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

Proceedings of the 2011 ACM Conference on Recommender Systems

Fullname:Proceedings of the Fifth ACM Conference on Recommender Systems
Editors:Bamshad Mobasher; Robin Burke; Dietmar Jannach; Gediminas Adomavicius
Location:Chicago, Illinois
Dates:2011-Oct-23 to 2011-Oct-27
Standard No:ISBN: 1-4503-0683-7, 978-1-4503-0683-6; ACM DL: Table of Contents hcibib: RecSys11
Links:Conference Home Page
  1. Keynote talks
  2. Invited tutorials: tutorial program
  3. Algorithms
  4. Recommenders and the social web
  5. Multi-dimensional recommendation, context-awareness and group recommendation
  6. Methodological issues, evaluation metrics and tools
  7. Human factors
  8. Emerging recommendation domains
  9. Poster session 1
  10. Poster session 2
  11. Industry half-day session: demos and speaker Lapers
  12. Doctoral symposium
  13. Workshop outlines

Keynote talks

Recommender systems at the long tail BIBAFull-Text 1-6
  Neel Sundaresan
Recommender systems form the core of e-commerce systems. In this paper we take a top-down view of recommender systems and identify challenges, opportunities, and approaches in building recommender systems for a marketplace platform. We use eBay as an example where the elaborate interaction offers a number opportunities for creative recommendations. However, eBay also poses complexities resulting from high sparsity of relationships. Our discussion can be generalized beyond eBay to other marketplaces.

Invited tutorials: tutorial program

Music recommendation and discovery revisited BIBAFull-Text 7-8
  Oscar Celma; Paul Lamere
The world of music is changing rapidly. We are now just a few clicks away from being able to listen to nearly any song that has ever been recorded. This easy access to a nearly endless supply of music is changing how we explore, discover, share and experience music.
   As the world of online music grows, music recommendation and discovery tools become an increasingly important way for music listeners to engage with music. Commercial recommenders such as Last.fm, iTunes Genius and Pandora have enjoyed commercial and critical success. But how well do these systems really work? How good are the recommendations? How far into the "long tail" do these recommenders reach?
   In this tutorial we look at the current state-of-the-art in music recommendation and discovery. We examine current commercial and research systems, focusing on the advantages and the disadvantages of the various recommendation strategies. We look at some of the challenges in building music recommenders and we explore some of the novel techniques that are being used to improve future music recommendation and discovery systems.
Robustness of recommender systems BIBAFull-Text 9-10
  Neil J. Hurley
The possibility of designing user rating profiles to deliberately and maliciously manipulate the recommendation output of a collaborative filtering system was first raised in 2002. One scenario proposed was that an author, motivated to increase recommendations of his book, might create a set of false profiles that rate the book highly, in an effort to artificially promote the ratings given by the system to genuine users. Several attack models have been proposed and the performance of these attacks in terms of influencing the system predictions has been evaluated for a number of memory-based and model-based collaborative filtering algorithms. Moreover, strategies have been proposed to enhance the robustness of existing algorithms and new algorithms have been proposed with built-in attack resistance. This tutorial will review the work that has taken place in the last decade on robustness of recommendation algorithms and seek to examine the question of the importance of robustness in future research.
Recommendations as a conversation with the user BIBAFull-Text 11-12
  Daniel Tunkelang
Recommender systems provide users with products or content intended to satisfy their information needs. The primary evaluation measures for recommender systems emphasize either the perceived relevance of the recommendations or the actions driven by those recommendations (e.g., purchases on ecommerce sites or clicks on news and social networking sites). Unfortunately, this transactional emphasis neglects the inherently interactive nature of the user experience.
   This tutorial explores recommendations as part of a conversation between users and systems. A conversational approach should provide transparency, control, and guidance. Transparency means that users understand why systems offer particular recommendations. Control means that users can explicitly manipulate the behavior of recommender systems based on personal needs and preferences. Guidance means that systems offers plausible and predictable next steps rather than requiring users to guess the consequences of their interactions.
   Finally, there are psychological factors -- in particular, the faith that users place in the recommender system's effectiveness. Since users develop mental models of recommender systems, the system should become more predictable with repeated use.
   The tutorial does not require any special background in interfaces or usability. Rather, it summarizes the best lessons from research and industry, offering concrete examples and practical techniques to make recommender systems most effective for users.


Generalizing matrix factorization through flexible regression priors BIBAFull-Text 13-20
  Liang Zhang; Deepak Agarwal; Bee-Chung Chen
Predicting user "ratings" on items is a crucial task in recommender systems. Matrix factorization methods that computes a low-rank approximation of the incomplete user-item rating matrix provide state-of-the-art performance, especially for users and items with several past ratings (warm starts). However, it is a challenge to generalize such methods to users and items with few or no past ratings (cold starts). Prior work [4][32] have generalized matrix factorization to include both user and item features for performing better regularization of factors as well as provide a model for smooth transition from cold starts to warm starts. However, the features were incorporated via linear regression on factor estimates. In this paper, we generalize this process to allow for arbitrary regression models like decision trees, boosting, LASSO, etc. The key advantage of our approach is the ease of computing -- any new regression procedure can be incorporated by "plugging" in a standard regression routine into a few intermediate steps of our model fitting procedure. With this flexibility, one can leverage a large body of work on regression modeling, variable selection, and model interpretation. We demonstrate the usefulness of this generalization using the MovieLens and Yahoo! Buzz datasets.
Modeling item selection and relevance for accurate recommendations: a Bayesian approach BIBAFull-Text 21-28
  Nicola Barbieri; Gianni Costa; Giuseppe Manco; Riccardo Ortale
We propose a Bayesian probabilistic model for explicit preference data. The model introduces a generative process, which takes into account both item selection and rating emission to gather into communities those users who experience the same items and tend to adopt the same rating pattern. Each user is modeled as a random mixture of topics, where each topic is characterized by a distribution modeling the popularity of items within the respective user-community and by a distribution over preference values for those items. The proposed model can be associated with a novel item-relevance ranking criterion, which is based both on item popularity and user's preferences. We show that the proposed model, equipped with the new ranking criterion, outperforms state-of-art approaches in terms of accuracy of the recommendation list provided to users on standard benchmark datasets.
Shared collaborative filtering BIBAFull-Text 29-36
  Yu Zhao; Xinping Feng; Jianqiang Li; Bo Liu
Traditional collaborative filtering (CF) methods suffer from sparse or even cold-start problems, especially for new established recommenders. However, since there are now quite a few recommender systems already existing in good working order, their data should be valuable to the new-start recommenders. This paper proposes shared collaborative filtering approach to leverage the data from other parties (contributor party) to improve own (beneficiary party's) CF performance, and at the same time the privacy of other parties cannot be compromised. Item neighborhood list is chosen as the shared data from the contributor party with considering differential privacy. And an innovative algorithm called neighborhood boosting is proposed to make the beneficiary party leverage the shared data. MovieLens and Netflix data sets are considered as two parties to simulate and evaluate the proposed shared CF approach. The experiment results validate the positive effects of shared CF for increasing the recommendation accuracy of the beneficiary party. Especially when the beneficiary party's data is quite sparse, the performance can be increased by around 10%. The experiments also show that shared CF even outperforms the methods that incorporate the detailed original rating scores of the contributor party without considering the privacy issues. The proposed shared CF approach obtains a win-win situation for both performance and privacy.
Wisdom of the better few: cold start recommendation via representative based rating elicitation BIBAFull-Text 37-44
  Nathan N. Liu; Xiangrui Meng; Chao Liu; Qiang Yang
Recommender systems have to deal with the cold start problem as new users and/or items are always present. Rating elicitation is a common approach for handling cold start. However, there still lacks a principled model for guiding how to select the most useful ratings. In this paper, we propose a principled approach to identify representative users and items using representative-based matrix factorization. Not only do we show that the selected representatives are superior to other competing methods in terms of achieving good balance between coverage and diversity, but we also demonstrate that ratings on the selected representatives are much more useful for making recommendations (about 10% better than competing methods). In addition to illustrating how representatives help solve the cold start problem, we also argue that the problem of finding representatives itself is an important problem that would deserve further investigations, for both its practical values and technical challenges.

