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

Proceedings of the 2010 ACM Conference on Recommender Systems

Fullname:Proceedings of the Fifth ACM Conference on Recommender Systems
Editors:Xavier Amatriain; Marc Torrens; Paul Resnick; Markus Zanker
Location:Barcelona, Spain
Dates:2010-Sep-26 to 2010-Sep-30
Publisher:ACM
Standard No:ISBN: 1-60558-906-3, 978-1-60558-906-0; ACM DL: Table of Contents hcibib: RecSys10
Papers:78
Pages:386
Links:Conference Home Page
  1. Tutorial program
  2. Industry panel
  3. Innovative preference expressions and usage assessments
  4. Contests: way forward or detour?
  5. Beyond prediction accuracy
  6. Algorithms
  7. All about groups
  8. Recommending in social networks
  9. Recommending non-standard items
  10. Friends and lovers
  11. Closing keynote
  12. Posters
  13. Demos
  14. Doctoral symposium
  15. Workshop program

Tutorial program

Tutorial on evaluating recommender systems BIBAFull-Text 1
  Guy Shani
In this tutorial we discuss the evaluation of recommender systems. We discuss the main reason for evaluating recommender systems, i.e., the selection task. We overview some general guidelines for conducting evaluation tests. We then discuss the evaluation of the system accuracy given specific system tasks. We also overview many properties of recommender systems, and explain how these properties can be evaluated.
Query intent prediction and recommendation BIBAFull-Text 5-6
  Ricardo Baeza-Yates
In this tutorial we first characterize user queries before focusing in two important problems related to search engines: query intention prediction and query recommendation.

Industry panel

Will recommenders kill search?: recommender systems -- an industry perspective BIBAFull-Text 7-12
  Ido Guy; Alejandro Jaimes; Pau Agulló; Pat Moore; Palash Nandy; Chahab Nastar; Henrik Schinzel
At the 2010 annual ACM Conference on Recommender Systems (RecSys 2010) a panel addressed emerging topics regarding recommender systems as a whole and specifically their role in industry. This report summarizes answers from a distinguished group of industry leaders representing different industries in which recommender systems are highly relevant. Panel members discuss questions regarding the role of recommender systems in their own industry area, killer applications, opportunities, and future directions.

Innovative preference expressions and usage assessments

Global budgets for local recommendations BIBAFull-Text 13-20
  Thomas Sandholm; Hang Ung; Christina Aperjis; Bernardo A. Huberman
We present the design, implementation and evaluation of a new geotagging service, Gloe, that makes it easy to find, rate and recommend arbitrary on-line content in a mobile setting. The service automates the content search process by taking advantage of geographic and social context, while using crowdsourced expertise to present a personalized feed of targeted information ranked by a novel geo-aware rating and incentive mechanism.
   Users rate the relevance of recommendations for particular locations using a limited, global voting budget. This budget is, in turn, increased by accurately predicting local content popularity. One of the key goals of our mechanism is to encourage ratings, and in an evaluation of the live system we found that the rating to click ratio was 107 times higher than the ratio for videos on YouTube, 34 times higher than the ratio for applications on the Android Market, and 3 times higher than the ratio for Web pages on Digg.
   To investigate whether our mechanism also had qualitative effects on the ratings we conducted a number of experiments on Amazon Mechanical Turk, with 500 users, comparing our mechanism to the de-facto 5-star ratings commonly in use on the Web. Our results show that budgets improved the ranking and incentives improved the aggregate rating of a series of location-dependent Web pages.
Aggregating preference graphs for collaborative rating prediction BIBAFull-Text 21-28
  Maunendra Sankar Desarkar; Sudeshna Sarkar; Pabitra Mitra
Collaborative filtering is a widely used technique for rating prediction in recommender systems. Memory based collaborative filtering algorithms assign weights to the users to capture similarities between them. The weighted average of similar users' ratings for the test item is output as prediction. We propose a memory based algorithm that is markedly different from the existing approaches. We use preference relations instead of absolute ratings for similarity calculations, as preference relations between items are generally more consistent than ratings across like-minded users. Each user's ratings are viewed as a preference graph. Similarity weights are learned using an iterative method motivated by online learning. These weights are used to create an aggregate preference graph. Ratings are inferred to maximally agree with this aggregate graph. The use of preference relations allows the rating of an item to be influenced by other items, which is not the case in the weighted-average approaches of the existing techniques. This is very effective when the data is sparse, specially for the items rated by few users. Our experiments show that the our method outperforms other methods in the sparse regions. However, for dense regions, sometimes our results are comparable to the competing approaches, and sometimes worse.
Eye-tracking product recommenders' usage BIBAFull-Text 29-36
  Sylvain Castagnos; Nicolas Jones; Pearl Pu
Recommender systems have emerged as an effective decision tool to help users more easily and quickly find products that they prefer, especially in e-commerce environments. However, few studies have tried to understand how this technology has influenced the way users search for products and make purchase decisions. Our current research aims at examining the impact of recommenders by understanding how recommendation tools integrate the classical economic schemes and how they modify product search patterns. We report our work in employing an eye tracking system and collecting users' interaction behaviors as they browsed and selected products to buy from an online product retail website offering over 3,500 items. This in-depth user study has enabled us to collect over 48,000 fixation data points and 7,720 areas of interest from eighteen users, each spending more than one hour on our site. Our study shows that while users still use traditional product search tools to examine alternatives, recommenders definitely provide users with new opportunities in their decision process. More specifically, users actively click and gaze at products recommended to them, up to 40% of the time. In addition, recommendation areas are highly attractive, drawing users to add 50% more items to their baskets as a traditional tool does. Observing that users consult the recommendation area more as they are close to the end of their search process, it seems that recommenders enhance users' decision confidence by satisfying their need for diversity. Based on these results, we derive several interaction design guidelines that can significantly improve users' satisfaction and perception of product recommenders.

