present a novel approach to re-rank the list of Top-N items predicted by a recommendation algorithm, in order to foster diversity in the final ranking. Experimental evaluation proves the effectiveness of the proposed approach.
Clinical online recommendation with subgroup rank feedback BIBAFull-Text 289-292
  Yanan Sui; Joel Burdick
Many real applications in experimental design need to make decisions online. Each decision leads to a stochastic reward with initially unknown distribution. New decisions are made based on the observations of previous rewards. To maximize the total reward, one needs to solve the tradeoff between exploring different strategies and exploiting currently optimal strategies. This kind of tradeoff problems can be formalized as Multi-armed bandit problem. We recommend strategies in series and generate new recommendations based on noisy rewards of previous strategies. When the reward for a strategy is difficult to quantify, classical bandit algorithms are no longer optimal. This paper, studies the Multi-armed bandit problem with feedback given as a stochastic rank list instead of quantified reward values. We propose an algorithm for this new problem and show its optimality. A real application of this algorithm on clinical treatment is helping paralyzed patient to regain the ability to stand on their own feet.
Convex AUC optimization for top-N recommendation with implicit feedback BIBAFull-Text 293-296
  Fabio Aiolli
In this paper, an effective collaborative filtering algorithm for top-N item recommendation with implicit feedback is proposed. The task of top-N item recommendation is to predict a ranking of items (movies, books, songs, or products in general) that can be of interest for a user based on earlier preferences of the user. We focus on implicit feedback where preferences are given in the form of binary events/ratings. Differently from state-of-the-art methods, the method proposed is designed to optimize the AUC directly within a margin maximization paradigm. Specifically, this turns out in a simple constrained quadratic optimization problem, one for each user. Experiments performed on several benchmarks show that our method significantly outperforms state-of-the-art matrix factorization methods in terms of AUC of the obtained predictions.
Cross-domain recommendations without overlapping data: myth or reality? BIBAFull-Text 297-300
  Paolo Cremonesi; Massimo Quadrana
Cross-domain recommender systems adopt different techniques to transfer learning from source domain to target domain in order to alleviate the sparsity problem and improve accuracy of recommendations. Traditional techniques require the two domains to be linked by shared characteristics associated to either users or items. In collaborative filtering (CF) this happens when the two domains have overlapping users or item (at least partially). Recently, Li et al. [7] introduced codebook transfer (CBT), a cross-domain CF technique based on co-clustering, and presented experimental results showing that CBT is able to transfer knowledge between non-overlapping domains. In this paper, we disprove these results and show that CBT does not transfer knowledge when source and target domains do not overlap.
CSLIM: contextual SLIM recommendation algorithms BIBAFull-Text 301-304
  Yong Zheng; Bamshad Mobasher; Robin Burke
Context-aware recommender systems (CARS) take contextual conditions into account when providing item recommendations. In recent years, context-aware matrix factorization (CAMF) has emerged as an extension of the matrix factorization technique that also incorporates contextual conditions. In this paper, we introduce another matrix factorization approach for contextual recommendations, the contextual SLIM (CSLIM) recommendation approach. It is derived from the sparse linear method (SLIM) which was designed for Top-N recommendations in traditional recommender systems. Based on the experimental evaluations over several context-aware data sets, we demonstrate that CLSIM can be an effective approach for context-aware recommendations, in many cases outperforming state-of-the-art CARS algorithms in the Top-N recommendation task.
Dynamics of human trust in recommender systems BIBAFull-Text 305-308
  Jason L. Harman; John O'Donovan; Tarek Abdelzaher; Cleotilde Gonzalez
The trust that humans place on recommendations is key to the success of recommender systems. The formation and decay of trust in recommendations is a dynamic process influenced by context, human preferences, accuracy of recommendations, and the interactions of these factors. This paper describes two psychological experiments (N=400) that evaluate the evolution of trust in recommendations over time, under personalized and non-personalized recommendations by matching or not matching a participant's profile. Main findings include: Humans trust inaccurate recommendations more than they should; when recommendations are personalized, they lose trust in inaccurate recommendations faster than when recommendations are not personalized; and participants report less trust and lower overall ratings of personalized but inaccurate recommendations compared to not-personalized inaccurate recommendations. We make connections to the possible implications of these psychological findings to the design of recommender systems.
Eliciting the users' unknown preferences BIBAFull-Text 309-312
  Julia Neidhardt; Rainer Schuster; Leonhard Seyfang; Hannes Werthner
Personalized recommendation strongly relies on an accurate model to capture user preferences; eliciting this information is, in general, a hard problem. In the field of tourism this initial profiling becomes even more challenging. It has been shown that particularly in the beginning of the travel decision making process, users themselves are often not conscious of their needs and are not able to express them. In this paper, the basics of a picture-based approach are introduced that aims at revealing implicitly given user preferences. Based on a set of travel related pictures selected by a user, an individual travel profile is deduced. This is accomplished by mapping those pictures onto seven basic factors that reflect different travel behavioral aspects. Also tourism products can be represented by this seven factor model. Thus, this model constitutes the basis of our recommendation algorithm. First tests show that this non-verbal way of interaction is experienced as exiting and inspiring.