Recommenders and the social web

Personalized PageRank vectors for tag recommendations: inside FolkRank BIBAFull-Text 45-52
  Heung-Nam Kim; Abdulmotaleb El Saddik
This paper looks inside FolkRank, one of the well-known folksonomy-based algorithms, to present its fundamental properties and promising possibilities for improving performance in tag recommendations. Moreover, we introduce a new way to compute a differential approach in FolkRank by representing it as a linear combination of the personalized PageRank vectors. By the linear combination, we present FolkRank's probabilistic interpretation that grasps how FolkRank works on a folksonomy graph in terms of the random surfer model. We also propose new FolkRank-like methods for tag recommendations to efficiently compute tags' rankings and thus reduce expensive computational cost of FolkRank. We show that the FolkRank approaches are feasible to recommend tags in real-time scenarios as well. The experimental evaluations show that the proposed methods provide fast tag recommendations with reasonable quality, as compared to FolkRank. Additionally, we discuss the diversity of the top n tags recommended by FolkRank and its variants.
A generalized stochastic block model for recommendation in social rating networks BIBAFull-Text 53-60
  Mohsen Jamali; Tianle Huang; Martin Ester
The rapidly increasing availability of online social networks and the well-known effect of social influence have motivated research on social-network based recommenders. Social influence and selection together lead to the formation of communities of like-minded and well connected users. Exploiting the clustering of users and items is one of the most important approaches for model-based recommendation. Users may belong to multiple communities or groups, but only a few clustering algorithms allow clusters to overlap. One of these algorithms is the probabilistic EM clustering method, which assumes that data is generated from a mixture of Gaussian models. The mixed membership stochastic block model (MMB) transfers the idea of EM clustering from conventional, non-relational data to social network data. In this paper, we introduce a generalized stochastic blockmodel (GSBM) that models not only the social relations but also the rating behavior. This model learns the mixed group membership assignments for both users and items in an SRN. GSBM can predict the future behavior of users, both the rating of items and creation of links to other users. We performed experiments on two real life datasets from Epinions.com and Flixster.com, demonstrating the accuracy of the proposed GSBM for rating prediction as well as link prediction.
Product recommendation and rating prediction based on multi-modal social networks BIBAFull-Text 61-68
  Panagiotis Symeonidis; Eleftherios Tiakas; Yannis Manolopoulos
Online Social Rating Networks (SRNs) such as Epinions and Flixster, allow users to form several implicit social networks, through their daily interactions like co-commenting on the same products, or similarly co-rating products. The majority of earlier work in Rating Prediction and Recommendation of products (e.g. Collaborative Filtering) mainly takes into account ratings of users on products. However, in SRNs users can also built their explicit social network by adding each other as friends. In this paper, we propose Social-Union, a method which combines similarity matrices derived from heterogeneous (unipartite and bipartite) explicit or implicit SRNs. Moreover, we propose an effective weighting strategy of SRNs influence based on their structured density. We also generalize our model for combining multiple social networks. We perform an extensive experimental comparison of the proposed method against existing rating prediction and product recommendation algorithms, using synthetic and two real data sets (Epinions and Flixter). Our experimental results show that our Social-Union algorithm is more effective in predicting rating and recommending products in SRNs.
Distributed rating prediction in user generated content streams BIBAFull-Text 69-76
  Sibren Isaacman; Stratis Ioannidis; Augustin Chaintreau; Margaret Martonosi
Recommender systems predict user preferences based on a range of available information. For systems in which users generate streams of content (e.g., blogs, periodically-updated newsfeeds), users may rate the produced content that they read, and be given accurate predictions about future content they are most likely to prefer. We design a distributed mechanism for predicting user ratings that avoids the disclosure of information to a centralized authority or an untrusted third party: users disclose the rating they give to certain content only to the user that produced this content.
   We demonstrate how rating prediction in this context can be formulated as a matrix factorization problem. Using this intuition, we propose a distributed gradient descent algorithm for its solution that abides with the above restriction on how information is exchanged between users. We formally analyse the convergence properties of this algorithm, showing that it reduces a weighted root mean square error of the accuracy of predictions. Although our algorithm may be used many different ways, we evaluate it on the Netflix data set and prediction problem as a benchmark. In addition to the improved privacy properties that stem from its distributed nature, our algorithm is competitive with current centralized solutions. Finally, we demonstrate the algorithm's fast convergence in practice by conducting an online experiment with a prototype user-generated content exchange system implemented as a Facebook application.

Multi-dimensional recommendation, context-awareness and group recommendation

Multi-criteria service recommendation based on user criteria preferences BIBAFull-Text 77-84
  Liwei Liu; Nikolay Mehandjiev; Dong-Ling Xu
Research in recommender systems is now starting to recognise the importance of multiple selection criteria to improve the recommendation output. In this paper, we present a novel approach to multi-criteria recommendation, based on the idea of clustering users in "preference lattices" (partial orders) according to their criteria preferences. We assume that some selection criteria for an item (product or a service) will dominate the overall ranking, and that these dominant criteria will be different for different users. Following this assumption, we cluster users based on their criteria preferences, creating a "preference lattice". The recommendation output for a user is then based on ratings by other users from the same or close clusters. Having introduced the general approach of clustering, we proceed to formulate three alternative recommendation methods instantiating the approach: (a) using the aggregation function of the criteria, (b) using the overall item ratings, and (c) combining clustering with collaborative filtering. We then evaluate the accuracy of the three methods using a set of experiments on a service ranking dataset, and compare them with a conventional collaborative filtering approach extended to cover multiple criteria. The results indicate that our third method, which combines clustering and extended collaborative filtering, produces the highest accuracy.
The effect of context-aware recommendations on customer purchasing behavior and trust BIBAFull-Text 85-92
  Michele Gorgoglione; Umberto Panniello; Alexander Tuzhilin
Despite the growing popularity of Context-Aware Recommender Systems (CARSs), only limited work has been done on how contextual recommendations affect the behavior of customers in real-life settings. In this paper, we study the effects of contextual recommendations on the purchasing behavior of customers and their trust in the provided recommendations. In particular, we did live controlled experiments with real customers of a major commercial Italian retailer in which we compared the customers' purchasing behavior and measured their trust in the provided recommendations across the contextual, content-based and random recommendations. As a part of this study, we have investigated the role of accuracy and diversity of recommendations on customers' behavior and their trust in the provided recommendations for the three types of RSes. We have demonstrated that the context-aware RS outperformed the other two RSes in terms of accuracy, trust and other economics-based performance metrics across most of our experimental settings.
Random walk based entity ranking on graph for multidimensional recommendation BIBAFull-Text 93-100
  Sangkeun Lee; Sang-il Song; Minsuk Kahng; Dongjoo Lee; Sang-goo Lee
In many applications, flexibility of recommendation, which is the capability of handling multiple dimensions and various recommendation types, is very important. In this paper, we focus on the flexibility of recommendation and propose a graph-based multidimensional recommendation method. We consider the problem as an entity ranking problem on the graph which is constructed using an implicit feedback dataset (e.g. music listening log), and we adapt Personalized PageRank algorithm to rank entities according to a given query that is represented as a set of entities in the graph. Our model has advantages in that not only can it support the flexibility, but also it can take advantage of exploiting indirect relationships in the graph so that it can perform competitively with the other existing recommendation methods without suffering from the sparsity problem.
Group recommendation using feature space representing behavioral tendency and power balance among members BIBAFull-Text 101-108
  Shunichi Seko; Takashi Yagi; Manabu Motegi; Shinyo Muto
This paper proposes an algorithm to estimate appropriate or novel content for groups of people who know each other such as friends, couples, and families. To achieve high recommendation accuracy, we focus on "Groupality", the entity or entities that characterize groups such as the tendency of content selection and the relationships among group members. Our algorithm calculates recommendation scores using a feature space that consists of the behavioral tendency of a group and the power balance among group members based on individual preference and the behavioral history of group. After gathering the behavioral history of subject groups when watching TV, we verify that our proposed algorithm can recommend appropriate content, and find novel content. Evaluations show that our proposal achieves higher performance than existing methods.

