| Preface to the special issue on context-aware recommender systems | | BIBAK | Full-Text | 1-5 | |
| Gediminas Adomavicius; Dietmar Jannach | |||
| Recommender systems represent a popular area of personalization technologies
that has enjoyed a tremendous amount of research and development activity in
both academia and industry in the last 10--15 years. Recommender systems
research typically explores and develops techniques and applications for
recommending various products or services to individual users based on the
knowledge of users' tastes and preferences as well as users' past activities
(such as previous purchases), which are applicable in a variety of domains and
settings (Jannach et al. 2010). Keywords: Recommender systems; Context-awareness; Collaborative filtering | |||
| Experimental evaluation of context-dependent collaborative filtering using item splitting | | BIBAK | Full-Text | 7-34 | |
| Linas Baltrunas; Francesco Ricci | |||
| Collaborative Filtering (CF) computes recommendations by leveraging a
historical data set of users' ratings for items. CF assumes that the users'
recorded ratings can help in predicting their future ratings. This has been
validated extensively, but in some domains the user's ratings can be influenced
by contextual conditions, such as the time, or the goal of the item
consumption. This type of contextual information is not exploited by standard
CF models. This paper introduces and analyzes a novel technique for
context-aware CF called Item Splitting. In this approach items experienced in
two alternative contextual conditions are "split" into two items. This means
that the ratings of a split item, e.g., a place to visit, are assigned (split)
to two new fictitious items representing for instance the place in summer and
the same place in winter. This split is performed only if there is statistical
evidence that under these two contextual conditions the items ratings are
different; for instance, a place may be rated higher in summer than in winter.
These two new fictitious items are then used, together with the unaffected
items, in the rating prediction algorithm. When the system must predict the
rating for that "split" item in a particular contextual condition (e.g., in
summer), it will consider the new fictitious item representing the original one
in that particular contextual condition, and will predict its rating. We
evaluated this approach on real world, and semi-synthetic data sets using
matrix factorization, and nearest neighbor CF algorithms. We show that Item
Splitting can be beneficial and its performance depends on the method used to
determine which items to split. We also show that the benefit of the method is
determined by the relevance of the contextual factors that are used to split. Keywords: Recommender Systems; Collaborative filtering; Context; Item splitting | |||
| Comparing context-aware recommender systems in terms of accuracy and diversity | | BIBAK | Full-Text | 35-65 | |
| Umberto Panniello; Alexander Tuzhilin; Michele Gorgoglione | |||
| Although the area of context-aware recommender systems (CARS) has made a
significant progress over the last several years, the problem of comparing
various contextual pre-filtering, post-filtering and contextual modeling
methods remained fairly unexplored. In this paper, we address this problem and
compare several contextual pre-filtering, post-filtering and contextual
modeling methods in terms of the accuracy and diversity of their
recommendations to determine which methods outperform the others and under
which circumstances. To this end, we consider three major factors affecting
performance of CARS methods, such as the type of the recommendation task,
context granularity and the type of the recommendation data. We show that none
of the considered CARS methods uniformly dominates the others across all of
these factors and other experimental settings; but that a certain group of
contextual modeling methods constitutes a reliable "best bet" when choosing a
sound CARS approach since they provide a good balance of accuracy and diversity
of contextual recommendations. Keywords: Context-aware recommender systems; CARS; Pre-filtering; Post-filtering;
Contextual modeling; Accuracy; Diversity; Performance measures | |||
| Time-aware recommender systems: a comprehensive survey and analysis of existing evaluation protocols | | BIBAK | Full-Text | 67-119 | |
| Pedro G. Campos; Fernando Díez; Iván Cantador | |||
| Exploiting temporal context has been proved to be an effective approach to
improve recommendation performance, as shown, e.g. in the Netflix Prize
competition. Time-aware recommender systems (TARS) are indeed receiving
increasing attention. A wide range of approaches dealing with the time
dimension in user modeling and recommendation strategies have been proposed. In
the literature, however, reported results and conclusions about how to
incorporate and exploit time information within the recommendation processes