Emphasize, don't filter!: displaying recommendations in Twitter timelines BIBAFull-Text 313-316
  Wesley Waldner; Julita Vassileva
This paper describes and evaluates a method for presenting recommendations that will increase the efficiency of the social activity stream while preserving the users' accurate awareness of the activity within their own social networks. With the help of a content-based recommender system, the application displays the user's home timeline in Twitter as three visually distinct tiers by emphasizing more strongly those Tweets predicted to be more interesting. Pilot study participants reported that they were able to read the interesting Tweets while ignoring the others with relative ease and that the recommender accurately categorized their Tweets into three tiers.
Implicit vs. explicit trust in social matrix factorization BIBAFull-Text 317-320
  Soude Fazeli; Babak Loni; Alejandro Bellogin; Hendrik Drachsler; Peter Sloep
Incorporating social trust in Matrix Factorization (MF) methods demonstrably improves accuracy of rating prediction. Such approaches mainly use the trust scores explicitly expressed by users. However, it is often challenging to have users provide explicit trust scores of each other. There exist quite a few works, which propose Trust Metrics (TM) to compute and predict trust scores between users based on their interactions. In this paper, we first evaluate several TMs to find out which one can best predict trust scores compared to the actual trust scores explicitly expressed by users. And, second, we propose to incorporate these trust scores inferred from the candidate TMs into social matrix factorization (MF). We investigate if incorporating the implicit trust scores in MF can make rating prediction as accurate as the MF on explicit trust scores. The reported results support the idea of employing implicit trust into MF whenever explicit trust is not available, since the performance of both models is similar.
Modeling the dynamics of user preferences in coupled tensor factorization BIBAFull-Text 321-324
  Dimitrios Rafailidis; Alexandros Nanopoulos
In several applications, user preferences can be fairly dynamic, since users tend to exploit a wide range of items and modify their tastes accordingly over time. In this paper, we model continuous user-item interactions over time using a tensor that has time as a dimension (mode). To account for the fact that user preferences are dynamic and change individually, we propose a new measure of user-preference dynamics (UPD) that captures the rate with which the current preferences of each user have been shifted. We generate recommendations based on factorizing the tensor, by weighting the importance of past user preferences according to their UPD values. We additionally exploit users' side data, such as demographics, which can help improving the accuracy of recommendations based on a coupled, tensor-matrix factorization scheme. Our empirical evaluation uses a real data set from last.fm, which allows us to demonstrate that user preferences can become very dynamic. Our experimental results show that the proposed method, by taking into account these dynamics, outperforms several baselines.
Multi-criteria journey aware housing recommender system BIBAFull-Text 325-328
  Elizabeth M. Daly; Adi Botea; Akihiro Kishimoto; Radu Marinescu
Recommender systems can be employed to assist users in complex decision making processes. This paper presents a multi-criteria housing recommender system which takes into account not just features of a home, such as rent, but also the transportation links to user specified locations. First, we describe an efficient multi-hop journey time calculator. Second, we introduce a mechanism to find the optimal solutions for multi-criteria evaluation, where a balanced trade-off between the target goals is found. Finally, we present a user study to demonstrate the potential of such a system.
PERSPeCT: collaborative filtering for tailored health communications BIBAFull-Text 329-332
  Roy J. Adams; Rajani S. Sadasivam; Kavitha Balakrishnan; Rebecca L. Kinney; Thomas K. Houston; Benjamin M. Marlin
The goal of computer tailored health communications (CTHC) is to elicit healthy behavior changes by sending motivational messages personalized to individual patients. One prominent weakness of many existing CTHC systems is that they are based on expert-written rules and thus have no ability to learn from their users over time. One solution to this problem is to develop CTHC systems based on the principles of collaborative filtering, but this approach has not been widely studied. In this paper, we present a case study evaluating nine rating prediction methods for use in the Patient Experience Recommender System for Persuasive Communication Tailoring, a system developed for use in a clinical trial of CTHC-based smoking cessation support interventions.
Preference elicitation for narrowing the recommended list for groups BIBAFull-Text 333-336
  Lihi Naamani-Dery; Meir Kalech; Lior Rokach; Bracha Shapira
A group may appreciate recommendations on items that fit their joint preferences. When the members' actual preferences are unknown, a recommendation can be made with the aid of collaborative filtering methods. We offer to narrow down the recommended list of items by eliciting the users' actual preferences. Our final goal is to output top-k preferred items to the group out of the top-N recommendations provided by the recommender system (k), where one of the items is a necessary winner. We propose an iterative preference elicitation method, where users are required to provide item ratings per request. We suggest a heuristic that attempts to minimize the preference elicitation effort under two aggregation strategies. We evaluate our methods on real-world Netflix data as well as on simulated data which allows us to study different cases. We show that preference elicitation effort can be cut in up to 90% while preserving the most preferred items in the narrowed list.