Methodological issues, evaluation metrics and tools

Rank and relevance in novelty and diversity metrics for recommender systems BIBAFull-Text 109-116
  Saúl Vargas; Pablo Castells
The Recommender Systems community is paying increasing attention to novelty and diversity as key qualities beyond accuracy in real recommendation scenarios. Despite the raise of interest and work on the topic in recent years, we find that a clear common methodological and conceptual ground for the evaluation of these dimensions is still to be consolidated. Different evaluation metrics have been reported in the literature but the precise relation, distinction or equivalence between them has not been explicitly studied. Furthermore, the metrics reported so far miss important properties such as taking into consideration the ranking of recommended items, or whether items are relevant or not, when assessing the novelty and diversity of recommendations.
   We present a formal framework for the definition of novelty and diversity metrics that unifies and generalizes several state of the art metrics. We identify three essential ground concepts at the roots of novelty and diversity: choice, discovery and relevance, upon which the framework is built. Item rank and relevance are introduced through a probabilistic recommendation browsing model, building upon the same three basic concepts. Based on the combination of ground elements, and the assumptions of the browsing model, different metrics and variants unfold. We report experimental observations which validate and illustrate the properties of the proposed metrics.
OrdRec: an ordinal model for predicting personalized item rating distributions BIBAFull-Text 117-124
  Yehuda Koren; Joe Sill
We propose a collaborative filtering (CF) recommendation framework, which is based on viewing user feedback on products as ordinal, rather than the more common numerical view. This way, we do not need to interpret each user feedback value as a number, but only rely on the more relaxed assumption of having an order among the different feedback ratings. Such an ordinal view frequently provides a more natural reflection of the user intention when providing qualitative ratings, allowing users to have different internal scoring scales. Moreover, we can address scenarios where assigning numerical scores to different types of user feedback would not be easy. Our approach is based on a pointwise ordinal model, which allows it to linearly scale with data size. The framework can wrap most collaborative filtering algorithms, upgrading those algorithms designed to handle numerical values into being able to handle ordinal values. In particular, we demonstrate our framework with wrapping a leading matrix factorization CF method. A cornerstone of our method is its ability to predict a full probability distribution of the expected item ratings, rather than only a single score for an item. One of the advantages this brings is a novel approach to estimating the confidence level in each individual prediction. Compared to previous approaches to confidence estimation, ours is more principled and empirically superior in its accuracy. We demonstrate the efficacy of the approach on some of the largest publicly available datasets, the Netflix data, and the Yahoo! Music data.
Item popularity and recommendation accuracy BIBAFull-Text 125-132
  Harald Steck
Recommendations from the long tail of the popularity distribution of items are generally considered to be particularly valuable. On the other hand, recommendation accuracy tends to decrease towards the long tail. In this paper, we quantitatively examine this trade-off between item popularity and recommendation accuracy. To this end, we assume that there is a selection bias towards popular items in the available data. This allows us to define a new accuracy measure that can be gradually tuned towards the long tail. We show that, under this assumption, this measure has the desirable property of providing nearly unbiased estimates concerning recommendation accuracy. In turn, this also motivates a refinement for training collaborative-filtering approaches. In various experiments with real-world data, including a user study, empirical evidence suggests that only a small, if any, bias of the recommendations towards less popular items is appreciated by users.
Rethinking the recommender research ecosystem: reproducibility, openness, and LensKit BIBAFull-Text 133-140
  Michael D. Ekstrand; Michael Ludwig; Joseph A. Konstan; John T. Riedl
Recommender systems research is being slowed by the difficulty of replicating and comparing research results. Published research uses various experimental methodologies and metrics that are difficult to compare. It also often fails to sufficiently document the details of proposed algorithms or the evaluations employed. Researchers waste time reimplementing well-known algorithms, and the new implementations may miss key details from the original algorithm or its subsequent refinements. When proposing new algorithms, researchers should compare them against finely-tuned implementations of the leading prior algorithms using state-of-the-art evaluation methodologies. With few exceptions, published algorithmic improvements in our field should be accompanied by working code in a standard framework, including test harnesses to reproduce the described results. To that end, we present the design and freely distributable source code of LensKit, a flexible platform for reproducible recommender systems research. LensKit provides carefully tuned implementations of the leading collaborative filtering algorithms, APIs for common recommender system use cases, and an evaluation framework for performing reproducible offline evaluations of algorithms. We demonstrate the utility of LensKit by replicating and extending a set of prior comparative studies of recommender algorithms -- showing limitations in some of the original results -- and by investigating a question recently raised by a leader in the recommender systems community on problems with error-based prediction evaluation.

Human factors

Each to his own: how different users call for different interaction methods in recommender systems BIBAFull-Text 141-148
  Bart P. Knijnenburg; Niels J. M. Reijmer; Martijn C. Willemsen
This paper compares five different ways of interacting with an attribute-based recommender system and shows that different types of users prefer different interaction methods. In an online experiment with an energy-saving recommender system the interaction methods are compared in terms of perceived control, understandability, trust in the system, user interface satisfaction, system effectiveness and choice satisfaction. The comparison takes into account several user characteristics, namely domain knowledge, trusting propensity and persistence. The results show that most users (and particularly domain experts) are most satisfied with a hybrid recommender that combines implicit and explicit preference elicitation, but that novices and maximizers seem to benefit more from a non-personalized recommender that just displays the most popular items.
Rating: how difficult is it? BIBAFull-Text 149-156
  E. Isaac Sparling; Shilad Sen
Netflix.com uses star ratings, Digg.com uses up/down votes and Facebook uses a "like" but not a "dislike" button. Despite the popularity and diversity of these rating scales, research offers little guidance for designers choosing between them.
   This paper compares four different rating scales: unary ("like it"), binary (thumbs up / thumbs down), five-star, and a 100-point slider. Our analysis draws upon 12,847 movie and product review ratings collected from 348 users through an online survey. We a) measure the time and cognitive load required by each scale, b) study how rating time varies with the rating value assigned by a user, and c) survey users' satisfaction with each scale.
   Overall, users work harder with more granular rating scales, but these effects are moderated by item domain (product reviews or movies). Given a particular scale, users rating times vary significantly for items they like and dislike. Our findings about users' rating effort and satisfaction suggest guidelines for designers choosing between rating scales.
A user-centric evaluation framework for recommender systems BIBAFull-Text 157-164
  Pearl Pu; Li Chen; Rong Hu
This research was motivated by our interest in understanding the criteria for measuring the success of a recommender system from users' point view. Even though existing work has suggested a wide range of criteria, the consistency and validity of the combined criteria have not been tested. In this paper, we describe a unifying evaluation framework, called ResQue (Recommender systems' Quality of user experience), which aimed at measuring the qualities of the recommended items, the system's usability, usefulness, interface and interaction qualities, users' satisfaction with the systems, and the influence of these qualities on users' behavioral intentions, including their intention to purchase the products recommended to them and return to the system. We also show the results of applying psychometric methods to validate the combined criteria using data collected from a large user survey. The outcomes of the validation are able to 1) support the consistency, validity and reliability of the selected criteria; and 2) explain the quality of user experience and the key determinants motivating users to adopt the recommender technology. The final model consists of thirty two questions and fifteen constructs, defining the essential qualities of an effective and satisfying recommender system, as well as providing practitioners and scholars with a cost-effective way to evaluate the success of a recommender system and identify important areas in which to invest development resources.