Contests: way forward or detour?

Contests: way forward or detour? BIBAFull-Text 37-38
  Paul Resnick; Joseph A. Konstan; Andreas Hotho; Jesus Pindado
Contests and challenges have energized researchers and focused attention in many fields recently, including recommender systems. At the 2008 RecSys conference, winners were announced for a contest proposing new startup companies. The 2009 conference featured a panel reflecting on the then recently completed Netflix challenge.
   Would additional contests help move the field of recommender systems forward? Or would they just draw attention from the most important problems to problems that are most easily formulated as contests? If contests would be useful, what should the tasks be and how should performance be evaluated? The panel will begin with short presentations by the panelists. Following that, the panelists will respond to brief sketches of possible new contests. In addition to prediction and ranking tasks, tasks might include making creative use of the outputs of a fixed recommender engine, or eliciting inputs for a recommender engine.

Beyond prediction accuracy

Performance of recommender algorithms on top-n recommendation tasks BIBAFull-Text 39-46
  Paolo Cremonesi; Yehuda Koren; Roberto Turrin
In many commercial systems, the 'best bet' recommendations are shown, but the predicted rating values are not. This is usually referred to as a top-N recommendation task, where the goal of the recommender system is to find a few specific items which are supposed to be most appealing to the user. Common methodologies based on error metrics (such as RMSE) are not a natural fit for evaluating the top-N recommendation task. Rather, top-N performance can be directly measured by alternative methodologies based on accuracy metrics (such as precision/recall).
   An extensive evaluation of several state-of-the art recommender algorithms suggests that algorithms optimized for minimizing RMSE do not necessarily perform as expected in terms of top-N recommendation task. Results show that improvements in RMSE often do not translate into accuracy improvements. In particular, a naive non-personalized algorithm can outperform some common recommendation approaches and almost match the accuracy of sophisticated algorithms. Another finding is that the very few top popular items can skew the top-N performance. The analysis points out that when evaluating a recommender algorithm on the top-N recommendation task, the test set should be chosen carefully in order to not bias accuracy metrics towards non-personalized solutions. Finally, we offer practitioners new variants of two collaborative filtering algorithms that, regardless of their RMSE, significantly outperform other recommender algorithms in pursuing the top-N recommendation task, with offering additional practical advantages. This comes at surprise given the simplicity of these two methods.
On the stability of recommendation algorithms BIBAFull-Text 47-54
  Gediminas Adomavicius; Jingjing Zhang
The paper introduces stability as a new measure of the recommender systems performance. In general, we define a recommendation algorithm to be "stable" if its predictions for the same items are consistent over a period of time, assuming that any new ratings that have been submitted to the recommender system over the same period of time are in complete agreement with system's prior predictions. In this paper, we advocate that stability should be a desired property of recommendation algorithms, because unstable recommendations can lead to user confusion and, therefore, reduce trust in recommender systems. Furthermore, we empirically evaluate stability of several popular recommendation algorithms. Our results suggest that model-based recommendation techniques demonstrate higher stability than memory-based collaborative filtering heuristics. We also find that the stability measure for recommendation techniques is influenced by many factors, including the sparsity of the initial rating data, the number of new incoming ratings (representing the length of the time period over which the stability is being measured), the distribution of the newly added rating values, and the rating normalization procedures employed by the recommendation algorithms.
Optimizing multiple objectives in collaborative filtering BIBAFull-Text 55-62
  Tamas Jambor; Jun Wang
This paper is about the utility of making personalized recommendations. While it is important to accurately predict the target user's preference, in practice the accuracy should not be the only concern; a useful recommender system needs to consider the user's utility or satisfaction of fulfilling a certain information seeking task. For example, recommending popular items (products) is unlikely to result in more gain than discovering insignificant ("long tail") yet liked items because the popular ones might be already known to the user. Equally, recommending items that are out of stock would be frustrating for both the user and system if the system is employed to discover items to purchase. Thus, it is important to have a flexible recommendation framework that takes into account additional recommendation goals meanwhile minimizing the performance loss in order to provide greater adjustability and a better user experience.
   To achieve this, in this paper, we propose a general recommendation optimization framework that not only considers the predicted preference scores (e.g. ratings) but also deals with additional operational or resource related recommendation goals. Using this framework we demonstrate through realistic examples how to expand existing rating prediction algorithms by biasing the recommendation depending on other external factors such as the availability, profitability or usefulness of an item. Our experiments on real data sets demonstrate that this framework is indeed able to cope with multiple objectives with minor performance loss.
Understanding choice overload in recommender systems BIBAFull-Text 63-70
  Dirk Bollen; Bart P. Knijnenburg; Martijn C. Willemsen; Mark Graus
Even though people are attracted by large, high quality recommendation sets, psychological research on choice overload shows that choosing an item from recommendation sets containing many attractive items can be a very difficult task. A web-based user experiment using a matrix factorization algorithm applied to the MovieLens dataset was used to investigate the effect of recommendation set size (5 or 20 items) and set quality (low or high) on perceived variety, recommendation set attractiveness, choice difficulty and satisfaction with the chosen item. The results show that larger sets containing only good items do not necessarily result in higher choice satisfaction compared to smaller sets, as the increased recommendation set attractiveness is counteracted by the increased difficulty of choosing from these sets. These findings were supported by behavioral measurements revealing intensified information search and increased acquisition times for these large attractive sets. Important implications of these findings for the design of recommender system user interfaces will be discussed.