Recommendation-based modeling support for data mining processes BIBAFull-Text 337-340
  Dietmar Jannach; Simon Fischer
RapidMiner is a software tool that allows users to define data mining processes based on a visual model and implements a variety of so-called "operators" for data extraction, manipulation, model learning and analysis. The large number of available operators can however make it challenging for the process designer to find the appropriate operators for the problem at hand. At the same time, some operators are only meaningful when combined with certain others.
   In this work, we evaluate different strategies of recommending additional operators to the user during the design of the process. The recommendation models are learned using a pool of several thousand existing data mining processes and evaluated in an offline experiment. The results indicate that good predictive accuracy can already be achieved with comparably simple co-occurrence based algorithms.
Scalable audience targeted models for brand advertising on social networks BIBAFull-Text 341-344
  Kunpeng Zhang; Aris M. Ouksel; Shaokun Fan; Hengchang Liu
People are using social media to generate, share, and communicate information with each other. Finding actionable insights from such big data has attracted a lot of research attentions on, for example, finding targeted user groups based on their historical on-line activities. However, existing machine learning algorithms fail to keep up with the increasing large data volume. In this paper, we develop a scalable regression-based algorithm called distributed iterative shrinkage-thresholding algorithm (DISTA) that can identify potential users. Our experiments conducted on Facebook data containing billions of users and associated activities show that DISTA with feature selection not only enables on-line audience-targeted approach for precise marketing but also performs efficiently on parallel computers.
Social collaborative filtering for cold-start recommendations BIBAFull-Text 345-348
  Suvash Sedhain; Scott Sanner; Darius Braziunas; Lexing Xie; Jordan Christensen
We examine the cold-start recommendation task in an online retail setting for users who have not yet purchased (or interacted in a meaningful way with) any available items but who have granted access to limited side information, such as basic demographic data (gender, age, location) or social network information (Facebook friends or page likes). We formalize neighborhood-based methods for cold-start collaborative filtering in a generalized matrix algebra framework that does not require purchase data for target users when their side information is available. In real-data experiments with 30,000 users who purchased 80,000+ books and had 9,000,000+ Facebook friends and 6,000,000+ page likes, we show that using Facebook page likes for cold-start recommendation yields up to a 3-fold improvement in mean average precision (mAP) and up to 6-fold improvements in Precision@k and Recall@k compared to most-popular-item, demographic, and Facebook friend cold-start recommenders. These results demonstrate the substantial predictive power of social network content, and its significant utility in a challenging problem -- recommendation for cold-start users.
Switching hybrid for cold-starting context-aware recommender systems BIBAFull-Text 349-352
  Matthias Braunhofer; Victor Codina; Francesco Ricci
Finding effective solutions for cold-starting Context-Aware Recommender Systems (CARSs) is important because usually low quality recommendations are produced for users, items or contextual situations that are new to the system. In this paper, we tackle this problem with a switching hybrid solution that exploits a custom selection of two CARS algorithms, each one suited for a particular cold-start situation, and switches between these algorithms depending on the detected recommendation situation (new user, new item or new context). We evaluate the proposed algorithms in an off-line experiment by using various contextually-tagged rating datasets. We illustrate some significant performance differences between the considered algorithms and show that they can be effectively combined into the proposed switching hybrid to cope with different types of cold-start problems.
Using graded implicit feedback for Bayesian personalized ranking BIBAFull-Text 353-356
  Lukas Lerche; Dietmar Jannach
In many application domains of recommender systems, explicit rating information is sparse or non-existent. The preferences of the current user have therefore to be approximated by interpreting his or her behavior, i.e., the implicit user feedback. In the literature, a number of algorithm proposals have been made that rely solely on such implicit feedback, among them Bayesian Personalized Ranking (BPR).
   In the BPR approach, pairwise comparisons between the items are made in the training phase and an item i is considered to be preferred over item j if the user interacted in some form with i but not with j. In real-world applications, however, implicit feedback is not necessarily limited to such binary decisions as there are, e.g., different types of user actions like item views, cart or purchase actions and there can exist several actions for an item over time.
   In this paper we show how BPR can be extended to deal with such more fine-granular, graded preference relations. An empirical analysis shows that this extension can help to measurably increase the predictive accuracy of BPR on realistic e-commerce datasets.
Inferring user interests in the Twitter social network BIBAFull-Text 357-360
  Parantapa Bhattacharya; Muhammad Bilal Zafar; Niloy Ganguly; Saptarshi Ghosh; Krishna P. Gummadi
We propose a novel mechanism to infer topics of interest of individual users in the Twitter social network. We observe that in Twitter, a user generally follows experts on various topics of her interest in order to acquire information on those topics. We use a methodology based on social annotations (proposed earlier by us) to first deduce the topical expertise of popular Twitter users, and then transitively infer the interests of the users who follow them. This methodology is a sharp departure from the traditional techniques of inferring interests of a user from the tweets that she posts or receives. We show that the topics of interest inferred by the proposed methodology are far superior than the topics extracted by state-of-the-art techniques such as using topic models (Labeled LDA) on tweets. Based upon the proposed methodology, we build a system Who Likes What, which can infer the interests of millions of Twitter users. To our knowledge, this is the first system that can infer interests for Twitter users at such scale. Hence, this system would be particularly beneficial in developing personalized recommender services over the Twitter platform.