Emerging recommendation domains

Yahoo! music recommendations: modeling music ratings with temporal dynamics and item taxonomy BIBAFull-Text 165-172
  Noam Koenigstein; Gideon Dror; Yehuda Koren
In the past decade large scale recommendation datasets were published and extensively studied. In this work we describe a detailed analysis of a sparse, large scale dataset, specifically designed to push the envelope of recommender system models. The Yahoo! Music dataset consists of more than a million users, 600 thousand musical items and more than 250 million ratings, collected over a decade. It is characterized by three unique features: First, rated items are multi-typed, including tracks, albums, artists and genres; Second, items are arranged within a four level taxonomy, proving itself effective in coping with a severe sparsity problem that originates from the unusually large number of items (compared to, e.g., movie ratings datasets). Finally, fine resolution timestamps associated with the ratings enable a comprehensive temporal and session analysis. We further present a matrix factorization model exploiting the special characteristics of this dataset. In particular, the model incorporates a rich bias model with terms that capture information from the taxonomy of items and different temporal dynamics of music ratings. To gain additional insights of its properties, we organized the KddCup-2011 competition about this dataset. As the competition drew thousands of participants, we expect the dataset to attract considerable research activity in the future.
CrimeWalker: a recommendation model for suspect investigation BIBAFull-Text 173-180
  Mohammad A. Tayebi; Mohsen Jamali; Martin Ester; Uwe Glässer; Richard Frank
Law enforcement and intelligence agencies have long realized that analysis of co-offending networks, networks of offenders who have committed crimes together, is invaluable for crime investigation, crime reduction and prevention. Investigating crime can be a challenging and difficult task, especially in cases with many potential suspects and inconsistent witness accounts or inconsistencies between witness accounts and physical evidence. We present here a novel approach to crime suspect recommendation based on partial knowledge of offenders involved in a crime incident and a known co-offending network. To solve this problem, we propose a random walk based method for recommending the top-K potential suspects. By evaluating the proposed method on a large crime dataset for the Province of British Columbia, Canada, we show experimentally that this method outperforms baseline random walk and association rule-based methods. Additionally, results obtained for public domain data from experiments for co-author recommendation on a DBLP co-authorship network are consistent with those on the crime dataset. Compared to the crime dataset, the performance of all competitors is much better on the DBLP dataset, confirming that crime suspect recommendation is an inherently harder task.
Personalized activity streams: sifting through the "river of news" BIBAFull-Text 181-188
  Ido Guy; Inbal Ronen; Ariel Raviv
Activity streams have emerged as a means to syndicate updates about a user or a group of users within a social network site or a set of sites. As the flood of updates becomes highly intensive and noisy, users are faced with a "needle in a haystack" challenge when they wish to read the news most interesting to them. In this work, we study activity stream personalization as a means of coping with this challenge. We experiment with an enterprise activity stream that includes status updates and news across a variety of social media applications. We examine an entity-based user profile and a stream-based profile across three dimensions: people, terms, and places, and provide a rich set of results through a user study that combines direct rating of the objects in the profile with rating of the news items it produces.

Poster session 1

Social link recommendation by learning hidden topics BIBAFull-Text 189-196
  Masoud Makrehchi
In this paper, a new approach to predicting the structure of a social network without any prior knowledge from the social links is proposed. In absence of links among nodes, we assume there are other information resources associated with the nodes which are called node profiles. The task of link prediction and recommendation from text data is to learn similarities between the nodes and then translate pair-wise similarities into social links. In other words, the process is to convert a similarity matrix into an adjacency matrix. In this paper, an alternative approach is proposed. First, hidden topics of node profiles are learned using Latent Dirichlet Allocation. Then, by mapping node-topic and topic-topic relations, a new structure called semi-bipartite graph is generated which is slightly different from regular bipartite graph. Finally, by applying topological metrics such as Katz and short path scores to the new structure, we are able to rank and recommend relevant links to each node. The proposed technique is applied to several co-authorship networks. While most link prediction methods are low precision solutions, the proposed method performs effectively and offers high precision.
Enhancing collaborative filtering systems with personality information BIBAFull-Text 197-204
  Rong Hu; Pearl Pu
Collaborative filtering (CF), one of the most successful recommendation approaches, continues to attract interest in both academia and industry. However, one key issue limiting the success of collaborative filtering in certain application domains is the cold-start problem, a situation where historical data is too sparse (known as the sparsity problem), new users have not rated enough items (known as the new user problem), or both. In this paper, we aim at addressing the cold-start problem by incorporating human personality into the collaborative filtering framework. We propose three approaches: the first is a recommendation method based on users' personality information alone; the second is based on a linear combination of both personality and rating information; and the third uses a cascade mechanism to leverage both resources. To evaluate their effectiveness, we have conducted an experimental study comparing the proposed approaches with the traditional rating-based CF in two cold-start scenarios: sparse data sets and new users. Our results show that the proposed CF variations, which consider personality characteristics, can significantly improve the performance of the traditional rating-based CF in terms of the evaluation metrics MAE and ROC sensitivity.
A market-based approach to address the new item problem BIBAFull-Text 205-212
  Sarabjot Singh Anand; Nathan Griffiths
In this paper we propose a market-based approach for seeding recommendations for new items in which publishers bid to have items presented to the most influential users for each item. Users are able to select (or not) items for rating on an earn-per-rating basis, with payment given for providing a rating regardless of whether the rating is positive or negative. This approach reduces the time taken to obtain ratings for new items, while encouraging users to give honest ratings (to increase their influence) which in turn supports the quality of recommendations. To support this approach we propose techniques for inferring the social influence network from users' rating vectors and recommendation lists. Using this influence network we apply existing heuristics for estimating a user's influence, adapting them to account for the new items already presented to a user. We also propose an extension to Chen et al.'s Degree Discount heuristic [Chen et al. 2009], to enable it to be used in this context. We evaluate our approach on the MovieLens dataset and show that we are able to reduce the time taken to achieve coverage, while supporting the quality of recommendations.
My head is your tail: applying link analysis on long-tailed music listening behavior for music recommendation BIBAFull-Text 213-220
  Kibeom Lee; Kyogu Lee
Collaborative filtering, being a popular method for generating recommendations, produces satisfying results for users by providing extremely relevant items. Despite being popular, however, this method is prone to many problems. One of these problems is popularity bias, in which the system becomes skewed towards items that are popular amongst the general user population. These 'obvious' items are, technically, extremely relevant items but fail to be novel. In this paper, we maintain using collaborative filtering methods while still managing to produce novel yet relevant items. This is achieved by utilizing the long-tailed distribution of listening behavior of users, in which their playlists are biased towards a few songs while the rest of the songs, those in the long tail, have relatively low play counts. In addition, we also apply a link analysis method to users and define links between them to create an increasingly fine-grained approach in calculating weights for the recommended items. The proposed recommendation method was available online as a user study in order to measure the relevancy and novelty of the recommended items. Results show that the algorithm manages to include novel recommendations that are still relevant, and shows the potential for a new way of generating novel recommendations.
Multi-value probabilistic matrix factorization for IP-TV recommendations BIBAFull-Text 221-228
  Yu Xin; Harald Steck
Matrix factorization (MF) has evolved as one of the most accurate approaches to collaborative filtering. In this paper, we extend the probabilistic MF framework as to account for multiple observations for each matrix element. This significantly improves the accuracy of recommender systems in several areas: (1) aggregation of ratings concerning items organized hierarchically, (2) (partial) compensation for the selection bias in the observed data by using an appropriate prior with virtual data points, and (3) improved recommendations of TV shows. While our framework applies to explicit and implicit feedback data, we outline in detail the latter application in this paper: we present the first approach that takes into account also negative feedback when training on implicit feedback data. Moreover, we shed light on the implicit assumptions underlying the most successful approach to IP-TV (Internet Protocol Television) recommendations in [Hu et al. 2008]. In our experiments, we obtain significant improvements over the existing approach.
A probabilistic definition of item similarity BIBAFull-Text 229-236
  Oliver Jojic; Manu Shukla; Niranjan Bhosarekar
In item-based collaborative filtering, a critical intermediate step to personalized recommendations is the definition of an item-similarity metric. Existing algorithms compute the item-similarity using the user-to-item ratings (cosine, Pearson, Jaccard, etc.). When computing the similarity between two items A and B many of these algorithms divide the actual number of co-occurring users by some "difficulty" of co-occurrence. We refine this approach by defining item similarity as the ratio of the actual number of co-occurrences to the number of co-occurrences that would be expected if user choices were random. In the final step of our method to compute personalized recommendations we apply the usage history of a user to the item similarity matrix. The well defined probabilistic meaning of our similarities allows us to further improve this final step. We measured the quality of our algorithm on a large real-world data-set. As part of Comcast's efforts to improve its personalized recommendations of movies and TV shows, several top recommender companies were invited to apply their algorithms to one year of Video-on-Demand usage data. Our algorithm tied for first place. This paper includes a MapReduce pseudo code implementation of our algorithm.
The "top N" news recommender: count distortion and manipulation resistance BIBAFull-Text 237-244
  Shankar Prawesh; Balaji Padmanabhan
The broad motivation for our research is to build manipulation resistant news recommender systems. However, there can be several different algorithms that are used to generate news recommendations, and the strategies for manipulation resistance are likely specific to the algorithm (or class of algorithm) employed. In this paper we will focus on a common method used by many media sites of recommending the N most read (or popular) articles (e.g. New York Times, BBC, Wall Street Journal all prominently use this). Through simulation results we show that whereas recommendation of the N most read articles is easily susceptible to manipulation, a simple probabilistic variant is more robust to common manipulation strategies. Further, for the "N most read" recommender, probabilistic selection has other desirable properties. Specifically, the (N+1)th article, which may have "just" missed making the cutoff, is unduly penalized under common user models. Small differences initially are easily amplified -- an observation that can be used by manipulators. Probabilistic selection, on the other hand, creates no such artificial penalty. We also use classical results from urn models to derive theoretical results for special cases.
Factorization vs. regularization: fusing heterogeneous social relationships in top-n recommendation BIBAFull-Text 245-252
  Quan Yuan; Li Chen; Shiwan Zhao
Collaborative Filtering (CF) based recommender systems often suffer from the sparsity problem, particularly for new and inactive users when they use the system. The emerging trend of social networking sites and their accommodation in other sites like e-commerce can potentially help alleviate the sparsity problem with their provided social relation data. In this paper, we have particularly explored a new kind of social relation, the membership, and its combined effect with friendship. The two type of heterogeneous social relations are fused into the CF recommender via a factorization process. Due to the two relations' respective properties, we adopt different fusion strategies: regularization was leveraged for friendship and collective matrix factorization (CMF) was proposed for incorporating membership. We further developed a unified model to combine the two relations together and tested it with real large-scale datasets at five sparsity levels. The experiment has not only revealed the significant effect of the two relations, especially the membership, in augmenting recommendation accuracy in the sparse data condition, but also identified the ability of our fusing model in achieving the desired fusion performance.