seem to be contradictory in some cases. Aiming to clarify and address existing
discrepancies, in this paper we present a comprehensive survey and analysis of
the state of the art on TARS. The analysis show that meaningful divergences
appear in the evaluation protocols used -- metrics and methodologies. We
identify a number of key conditions on offline evaluation of TARS, and based on
these conditions, we provide a comprehensive classification of evaluation
protocols for TARS. Moreover, we propose a methodological description framework
aimed to make the evaluation process fair and reproducible. We also present an
empirical study on the impact of different evaluation protocols on measuring
relative performances of well-known TARS. The results obtained show that
different uses of the above evaluation conditions yield to remarkably distinct
performance and relative ranking values of the recommendation approaches. They
reveal the need of clearly stating the evaluation conditions used to ensure
comparability and reproducibility of reported results. From our analysis and
experiments, we finally conclude with methodological issues a robust evaluation
of TARS should take into consideration. Furthermore we provide a number of
general guidelines to select proper conditions for evaluating particular TARS. Keywords: Time-aware recommender systems; Context-aware recommender systems;
Evaluation methodologies; Survey | |||
| Hybreed: A software framework for developing context-aware hybrid recommender systems | | BIBAK | Full-Text | 121-174 | |
| Tim Hussein; Timm Linder; Werner Gaulke; Jürgen Ziegler | |||
| This article introduces Hybreed, a software framework for building complex
context-aware applications, together with a set of components that are
specifically targeted at developing hybrid, context-aware recommender systems.
Hybreed is based on a concept for processing context that we call dynamic
contextualization. The underlying notion of context is very generic, enabling
application developers to exploit sensor-based physical factors as well as
factors derived from user models or user interaction. This approach is well
aligned with context definitions that emphasize the dynamic and
activity-oriented nature of context. As an extension of the generic framework,
we describe Hybreed RecViews, a set of components facilitating the development
of context-aware and hybrid recommender systems. With Hybreed and RecViews,
developers can rapidly develop context-aware applications that generate
recommendations for both individual users and groups. The framework provides a
range of recommendation algorithms and strategies for producing group
recommendations as well as templates for combining different methods into
hybrid recommenders. Hybreed also provides means for integrating existing user
or product data from external sources such as social networks. It combines
aspects known from context processing frameworks with features of
state-of-the-art recommender system frameworks, aspects that have been
addressed only separately in previous research. To our knowledge, Hybreed is
the first framework to cover all these aspects in an integrated manner. To
evaluate the framework and its conceptual foundation, we verified its
capabilities in three different use cases. The evaluation also comprises a
comparative assessment of Hybreed's functional features, a comparison to
existing frameworks, and a user study assessing its usability for developers.
The results of this study indicate that Hybreed is intuitive to use and extend
by developers. Keywords: Recommender systems; Group recommendations; Context-aware recommendations;
Distributed user models; Framework | |||
| A case study of intended versus actual experience of adaptivity in a tangible storytelling system | | BIBAK | Full-Text | 175-217 | |
| Karen Tanenbaum; Marek Hatala; Joshua Tanenbaum; Ron Wakkary; Alissa Antle | |||
| This article presents a case study of an adaptive, tangible storytelling
system called "The Reading Glove". The research addresses a gap in the field of
adaptivity for ubiquitous systems by taking a critical look at the notion of
"adaptivity" and how users experience it. The Reading Glove is an interactive
storytelling system featuring a wearable, glove-based interface and a set of
narratively rich objects. A tabletop display provides adaptive recommendations
which highlight objects to select next, functioning as an expert storytelling
system. The recommendation engine can be run in three different configurations
to examine the effects of different adaptive methods. The study of the design
process as well as the user experience of the Reading Glove allows us to
develop a deeper understanding of the experience of adaptivity that is useful
for designers of intelligent systems, particularly those with ubiquitous and
tangible forms of interaction. Keywords: Adaptivity; Tangible computing; User models; Recommendation systems; Expert
systems; User experience | |||