Aspect-based opinion mining and recommendation system for restaurant reviews BIBAFull-Text 361-362
  Vaishak Suresh; Syeda Roohi; Magdalini Eirinaki
The success of a product/service in e-commerce largely depends on the user reviews. A product/service that has a higher average review or rating usually gets picked against a similar product/service with less favorable reviews. Reviews usually have an overall rating, but most of the times there are sub-texts in the review body that describe certain features/aspects of the product. This demonstration presents a system that extracts aspect-specific ratings from reviews and also recommends reviews to users based on their and other users' rating patterns.
Configuring and monitoring recommender system as a service BIBAFull-Text 363-364
  David Ben-Shimon; Alexander Alexander Tsikinovsky; Michael Friedmann; Johannes Hörle
Many small and medium e-commerce retailers and publishers use recommender systems (RS) to personalize the website content. Many of them do not have an on premise solution for doing that, but rather contact a company that delivers the RS as a service to their website. The service is then responsible for collecting and storing the data, building recommendation models, and answering recommendation requests.
   Once the integration to such a service is done, the e-commerce retailer still wish to have some control on the service. Control that allows him to configure the recommendation models, turn off/on the service, apply filters on recommendations, define fallback models and more. In this demo we provide an overview of a real backend system which enables to a typical website owner exactly these capabilities. Capabilities for controlling the RS service in terms of configuration, management and monitoring.
Content ordering based on commuting patterns BIBAFull-Text 365-366
  Travis Gingerich; Omar Alonso
Recommender systems take into account a wide range of information about both an individual user and other user's preferences in order to provide relevant content. However, one source of information that appears to be under-utilized is contextual information about the users' trajectory: where they are currently located, and where they are traveling to. We demonstrate a system that recommends the reading order of Twitter content based on the user's planned travel.
Cosibon: an E-commerce like platform enabling bricks-and-mortar stores to use sophisticated product recommender systems BIBAFull-Text 367-368
  Thorben Keller; Matthias Raffelsieper
Compared to online-retailers, bricks-and-mortar stores have only limited possibilities to understand consumer preferences, their intentions, and their feedback. The first are able to evaluate clickstream data collected on their webpages alongside the actual purchase data to put together a comprehensive view on individual customers. Bricks-and-mortar stores on the other hand have to rely solely on the evaluation of scanner data collected at the point of sale. Thus, akin to the Event Horizon in physics, describing the boundary beyond which events are unobservable, we introduce the term Receipt Horizon to describe the natural boundary beyond which a retailing company is unable to observe the behavior of individual customers. In this demo paper we present our comprehensive approach on how bricks-and-mortar stores can go beyond the Receipt Horizon. We demonstrate how existing customer loyalty programs can be leveraged by an extensive mobile app, transferring proven ecommerce concepts to physical retailers and collecting numerous novel information about consumers.
Focal: a personalized mobile news reader BIBAFull-Text 369-370
  Florent Garcin; Frederik Galle; Boi Faltings
Traditionally in mobile apps, news articles and recommendations are presented to the users as an ordered list. This ordering often reflects the freshness of the stories. Although most users are satisfied with such presentation, some users have different expectations and want to read stories related to some specific topics. In this demo, we depart from the classic list-view layout and aim at exploring other ways to present news stories to the users. We introduce Focal, a personalized mobile news reader, which implements a fisheye-inspired interface. We briefly describe its system architecture and interface.
Rival: a toolkit to foster reproducibility in recommender system evaluation BIBAFull-Text 371-372
  Alan Said; Alejandro Bellogín
Currently, it is difficult to put in context and compare the results from a given evaluation of a recommender system, mainly because too many alternatives exist when designing and implementing an evaluation strategy. Furthermore, the actual implementation of a recommendation algorithm sometimes diverges considerably from the well-known ideal formulation due to manual tuning and modifications observed to work better in some situations. RiVal -- a recommender system evaluation toolkit -- allows for complete control of the different evaluation dimensions that take place in any experimental evaluation of a recommender system: data splitting, definition of evaluation strategies, and computation of evaluation metrics. In this demo we present some of the functionality of RiVal and show step-by-step how RiVal can be used to evaluate the results from any recommendation framework and make sure that the results are comparable and reproducible.
System U: automatically deriving personality traits from social media for people recommendation BIBAFull-Text 373-374
  Hernan Badenes; Mateo N. Bengualid; Jilin Chen; Liang Gou; Eben Haber; Jalal Mahmud; Jeffrey W. Nichols; Aditya Pal; Jerald Schoudt; Barton A. Smith; Ying Xuan; Huahai Yang; Michelle X. Zhou
This paper presents a system, System U, which automatically derives people's personality traits from social media and recommends people for different tasks. The system leverages linguistic signals appearing in a person's social media activities to compute the personality portraits including Big Five personality, fundamental needs and basic human values. This system and technology can be used in a wide variety of personalized applications, such as recommending people to answer questions.