Poster session 2

Recommending music for places of interest in a mobile travel guide BIBAFull-Text 253-256
  Matthias Braunhofer; Marius Kaminskas; Francesco Ricci
Context-aware music recommender systems suggest music items taking into consideration contextual conditions, such as the user mood or location, that may influence the user preferences at a particular moment. In this paper we consider a particular kind of context-aware recommendation task: selecting music suited for a place of interest (POI), which the user is visiting, and that is illustrated in a mobile travel guide. We have designed an approach for this novel recommendation task by matching music to POIs using emotional tags. In order to test our approach, we have developed a mobile application that suggests an itinerary and plays recommended music for each visited POI. The results of the study show that users judge the recommended music suited for the POIs, and the music is rated higher when it is played in this usage scenario.
Adaptive social similarities for recommender systems BIBAFull-Text 257-260
  Le Yu; Rong Pan; Zhangfeng Li
Collaborative filtering (CF) is an effective recommendation technique, which selects items for an individual user based on similar users' preferences. However, CF may not fully reflect the procedure how people choose an item in real life, for users are more likely to ask friends for opinions instead of asking similar strangers. Recently, some recommendation methods based on social network have been raised. These approaches incorporate social network into the CF algorithms and users' preferences can be influenced by the favors of their friends. These social approaches require the knowledge of similarities among friends. There are two popular similarity functions: Vector Space Similarity (VSS) and Pearson Correlation Coefficient (PCC). However, both friends similarity functions are based on the item-sets they rated in common. In most cases, these functions are impractical, i.e. if two friends do not share the same items in common, the similarity between them will be zeros. To solve this problem, we propose an Adaptive Social Similarity (ASS) function based on the matrix factorization technique. We conduct our experiment on a large dataset: Epinions, which is a widely-used dataset with social information. The experiment results illustrate that our approach outperforms the baseline models and achieves a better performance than social-based method in [4].
Content-boosted matrix factorization for recommender systems: experiments with recipe recommendation BIBAFull-Text 261-264
  Peter Forbes; Mu Zhu
The Netflix prize has rejuvenated a widespread interest in the matrix factorization approach for collaborative filtering. We describe a simple algorithm for incorporating content information directly into this approach. We present experimental evidence using recipe data to show that this not only improves recommendation accuracy but also provides useful insights about the contents themselves that are otherwise unavailable.
Interactive multi-party critiquing for group recommendation BIBAFull-Text 265-268
  Francesca Guzzi; Francesco Ricci; Robin Burke
Group recommender systems (RS) are used to support groups in making common decisions when considering a set of alternatives. Current approaches generate group recommendations based on the users' individual preferences models. We believe that members of a group can reach an agreement more effectively by exchanging proposals suggested by a conventional RS. We propose to use a critiquing RS that has been shown to be effective in single-user recommendation. In the group recommendation context, critiquing allows each user to get new recommendations similar to the proposals made by the other group members and to communicate the rationale behind their own counter-proposals. We describe a mobile application implementing the proposed approach and its evaluation in a live user experiment.
A model for proactivity in mobile, context-aware recommender systems BIBAFull-Text 273-276
  Wolfgang Woerndl; Johannes Huebner; Roland Bader; Daniel Gallego-Vico
A proactive recommender system pushes recommendations to the user when the current situation seems appropriate, without explicit user request. This is conceivable in mobile scenarios such as restaurant or gas station recommendations. In this paper, we present a model for proactivity in mobile recommender systems. The model relies on domain-dependent context modeling in several categories. The recommendation process is divided into two phases to first analyze the current situation and then examine the suitability of particular items. We have implemented a prototype gas station recommender and conducted a survey for evaluation. Results showed good correlation of the output of our system with the assessment of users regarding the question when to generate recommendations.
Effective event discovery: using location and social information for scoping event recommendations BIBAFull-Text 277-280
  Elizabeth M. Daly; Werner Geyer
The ever blurring line between online interactions and physical encounters presents an interesting challenge when recommending events. Events created on social networking sites may have ambiguous location scope. The location information provided may be fuzzy or non existent and additionally the reach and radius of interest in the event can vary greatly. In this work, we identify four categories of events: global, location dependent and socially independent, socially dependent and location independent, and location and socially dependent. We classify events from an organizations internal event management service where the location of the event is unknown, but the location of the attendees are known in order to improve scoping of event recommendations. Our results, investigate the impact of ignoring location properties when recommending events using classic collaborative filtering techniques. Additionally, once global and socially independent events are identified, they can be used to provide recommendations to new users, addressing the cold-start problem.
Collaborative filtering with collective training BIBAFull-Text 281-284
  Yong Ge; Hui Xiong; Alexander Tuzhilin; Qi Liu
Rating sparsity is a critical issue for collaborative filtering. For example, the well-known Netflix Movie rating data contain ratings of only about 1% user-item pairs. One way to address this rating sparsity problem is to develop more effective methods for training rating prediction models. To this end, in this paper, we introduce a collective training paradigm to automatically and effectively augment the training ratings. Essentially, the collective training paradigm builds multiple different Collaborative Filtering (CF) models separately, and augments the training ratings of each CF model by using the partial predictions of other CF models for unknown ratings. Along this line, we develop two algorithms, Bi-CF and Tri-CF, based on collective training. For Bi-CF and Tri-CF, we collectively and iteratively train two and three different CF models via iteratively augmenting training ratings for individual CF model. We also design different criteria to guide the selection of augmented training ratings for Bi-CF and Tri-CF. Finally, the experimental results show that Bi-CF and Tri-CF algorithms can significantly outperform baseline methods, such as neighborhood-based and SVD-based models.
Using Wikipedia to boost collaborative filtering techniques BIBAFull-Text 285-288
  Gilad Katz; Nir Ofek; Bracha Shapira; Lior Rokach; Guy Shani
One important challenge in the field of recommender systems is the sparsity of available data. This problem limits the ability of recommender systems to provide accurate predictions of user ratings. We overcome this problem by using the publicly available user generated information contained in Wikipedia. We identify similarities between items by mapping them to Wikipedia pages and finding similarities in the text and commonalities in the links and categories of each page. These similarities can be used in the recommendation process and improve ranking predictions. We find that this method is most effective in cases where ratings are extremely sparse or nonexistent. Preliminary experimental results on the MovieLens dataset are encouraging.
Semi-SAD: applying semi-supervised learning to shilling attack detection BIBAFull-Text 289-292
  Zhiang Wu; Jie Cao; Bo Mao; Youquan Wang
Collaborative filtering (CF) based recommender systems are vulnerable to shilling attacks. In some leading e-commerce sites, there exists a large number of unlabeled users, and it is expensive to obtain their identities. Existing research efforts on shilling attack detection fail to exploit these unlabeled users. In this article, Semi-SAD, a new semi-supervised learning based shilling attack detection algorithm is proposed. Semi-SAD is trained with the labeled and unlabeled user profiles using the combination of naïve Bayes classifier and EM-», augmented Expectation Maximization (EM). Experiments on MovieLens datasets show that our proposed Semi-SAD is efficient and effective.
Leveraging the LinkedIn social network data for extracting content-based user profiles BIBAFull-Text 293-296
  Pasquale Lops; Marco de Gemmis; Giovanni Semeraro; Fedelucio Narducci; Cataldo Musto
In the last years, hundreds of social networks sites have been launched with both professional (e.g., LinkedIn) and non-professional (e.g., MySpace, Facebook) orientations. This resulted in a renewed information overload problem, but it also provided a new and unforeseen way of gathering useful, accurate and constantly updated information about user interests and tastes. Content-based recommender systems can leverage the wealth of data emerging by social networks for building user profiles in which representations of the user interests are maintained.
   The idea proposed in this paper is to extract content-based user profiles from the data available in the LinkedIn social network, to have an image of the users' interests that can be used to recommend interesting academic research papers. A preliminary experiment provided interesting results which deserve further attention.
Applications of the conjugate gradient method for implicit feedback collaborative filtering BIBAFull-Text 297-300
  Gábor Takács; István Pilászy; Domonkos Tikk
The need for solving weighted ridge regression (WRR) problems arises in a number of collaborative filtering (CF) algorithms. Often, there is not enough time to calculate the exact solution of the WRR problem, or it is not required. The conjugate gradient (CG) method is a state-of-the-art approach for the approximate solution of WRR problems. In this paper, we investigate some applications of the CG method for new and existing implicit feedback CF models. We demonstrate through experiments on the Netflix dataset that CG can be an efficient tool for training implicit feedback CF models.