| A comparative study of collaboration-based reputation models for social recommender systems | | BIBAK | Full-Text | 219-260 | |
| Kevin McNally; Michael P. O'Mahony; Barry Smyth | |||
| Today, people increasingly leverage their online social networks to discover
meaningful and relevant information, products and services. Thus, the ability
to identify reputable online contacts with whom to interact has become ever
more important. In this work we describe a generic approach to modeling user
and item reputation in social recommender systems. In particular, we show how
the various interactions between producers and consumers of content can be used
to create so-called collaboration graphs, from which the reputation of users
and items can be derived. We analyze the performance of our reputation models
in the context of the HeyStaks social search platform, which is designed to
complement mainstream search engines by recommending relevant pages to users
based on the past experiences of search communities. By incorporating
reputation into the existing HeyStaks recommendation framework, we demonstrate
that the relevance of HeyStaks recommendations can be significantly improved
based on data recorded during a live-user trial of the system. Keywords: Reputation; Social recommender systems; Collaboration graphs | |||
| Personalised viewing-time prediction in museums | | BIBAK | Full-Text | 263-314 | |
| Fabian Bohnert; Ingrid Zukerman | |||
| People are often overwhelmed by the large amount of information provided in
museum spaces, which makes it difficult for them to select exhibits of
potential interest. As a first step in recommending exhibits where a visitor
may wish to spend some time, this article investigates predictive user models
for personalised prediction of museum visitors' viewing times at exhibits. We
consider two content-based models and a nearest-neighbour collaborative filter,
and develop a collaborative model based on the theory of spatial processes
which relies on a notion of distance between exhibits. We discuss models of
exhibit distance derived from viewing-time similarity, semantic similarity and
walking distance. The results from our evaluation with a real-world dataset of
visitor pathways collected at Melbourne Museum (Melbourne, Australia) suggest
that utilising walking and semantic distances between exhibits enables more
accurate predictions of a visitor's viewing times of unseen exhibits than using
distances derived from observed exhibit viewing times. Our results also show
that all models outperform a non-personalised baseline, that content-based
viewing time prediction yields better results than nearest-neighbour
collaborative prediction, and that our collaborative model based on spatial
processes attains the highest predictive accuracy overall. Keywords: Predictive user modelling; Content-based user models; Collaborative user
models; Gaussian spatial processes; Cultural heritage | |||
| Identification of human implicit visual search intention based on eye movement and pupillary analysis | | BIBAK | Full-Text | 315-344 | |
| Young-Min Jang; Rammohan Mallipeddi; Minho Lee | |||
| We propose a novel approach for the identification of human implicit visual
search intention based on eye movement patterns and pupillary analysis, in
general, as well as pupil size, gradient of pupil size variation, fixation
length and fixation count corresponding to areas of interest, and fixation
count corresponding to non-areas of interest, in particular. The proposed model
identifies human implicit visual search intention as task-free visual browsing
or task-oriented visual search. Task-oriented visual search is further
identified as task-oriented visual search intent generation, task-oriented
visual search intent maintenance, or task-oriented visual search intent
disappearance. During a visual search, measurement of the pupillary response is
greatly influenced by external factors such the intensity and size of the
visual stimulus. To alleviate the effects of external factors, we propose a
robust baseline model that can accurately measure the pupillary response.
Graphical representation of the measured parameter values shows significant
differences among the different intent conditions, which can then be used as
features for identification. By using the eye movement patterns and pupillary
analysis, we can detect the transitions between different implicit intentions
-- task-free visual browsing intent to task-oriented visual search intent and
task-oriented visual search intent maintenance to task-oriented visual search
intent disappearance -- using a hierarchical support vector machine. In the
proposed model, the hierarchical support vector machine is able to identify the
transitions between different intent conditions with greater than 90% accuracy. Keywords: Implicit intention detection; Task-free visual browsing intent;
Task-oriented visual search intent; Intention recognition; Human computer
interface & interaction; Pupillary analysis; Eye tracking; Pupil dilation | |||