Tell me where to go and what to do next, but do not bother me BIBAFull-Text 375-376
  Hongwei Liu; Gang Wu; Guoren Wang
In this demonstration, we present a system that recommends to the user the locations and activities she/he might be interested in according to history GPS trajectories and public places of interest (POI) data. Its innovation lies in the acceptable performance of recommendations in cases where no user comments on activity types are available. Such situations are more realistic considering the restrictions on mobile devices' abilities, users' privacies, or business secret. For this purpose, we first extract stay points according to uses' trajectories, and label them with the top-k common activities which have the most possibility in terms of the POI dataset. Then, by taking stay points as observations, and activities as hidden states, a Hidden Markov model is built to learn the transfer possibilities between activities and the generation probabilities between activities and stay points. Finally, with the obtained model, our system can perform two types of recommendation, i.e. the history based recommendation and the similarity based recommendation. The results of former type are those stay points from user's own history positions. While, the latter one conducts collaborative filtering by taking history based recommendation results from similar users. The demonstration shows the running effects of the implemented prototype system, in which the Microsoft GeoLife trajectories dataset and the "DianPing.com" POI dataset were loaded. The preliminary experimental results demonstrate the feasibility.
WrapRec: an easy extension of recommender system libraries BIBAFull-Text 377-378
  Babak Loni; Alan Said
WrapRec is an easy-to-use Recommender Systems toolkit, which allows users to easily implement or wrap recommendation algorithms from other frameworks. The main goals of WrapRec are to provide a flexible I/O, evaluation mechanism and code reusability. WrapRec provides a rich data model which makes it easy to implement algorithms for different recommender system problems, such as context-aware and cross-domain recommendation. The toolkit is written in C# and the source code is publicly available on Github under the GPL license.


Workshop on new trends in content-based recommender systems: (CBRecSys 2014) BIBAFull-Text 379-380
  Toine Bogers; Marijn Koolen; Iván Cantador
While content-based recommendation has been applied successfully in many different domains, it has not seen the same level of attention as collaborative filtering techniques have. However, there are many recommendation domains and applications where content and metadata play a key role, either in addition to or instead of ratings and implicit usage data. For some domains, such as movies, the relationship between content and usage data has seen thorough investigation already, but for many other domains, such as books, news, scientific articles, and Web pages we still do not know if and how these data sources should be combined to provided the best recommendation performance. The CBRecSys 2014 workshop aims to address this by providing a dedicated venue for papers dedicated to all aspects of content-based recommendation.
Overview of ACM RecSys CrowdRec 2014 workshop: crowdsourcing and human computation for recommender systems BIBAFull-Text 381-382
  Martha Larson; Paolo Cremonesi; Alexandros Karatzoglou
The CrowdRec workshop brings together the recommender system community for discussion and exchange of ideas. Its goal is to allow the potential of human computation and crowdsourcing to be exploited fully and sustainably, leading to the development of improved recommendation and information filtering technologies. Currently, the complete range of possible intelligent contributions that recommender systems could elicit from users is under-explored, and its full extent is unknown. Critical questions addressed in the workshop include how to: formulate crowdtasks, match tasks with crowdmembers, ensure the quality of crowd input, and integrate feedback from the crowd in an optimal manner to improve recommendation. Further, crowdsourcing can also be exploited for system design and system evaluation.
RecSys'14 joint workshop on interfaces and human decision making for recommender systems BIBAFull-Text 383-384
  Nava Tintarev; John O'Donovan; Peter Brusilovsky; Alexander Felfernig; Giovanni Semeraro; Pasquale Lops
As an interactive intelligent system, recommender systems are developed to give predictions that match users preferences. Since the emergence of recommender systems, a large majority of research focuses on objective accuracy criteria and less attention has been paid to how users interact with the system and the efficacy of interface designs from the end-user perspective. The field has reached a point where it is ready to look beyond algorithms, into users interactions, decision making processes and overall experience. Accordingly, the goals of this workshop (IntRS@RecSys) are to explore the human aspects of recommender systems, with a particular focus on the impact of interfaces and interaction design on decision-making and user experiences with recommender systems, and to explore methodologies to evaluate these human aspects of the recommendation process that go beyond traditional automated approaches.
Second workshop on large-scale recommender systems: research and best practice (LSRS 2014) BIBAFull-Text 385-386
  Tao Ye; Danny Bickson; Qiang Yan
With the increase of data collected and computation power available, modern recommender systems are ever facing new challenges. While complex models are developed in academia, industry practice seems to focus on relatively simple techniques that can deal with the magnitude of data and the need to distribute the computation. The workshop on large-scale recommender systems (LSRS) is a meeting place for industry and academia to discuss the current and future challenges of applied large-scale recommender systems.
Recommender systems challenge 2014 BIBAFull-Text 387-388
  Alan Said; Simon Dooms; Babak Loni; Domonkos Tikk
The 2014 ACM Recommender Systems Challenge invited researchers and practitioners to work towards a common goal, this goal being the prediction of users engagement in movie ratings expressed on Twitter. More than 200 participants sought to join the challenge and work on the new dataset released in its scope. The participants were asked to develop new algorithms to predict user engagement and evaluate them in a common setting, ensuring that the comparison was objective and unbiased, within the challenge.