Matrix factorization techniques for context aware recommendation BIBAFull-Text 301-304
  Linas Baltrunas; Bernd Ludwig; Francesco Ricci
Context aware recommender systems (CARS) adapt the recommendations to the specific situation in which the items will be consumed. In this paper we present a novel context-aware recommendation algorithm that extends Matrix Factorization. We model the interaction of the contextual factors with item ratings introducing additional model parameters. The performed experiments show that the proposed solution provides comparable results to the best, state of the art, and more complex approaches. The proposed solution has the advantage of smaller computational cost and provides the possibility to represent at different granularities the interaction between context and items. We have exploited the proposed model in two recommendation applications: places of interest and music.
MyMediaLite: a free recommender system library BIBAFull-Text 305-308
  Zeno Gantner; Steffen Rendle; Christoph Freudenthaler; Lars Schmidt-Thieme
MyMediaLite is a fast and scalable, multi-purpose library of recommender system algorithms, aimed both at recommender system researchers and practitioners. It addresses two common scenarios in collaborative filtering: rating prediction (e.g. on a scale of 1 to 5 stars) and item prediction from positive-only implicit feedback (e.g. from clicks or purchase actions). The library offers state-of-the-art algorithms for those two tasks. Programs that expose most of the library's functionality, plus a GUI demo, are included in the package. Efficient data structures and a common API are used by the implemented algorithms, and may be used to implement further algorithms. The API also contains methods for real-time updates and loading/storing of already trained recommender models.
   MyMediaLite is free/open source software, distributed under the terms of the GNU General Public License (GPL). Its methods have been used in four different industrial field trials of the MyMedia project, including one trial involving over 50,000 households.
Towards a more realistic evaluation: testing the ability to predict future tastes of matrix factorization-based recommenders BIBAFull-Text 309-312
  Pedro G. Campos; Fernando Díez; Manuel Sánchez-Montañés
The use of temporal dynamic terms in Matrix Factorization (MF) models of recommendation have been proposed as a means to obtain better accuracy in rating prediction task. However, the way such models have been tested may not be a realistic setting for recommendation. In this paper, we evaluated rating prediction and top-N recommendation tasks using a MF model with and without temporal dynamic terms under two evaluation settings. Our experiments show that the addition of dynamic parameters do not necessarily yield to better results on these tasks when a more strict time-aware separation of train/test data is performed, and moreover, results may vary notably when different evaluation schemes are used.
Collaborative temporal order modeling BIBAFull-Text 313-316
  Alexandros Karatzoglou
Past consumption of items affect current choices and influence the perceived quality. The order in which items are consumed can affect the score that a user might give to them. In this work we present two simple models that take advantage of the temporal order of choices and ratings by the user in order to improve the quality of the recommendation. Our model exploits the collaborative effects in the data while also taking into account the order in which items are seen by the users. Experiments show that our approach outperforms standard Matrix Factorization models.
LOGO: a long-short user interest integration in personalized news recommendation BIBAFull-Text 317-320
  Lei Li; Li Zheng; Tao Li
In this paper, we initially provide an experimental study on the evolution of user interests in real-world news recommender systems, and then propose a novel recommendation approach, in which the long-term and short-term reading preferences of users are seamlessly integrated when recommending news items. Given a hierarchy of newly-published news articles, news groups that the user might prefer are differentiated using the long-term profile, and then in each selected news group, a list of news items are chosen based on the short-term user profile. Extensive empirical experiments on a collection of news articles obtained from various popular news websites demonstrate the efficacy of our method.
A pragmatic procedure to support the user-centric evaluation of recommender systems BIBAFull-Text 321-324
  Bart P. Knijnenburg; Martijn C. Willemsen; Alfred Kobsa
As recommender systems are increasingly deployed in the real world, they are not merely tested offline for precision and coverage, but also "online" with test users to ensure good user experience. The user evaluation of recommenders is however complex and resource-consuming. We introduce a pragmatic procedure to evaluate recommender systems for experience products with test users, within industry constraints on time and budget. Researchers and practitioners can employ our approach to gain a comprehensive understanding of the user experience with their systems.
Machine learned job recommendation BIBAFull-Text 325-328
  Ioannis Paparrizos; B. Barla Cambazoglu; Aristides Gionis
We address the problem of recommending suitable jobs to people who are seeking a new job. We formulate this recommendation problem as a supervised machine learning problem. Our technique exploits all past job transitions as well as the data associated with employees and institutions to predict an employee's next job transition. We train a machine learning model using a large number of job transitions extracted from the publicly available employee profiles in the Web. Experiments show that job transitions can be accurately predicted, significantly improving over a baseline that always predicts the most frequent institution in the data.
Utilizing related products for post-purchase recommendation in e-commerce BIBAFull-Text 329-332
  Jian Wang; Badrul Sarwar; Neel Sundaresan
In this paper, we design a recommender system for the post-purchase stage, i.e., after a user purchases a product. Our method combines both behavioral and content aspects of recommendations. We first find the most related categories for the active product in the post-purchase stage. Among these related categories, products with high behavioral relevance and content relevance are recommended to the user. In addition, our algorithm considers the temporal factor, i.e., the purchase time of the active product and the recommendation time. We apply our algorithm on a random sample of the purchase data from eBay. Comparing to the baseline item-based collaborative filtering approach, our hybrid recommender system achieves significant coverage and purchase rate gain for different time windows.
Precision-oriented evaluation of recommender systems: an algorithmic comparison BIBAFull-Text 333-336
  Alejandro Bellogin; Pablo Castells; Ivan Cantador
There is considerable methodological divergence in the way precision-oriented metrics are being applied in the Recommender Systems field, and as a consequence, the results reported in different studies are difficult to put in context and compare. We aim to identify the involved methodological design alternatives, and their effect on the resulting measurements, with a view to assessing their suitability, advantages, and potential shortcomings. We compare five experimental methodologies, broadly covering the variants reported in the literature. In our experiments with three state-of-the-art recommenders, four of the evaluation methodologies are consistent with each other and differ from error metrics, in terms of the comparative recommenders' performance measurements. The other procedure aligns with RMSE, but shows a heavy bias towards known relevant items, considerably overestimating performance.
Power to the people: exploring neighbourhood formations in social recommender system BIBAFull-Text 337-340
  Steven Bourke; Kevin McCarthy; Barry Smyth
The explosive growth of online social networks in recent times has presented a powerful source of information to be utilised in personalised recommendations. Unsurprisingly there has already been a large body of work completed in the recommender system field to incorporate this social information into the recommendation process. In this paper we examine the practice of leveraging a user's social graph in order to generate recommendations. Using various neighbourhood selection strategies, we examine the user satisfaction and the level of perceived trust in the recommendations received.
Stochastic matching and collaborative filtering to recommend people to people BIBAFull-Text 341-344
  Luiz Augusto Pizzato; Cameron Silvestrini
The bias towards popular items is not necessarily an undesired outcome of recommender algorithms since a large amount of revenue on e-commerce websites is drawn from these popular items. On the other hand, in domains such as online dating and employment websites, where users and items of the recommendation are both people, a strong bias towards popular users may cause these users to feel overwhelmed and unpopular users to feel neglected. In this paper, we use collaborative filtering (CF) to generate recommendations for all users, and by using stochastic matching we select a number of reciprocal recommendations for each user that maximizes the matches among all users. In this way, all users, regardless of their popularity, will receive the same number of recommendations the number of times they will be recommended to others. This study is the first to apply a stochastic matching solution to balance the number of recommendations given to users in a CF setting. Using historical data, we demonstrate that the proposed recommender improves the chance of finding a successful relationship in comparison to CF recommendations.
Recommendations in social media for brand monitoring BIBAFull-Text 345-348
  Shanchan Wu; William Rand; Louiqa Raschid
We present a recommendation system for social media that draws upon monitoring and prediction methods. We use historical posts on some focal topic or historical links to a focal blog channel to recommend a set of authors to follow. Such a system would be useful for brand managers interested in monitoring conversations about their products. Our recommendations are based on a prediction system that trains a ranking Support Vector Machine (RSVM) using multiple features including the content of a post, similarity between posts, links between posts and/or blog channels, and links to external websites. We solve two problems, Future Author Prediction (FAP) and Future Link Prediction (FLP), and apply the prediction outcome to make recommendations. Using an extensive experimental evaluation on a blog dataset, we demonstrate the quality and value of our recommendations.