Controlled experimentation in recommendations, ranking & response prediction BIBAFull-Text 389
  Ya Xu; Rajesh Parekh; Juliette Aurisset
In this workshop, we have several leading industry experts sharing their knowledge and experiences on how online controlled experiments are used in their applications. The individual talks are followed by a panel discussion.
First workshop on recommendation systems for television and online video: (RecSysTV 2014) BIBAFull-Text 391-392
  Danny Bickson; John Hannon; Jan Neumann; Hassan Sayyadi
For many households the television is the central entertainment hub in their home, and the average TV viewer spends about half of their leisure time in front of a TV. At any given moment, a customer has hundreds to thousands of entertainment choices available, which makes some sort of automatic, personalized recommendations desirable to help consumers deal with the often overwhelming number of choices they face. The First Workshop on Recommendation Systems for Television and Online Video aims to offer a place to present and discuss the latest academic and industrial research on recommendation systems for this challenging and exciting application domain.
REDD 2014 -- international workshop on recommender systems evaluation: dimensions and design BIBAFull-Text 393-394
  Panagiotis Adamopoulos; Alejandro Bellogín; Pablo Castells; Paolo Cremonesi; Harald Steck
Evaluation is a cardinal issue in recommender systems; as in any technical discipline, it highlights to a large extent the problems that need to be solved by the field and, hence, leads the way for algorithmic research and development in the community. Yet, in the field of recommender systems, there still exists considerable disparity in evaluation methods, metrics and experimental designs, as well as a significant mismatch between evaluation methods in the lab and what constitutes an effective recommendation for real users and businesses. Even after the relevant quality dimensions have been defined, a clear evaluation protocol should be specified in detail and agreed upon, allowing for the comparison of results and experiments conducted by different authors. This would enable any contribution to the same problem to be incremental and add up on top of previous work, rather than grow sideways. The REDD 2014 workshop seeks to provide an informal forum to tackle such issues and to move towards better understood and shared evaluation methodologies, allowing one to leverage the efforts and the workforce of the academic community towards meaningful and relevant directions in real-world developments.
The sixth ACM RecSys workshop on recommender systems and the social web BIBAFull-Text 395
  Dietmar Jannach; Jill Freyne; Werner Geyer; Ido Guy; Andreas Hotho; Bamshad Mobasher
The emergence of what is called the social web and the continuing stream of new applications and community-based platforms including Facebook, Twitter, LinkedIn and others had a substantial impact on recommender systems research and practice over the last years in different ways.
   First, today's web users are more willing to share more about themselves than before the Web 2.0, thus providing more information sources that can be leveraged in the user modeling and recommendation process. Furthermore, the newly available information sources can not only be used to optimize the recommendations for an individual user, but can also help to identify more general patterns and trends in the behavior of the community that can be exploited by other applications.
   Second, personalization, information filtering and recommendation are often the central functionality of many of these social web based applications. On typical social networks, users for example get recommendations for news to read, songs to listen to, groups to join, friends to follow, people to connect or jobs that might be interesting.
   These developments lead to different challenges to be addressed in recommender systems research. On the one hand, for example, the question arises of how to effectively combine the huge variety of information sources for improved recommendations. On the other hand, regarding the new opportunities for applying recommender systems in social web environments, in many cases new techniques are required to address the particularities of the domain or to deal with scalability issues.
   The ACM RecSys 2014 Workshop on Recommender Systems and the Social Web aims to be a platform for researchers from academia and industry as well as for practitioners to present and discuss the various challenges and possible solutions related to all aspects of social web recommendations. The call for papers correspondingly covered a variety of topics in this area including all sorts of applications of recommender systems technology and their interfaces; collective knowledge creation and topic emergence; context-aware and group recommendation approaches; and case studies and empirical evaluations.
   This year's workshop was already the sixth in a series of successful workshops co-located with the ACM Conference on Recommender Systems since 2009. Again, we received several submissions from researchers from academia and industry which were thoroughly reviewed and selected for presentation at the workshop by a program committee of international experts in the field.
   The papers submitted to the workshop addressed a number of different topics and put forward novel proposals to build social web recommender system. In the context of applying recommendation technology to information personalization and resource ranking problems in Social Web environments, the submitted papers for example dealt with the problem of ranking community-provided product reviews based on opinion mining or with the recommendation of friends on social networks. As an example of how to leverage Social Web information to build better systems, one of the works proposed to analyze the characteristics of publicly shared music playlists to better understand how future music recommendation systems should be designed. Finally, another contribution from industry addressed challenges and lessons learned when building large-scale collaborative filtering solutions on Social Web platforms in a real-world environment.


The recommender problem revisited BIBAFull-Text 397-398
  Xavier Amatriain
In 2006, Netflix announced a $1M prize competition to advance recommendation algorithms. The recommendation problem was simplified as the accuracy in predicting a user rating measured by the Root Mean Squared Error (RMSE). While that formulation helped get the attention of the research community in the area, it may have put an excessive focus on what is simply one of the many possible approaches to recommendations.