Industry half-day session: demos and speaker Lapers

LensKit: a modular recommender framework BIBAFull-Text 349-350
  Michael D. Ekstrand; Michael Ludwig; Jack Kolb; John T. Riedl
LensKit is a new recommender systems toolkit aiming to be a platform for recommender research and education. It provides a common API for recommender systems, modular implementations of several collaborative filtering algorithms, and an evaluation framework for consistent, reproducible offline evaluation of recommender algorithms. In this demo, we will showcase the ease with which LensKit allows recommenders to be configured and evaluated.
myMicSound: an online sound-based microphone recommendation system BIBFull-Text 351-352
  Andrew T. Sabin; Chun Liang Chan
Recommenders benchmark framework BIBAFull-Text 353-354
  Aviram Dayan; Guy Katz; Naseem Biasdi; Lior Rokach; Bracha Shapira; Aykan Aydin; Roland Schwaiger; Radmila Fishel
In this demo we present a recommender benchmark framework that serves as an infrastructure for comparing and examining the performance and feasibility of different recommender algorithms on various datasets with a variety of measures. The extendable infrastructure aims to provide easy plugging of novel recommendation-algorithms, datasets and compare their performance using visual tools and metrics with other algorithms in the benchmark. It also aims at generating a WEKA-type workbench [1] for the recommender systems field to enable usage and application of common recommender systems (RS) algorithms for research and practice.
Note: The demo movie is available at: http://www.youtube.com/watch?v=fsDITf6s0WY

Doctoral symposium

Using canonical correlation analysis for generalized sentiment analysis, product recommendation and search BIBAFull-Text 355-358
  Siamak Faridani
Standard Sentiment Analysis applies Natural Language Processing methods to assess an "approval" value of a given text, categorizing it into "negative", "neutral", or "positive" or on a linear scale. Sentiment Analysis can be used to infer ratings values for users based on textual reviews of items such as books, films, or products. We propose an approach to generalizing the concept to multiple dimensions to estimate user ratings along multiple axes such as "service", "price" and "value". We use Canonical Correlation Analysis (CCA) and derive a mathematical model that can be used as a multivariate regression tool. This model has a number of valuable properties: it can be trained offline and used efficiently on live stream of texts like blogs and tweets, can be used for visualization and data clustering and labeling, and finally it can potentially be incorporated into natural language product search algorithms. At the end we propose an evaluation procedure that can be used on live data when a ground truth is not available. Based on this model we present our preliminary results from empirical data that we have collected from our system Opinion Space1. We show that for this dataset the CCA model outperforms the PCA that was originally used in Opinion Space.
Design guidelines for mobile group recommender systems to handle inaccurate or missing location data BIBAFull-Text 359-362
  Markus Tschersich
Today's group recommender systems do not consider unavailable, inaccessible, or incomplete user information of one ore more members within a group. This is a problem for mobile group recommender system, because changed user behaviour or technical limitations of mobile services let user may not be willing or able to disclose all information, which are part of a user profile in a mobile environment. For location information, as one of the most important type of user information for an ad-hoc mobile recommendation service, this can lead to inaccurate, or missing location information. Inaccurate or missing location information has an impact on different parts of building group recommendations. This impact reduces the quality of recommendations, which is a key-challenge of recommender systems. Therefore, design guidelines are needed to address the problem of missing or inaccurate location information in mobile group recommender systems. This work describes the approach of building and validating those design guidelines and gives a first idea of impacts.
Interface and interaction design for group and social recommender systems BIBAFull-Text 363-366
  Yu Chen
Group and social recommender systems aim to recommend items of interest to a group or a community of people. The user issues in such systems cannot be addressed by examining the satisfaction of their members as individuals. Rather, group satisfaction should be studied as a result of the interaction and interface methods that support group dynamics and interaction. In this paper, we survey the state-of-the-art in user experience design of group and social recommender systems. We further apply the techniques used in the current recommender systems to GroupFun, a music social group recommender system. After presenting the interface and interaction characteristics of GroupFun, we further analyze the design space and propose areas for future research in pursuit of an affective recommender.
Intelligent web usage clustering based recommender system BIBAFull-Text 367-370
  Shafiq Alam
Our work focuses on tackling the problem of efficiency and accuracy of web usage clustering for recommender systems. Accurate analysis and preprocessing of web usage data and efficient web usage clustering are the key factors that influence the development of clustering based implicit recommender system. We propose an analysis and preprocessing model to tackle the poor quality of web usage data. To address the problem of efficient web usage clustering, we propose a Particle Swarm Optimization (PSO) based clustering approach. Having shown our PSO based clustering performs well; we extend it for mining the usage behavior of web users. We select Java API (Application Programming Interface) documentation usage data as a case study for our recommender system.
Predicting performance in recommender systems BIBAFull-Text 371-374
  Alejandro Bellogin
Performance prediction has gained growing attention in the Information Retrieval field since the late nineties and has become an established research topic in the field. Our work restates the problem in the area of Recommender Systems, where it has barely been researched so far, despite being an appealing problem, as it enables an array of strategies for deciding when to deliver or hold back recommendations based on their foreseen accuracy. We investigate the adaptation and definition of different performance predictors based on the available user and item features. The properties of the predictor are empirically studied by checking the correlation of the predictor output with a performance measure. Then, we propose to introduce the performance predictor in a recommender system to produce a dynamic strategy. Depending on how the predictor is introduced we analyze two different problems: dynamic neighbor weighting in collaborative filtering and dynamic weighting of ensemble recommenders.
Anchoring effects of recommender systems BIBAFull-Text 375-378
  Jingjing Zhang
We explore how consumer preferences at the time of consumption are impacted by predictions generated by recommender systems. We conducted three controlled laboratory experiments to explore the effects of system recommendations on preferences. Results provide strong evidence that the rating provided by a recommender system serves as an anchor for the consumer's constructed preference. Consumer's preferences appear malleable and can be significantly influenced by the recommendation received. Additionally, the effects of pure number-based anchoring can be separated from the effects of the perceived reliability of a recommender system. In particular, when the recommender system was described to the participants as being in testing phase, the anchoring effect was reduced. Finally, the effect of anchoring is roughly continuous, operating over a range of perturbations of the system.

Workshop outlines

3rd workshop on context-aware recommender systems (CARS 2011) BIBAFull-Text 379-380
  Gediminas Adomavicius; Linas Baltrunas; Tim Hussein; Francesco Ricci; Alexander Tuzhilin
CARS 2011 builds upon the success of the two previous editions held in conjunction with the 3rd and 4th ACM Conferences on Recommender Systems in 2009 and 2010. The first CARS Workshop was held in New York, NY, USA (2009), and Barcelona, Spain, was the home of the second CARS Workshop in 2010.
WOMRAD: 2nd workshop on music recommendation and discovery BIBAFull-Text 381-382
  Amélie Anglade; Òscar Celma; Ben Fields; Paul Lamere; Brian McFee
The world of music is changing rapidly. We are now just a few clicks away from being able to listen to nearly any song that has ever been recorded. This easy access to a nearly endless supply of music is changing how we explore, discover, share and experience music.
3rd workshop on recommender systems and the social web BIBAFull-Text 383-384
  Jill Freyne; Sarabjot Singh Anand; Ido Guy; Andreas Hotho
The exponential growth of the social web poses challenges and new opportunities for recommender systems. The social web has turned information consumers into active contributors creating massive amounts of information. Finding relevant and interesting content at the right time and in the right context is challenging for existing recommender approaches. At the same time, social systems by their definition encourage interaction between users and both online content and other users, thus generating new sources of knowledge for recommender systems. Web 2.0 users explicitly provide personal information and implicitly express preferences through their interactions with others and the system (e.g. commenting, friending, rating, etc.). These various new sources of knowledge can be leveraged to improve recommendation techniques and develop new strategies which focus on social recommendation. The Social Web provides huge opportunities for recommender technology and in turn recommender technologies can play a part in fuelling the success of the Social Web phenomenon.
   The goal of this one day workshop was to bring together researchers and practitioners to explore, discuss, and understand challenges and new opportunities for Recommender Systems and the Social Web. The workshop consisted both of technical sessions, in which selected participants presented their results or ongoing research, as well as informal breakout sessions on more focused topics.
   Papers discussing various aspects of recommender system in the Social Web were submitted and selected for presentation and discussion in the workshop in a formal reviewing process: Case studies and novel fielded social recommender applications; Economy of community-based systems: Using recommenders to encourage users to contribute and sustain participation.; Social network and folksonomy development: Recommending friends, tags, bookmarks, blogs, music, communities etc.; Recommender systems mash-ups, Web 2.0 user interfaces, rich media recommender systems; Collaborative knowledge authoring, collective intelligence; Recommender applications involving users or groups directly in the recommendation process; Exploiting folksonomies, social network information, interaction, user context and communities or groups for recommendations; Trust and reputation aware social recommendations; Semantic Web recommender systems, use of ontologies or microformats; Empirical evaluation of social recommender techniques, success and failure measures.
Note: Full workshop details are available at http://www.dcs.warwick.ac.uk/~ssanand/RSWeb11/index.htm
Challenge on context-aware movie recommendation: CAMRa2011 BIBAFull-Text 385-386
  Alan Said; Shlomo Berkovsky; Ernesto William De Luca; Jannis Hermanns
This paper provides an overview of CAMRa2011, the second edition of the Challenge on Context-Aware Movie Recommendation. The challenge attracted a large number of participants to work on the challenge tracks, which this time focused on group related recommendation aspects.
Second workshop on information heterogeneity and fusion in recommender systems (HetRec2011) BIBFull-Text 387-388
  Ivan Cantador; Peter Brusilovsky; Tsvi Kuflik
RecSys'11 workshop on human decision making in recommender systems BIBAFull-Text 389-390
  Alexander Felfernig; Li Chen; Monika Mandl
Interacting with a recommender system means to take different decisions such as selecting a song/movie from a recommendation list, selecting specific feature values (e.g., camera's size, zoom) as criteria, selecting feedback features to be critiqued in a critiquing based recommendation session, or selecting a repair proposal for inconsistent user preferences when interacting with a knowledge-based recommender. In all these scenarios, users have to solve a decision task. The major focuses of this workshop (Decisions@RecSys) were approaches for efficient human decision making in different types of recommendation scenarios.
RecSys'11 workshop outline PeMA 2011: personalization in mobile applications BIBAFull-Text 391-392
  Neal Lathia; Daniele Quercia; Licia Capra; Jon Crowcroft
The rise of location-enabled mobile phones and location based services offers a great opportunity to apply personalization and recommender system technology to people's everyday lives. A variety of digital traces can now be used to infer how people move about their city and extract their context and habits. Personalization and recommender systems, potentially merged with the data that people store online (e.g., social networks, web ratings), can then not only be used to recommend new places and events that they may find interesting to attend, but, more broadly, personalize and enhance any service that people find themselves using.
   The goal of this one-day workshop was to bring together researchers and practitioners to explore, discuss, and understand challenges and new opportunities for personalisation within the urban domain. Topics of discussion during the workshop included: Innovative applications of recommender systems in mobile settings; Location and/or context-based recommender systems; Recommending locations, venues, and social events; Incentives and persuasion in mobile settings; User-centric evaluation of personalised mobile services; Recommender systems for smart cities/urban environments; Intelligent transport systems; Real-time and/or multi-source information processing for personalisation; Personalized and adaptive mobile interfaces; Security, privacy, reputation and trust issues in mobile recommenders; Geographic/location-based social networks and social filtering; Case studies of recommender systems in mobile environments.
Workshop on novelty and diversity in recommender systems -- DiveRS 2011 BIBAFull-Text 393-394
  Pablo Castells; Jun Wang; Rubén Lara; Dell Zhang
Novelty and diversity have been identified as key dimensions of recommendation utility in real scenarios, and a fundamental research direction to keep making progress in the field. Yet recommendation novelty and diversity remain a largely open area for research. The DiveRS workshop gathered researchers and practitioners interested in the role of these dimensions in recommender systems. The workshop seeks to advance towards a better understanding of what novelty and diversity are, how they can improve the effectiveness of recommendation methods and the utility of their outputs. The workshop pursued the identification of open problems, relevant research directions, and opportunities for innovation in the recommendation business.
UCERSTI 2: second workshop on user-centric evaluation of recommender systems and their interfaces BIBFull-Text 395-396
  Martijn Willemsen; Dirk Bollen; Michael Ekstrand