   In this tutorial we will describe different components of modern recommender systems such as: personalized ranking, similarity, explanations, context-awareness, or search as recommendation. We will use the Netflix use case as a driving example of a prototypical industrial-scale recommender system that has evolved from focusing on rating prediction to full page optimization. We will also review the usage of modern algorithmic approaches that include algorithms such as Factorization Machines [9], Restricted Boltzmann Machines [10], SimRank [7], Deep Neural Networks, or Listwise Learning-to-rank [6, 12, 11].
   The original recommendation problem was formulated around the existence of explicit user ratings. However, recommender systems can be built using different kinds of data including implicit behavioral data, social connections, or demographics. In this tutorial we will review the usage of different data types and discuss what the availability of Big Data has brought into the research area.
   Finally, and also related to the availability of large quantities of data, we will talk about how system and architectural decisions play a role in understanding the recommender problem.
   This tutorial is in part based on recent publications by the author [5, 1, 8, 2, 4, 3].
Personalized location recommendation on location-based social networks BIBAFull-Text 399-400
  Huiji Gao; Jiliang Tang; Huan Liu
Personalized location recommendation is a special topic of recommendation. It is related to human mobile behavior in the real world regarding various contexts including spatial, temporal, social, and content. The development of this topic is subject to the availability of human mobile data. The recent rapid growth of location-based social networks has alleviated such limitation, which promotes the development of various location recommendation techniques. This tutorial offers an overview, in a data mining perspective, of personalized location recommendation on location-based social networks. It introduces basic concepts, summarizes unique LBSN characteristics and research opportunities, elaborates associated challenges, reviews state-of-the-art algorithms with illustrative examples and real-world LBSN datasets, and discusses effective evaluation methods.
Tutorial on cross-domain recommender systems BIBAFull-Text 401-402
  Iván Cantador; Paolo Cremonesi
Cross-domain recommender systems aim to generate or enhance personalized recommendations in a target domain by exploiting knowledge (mainly user preferences) from other source domains. This may beneficial for generating better recommendations, e.g. mitigating the cold-start and sparsity problems in a target domain, and enabling personalized cross-selling for items from multiple domains. In this tutorial, we formalize the cross-domain recommendation problem, categorize and survey state of the art cross-domain recommender systems, discuss related evaluation issues, and outline future research directions on the topic.
Social recommender system tutorial BIBAFull-Text 403-404
  Ido Guy; Werner Geyer
In recent years, with the proliferation of the social web, users are increasingly exposed to social overload and the designers of social web sites are challenged to attract and retain their user basis. Social recommender systems are becoming an integral part of virtually any leading website, playing a key factor in its success: First, they aim to address the overload problem by helping users to find relevant content. Second, they can provide recommendations for content creation, increasing participation and user retention. In this tutorial, we will review the broad domain of social recommender systems, their application for the social web, the underlying techniques and methodologies; the data in use, recommended entities, and target population; evaluation techniques; and open issues and challenges.

Doctoral consortium

Hybridisation techniques for cold-starting context-aware recommender systems BIBAFull-Text 405-408
  Matthias Braunhofer
Context-Aware Recommender Systems (CARSs) suffer from the cold-start problem, i.e., the inability to provide accurate recommendations for new users, items or contextual situations. In this research, we aim at solving this problem by exploiting various hybridisation techniques, from simple heuristic-based solutions to complex adaptive solutions, in order to take advantage of the strengths of different CARS algorithms while avoiding their weaknesses in a given (cold-start) situation. Our initial research based on offline experiments using various contextually-tagged rating datasets has shown that basic CARS algorithms perform very differently in different recommendation scenarios, and that they can be effectively hybridised to achieve an overall optimal performance. Further research is now required to find the optimal method for hybridisation.
Moving beyond linearity and independence in top-N recommender systems BIBAFull-Text 409-412
  Evangelia Christakopoulou
This paper suggests a number of research directions in which the recommender systems can improve their quality, by moving beyond the assumptions of linearity and independence that are traditionally made. These assumptions, while producing effective and meaningful results, can be suboptimal, as in lots of cases they do not represent the real datasets. In this paper, we discuss three different ways to address some of the previous constraints. More specifically, we focus on the development of methods capturing higher-order relations between the items, cross-feature interactions and intra-set dependencies which can potentially lead to a considerable enhancement of the recommendation accuracy.
Enhancing personalization and learner engagement through context-aware recommendation in TEL BIBAFull-Text 413-415
  Betty Mayeku
Providing a personalized learning experience that caters for individual learner's needs within the learner's context of use is crucial in achieving effective learning in a technology enhanced learning (TEL) environment. However, achieving personalization amidst diverse and rich environment within which learning takes place still remains a major challenge. Though adaption has been proposed to provide learners with learning experiences that are tailored to their particular educational needs, however, one of its limitation is user involvement. Absolute machine control is not always desirable considering the intellectual presence of human-beings. Furthermore learner engagement is one of crucial elements for realizing effective learning. Therefore, this study aims at exploring how context-awareness can support a personalized and engaged learning experience. The study in particular proposes the use of context-aware recommendation mechanism and the consideration of learner's preference to learning as approaches for achieving personalization and learner engagement.
Improving recommender systems: user roles and lifecycles BIBAFull-Text 417-420
  Tien T. Nguyen
In the era of big data, it is usually agreed that the more data we have, the better results we can get. However, for some domains that heavily depend on user inputs (such as recommender systems), the performance evaluation metrics are sensitive to the amount of noise introduced by users. Such noise can be from users who only wanted to explore the systems, and thus did not spend efforts to provide accurate inputs. Noise can also be introduced by the methods of collecting user ratings. In my dissertation, I study how user data can affect prediction accuracies and performances of recommendation algorithms. To that end, I investigate how the data collection methods and the life cycles of users affect the prediction accuracies and the performance of recommendation algorithms.
Modeling the effect of people's preferences and social forces on adopting and sharing items BIBAFull-Text 421-424
  Amit Sharma
Recommender systems within social networks face three distinct challenges: suggesting what to consume/adopt, what to share and who to share it with. For all three cases, my and others' research work shows that people's decisions to adopt and share depend not only on their preferences for items, but also on social forces such as influence, conformity and identity management. Modeling the combined effects of people's preferences and social forces can lead to socially-aware recommender algorithms and interfaces as well more accurate models of information diffusion.
   I take a bottom-up approach to understanding how items are shared or adopted in a social network. First, I conduct behavioral experiments that give insights about, and allow to model the processes by which people decide to share or adopt items. Second, I use data from multiple social networking websites to validate and extend these models and develop tractable algorithms to predict people's decisions on items.
   This paper presents preliminary models for adoption and sharing along with future directions towards more accurate models. Results of my current work indicate that people consider their own preferences for items more than the recipients' when sharing and share only highly liked items. When adopting, people's preferences towards items matter, but so do annotations that accompany recommendations based on social influences; I show how their relative effects can be modeled as a mixture distribution.
Choicla: towards domain-independent decision support for groups of users BIBAFull-Text 425-428
  Martin Stettinger
Group recommendation technologies have been successfully applied in domains such as interactive television, music, and tourist destinations. Existing technologies are focusing on specific domains and do not offer the possibility of supporting different kinds of decision scenarios. The Choicla group decision support environment advances the state of the art by supporting decision scenarios in a domain-independent fashion. In this paper we give an overview of the Choicla environment and report the results of a first user study which focused on system usability.
Weighted hybrid recommendation for heterogeneous networks BIBAFull-Text 429-432
  Fatemeh Vahedian
Social media sites accumulate a wide variety of information about users: likes and ratings, friend and follower links, annotations, posts, media uploads, just to name a few. Key challenges for recommender systems research are (a) to synthesize of all of this data into an integrated recommendation model and (b) to support a wide variety of recommendation types simultaneously (items, friends, tags, etc.) One approach that has been explored in recent research is to view this multi-faceted data as a heterogeneous network and use network-based methods of generating recommendations. However, most such approaches involve computationally-intensive model generation resulting in a single-purpose recommender system. Our approach is to create a component-based hybrid model whose components can be reused for multiple recommendation tasks. In this paper, we show how this model can be applied to heterogeneous networks.
Browser-oriented universal cross-site recommendation and explanation based on user browsing logs BIBAFull-Text 433-436
  Yongfeng Zhang
Our research aims to bridge the gap between different websites to provide cross-site recommendations based on browsers. Recent advances have made recommender systems essential to various online applications, such as e-commerce, social networks, and review service websites. However, practical systems mainly focus on recommending inner-site homogeneous items. For example, a movie review website usually recommends other movies within the site when a user has enjoyed a movie online. However, it would be exciting if the system recommends some attractive products related to this movie from some e-commerce websites like Amazon or eBay.
   Such an ability to provide heterogeneous cross-site recommendations may shed light on brand new and promising business models, which could benefit both the online shops in expanding the marketing efforts, and the online users in discovering items of interest from a wider scope. In this research, we propose and formalize the problem of universal recommendation, record and analyze user browsing actions in web browsers, and provide browser-oriented cross-site recommendations when the users are surfing online.
Deviation-based and similarity-based contextual SLIM recommendation algorithms BIBAFull-Text 437-440
  Yong Zheng
Context-aware recommender systems (CARS) have been demonstrated to be able to enhance recommendations by adapting users' preferences to different contextual situations. In recent years, several CARS algorithms have been developed to incorporated into the recommender systems. For example, differential context modeling (DCM) was modified based on traditional neighborhood collaborative filtering (NBCF), context-aware matrix factorization (CAMF) coupled contextual dependency with the matrix factorization technique (MF), and tensor factorization directly models contexts as additional dimensions in the multi-dimensional space, etc. CAMF works well but it is difficult to interpret the latent features in the algorithm. DCM is good for explanation but it may only work well on data sets with dense contextual ratings. Recently, we successfully incorporate contexts into Sparse LInear Method (SLIM) and develop contextual SLIM (CSLIM) recommendation algorithms which take advantages of both NBCF and MF. CSLIM are demonstrated as more effective and promising context-aware recommenders. In this work, we provide the introduction on the framework of the CSLIM algorithms, present the current state of the research, and discuss our ongoing future work to develop and improve our CSLIM models for context-aware recommendations.