Algorithms

Fast ALS-based matrix factorization for explicit and implicit feedback datasets BIBAFull-Text 71-78
  István Pilászy; Dávid Zibriczky; Domonkos Tikk
Alternating least squares (ALS) is a powerful matrix factorization (MF) algorithm for both explicit and implicit feedback based recommender systems. As shown in many articles, increasing the number of latent factors (denoted by K) boosts the prediction accuracy of MF based recommender systems, including ALS as well. The price of the better accuracy is paid by the increased running time: the running time of the original version of ALS is proportional to K3. Yet, the running time of model building can be important in recommendation systems; if the model cannot keep up with the changing item portfolio and/or user profile, the prediction accuracy can be degraded.
   In this paper we present novel and fast ALS variants both for the implicit and explicit feedback datasets, which offers better trade-off between running time and accuracy. Due to the significantly lower computational complexity of the algorithm -- linear in terms of K -- the model being generated under the same amount of time is more accurate, since the faster training enables to build model with more latent factors. We demonstrate the efficiency of our ALS variants on two datasets using two performance measures, RMSE and average relative position (ARP), and show that either a significantly more accurate model can be generated under the same amount of time or a model with similar prediction accuracy can be created faster; for explicit feedback the speed-up factor can be even 5-10.
Multiverse recommendation: n-dimensional tensor factorization for context-aware collaborative filtering BIBAFull-Text 79-86
  Alexandros Karatzoglou; Xavier Amatriain; Linas Baltrunas; Nuria Oliver
Context has been recognized as an important factor to consider in personalized Recommender Systems. However, most model-based Collaborative Filtering approaches such as Matrix Factorization do not provide a straightforward way of integrating context information into the model. In this work, we introduce a Collaborative Filtering method based on Tensor Factorization, a generalization of Matrix Factorization that allows for a flexible and generic integration of contextual information by modeling the data as a User-Item-Context N-dimensional tensor instead of the traditional 2D User-Item matrix. In the proposed model, called Multiverse Recommendation, different types of context are considered as additional dimensions in the representation of the data as a tensor. The factorization of this tensor leads to a compact model of the data which can be used to provide context-aware recommendations.
   We provide an algorithm to address the N-dimensional factorization, and show that the Multiverse Recommendation improves upon non-contextual Matrix Factorization up to 30% in terms of the Mean Absolute Error (MAE). We also compare to two state-of-the-art context-aware methods and show that Tensor Factorization consistently outperforms them both in semi-synthetic and real-world data -- improvements range from 2.5% to more than 12% depending on the data. Noticeably, our approach outperforms other methods by a wider margin whenever more contextual information is available.
Collaborative filtering via euclidean embedding BIBAFull-Text 87-94
  Mohammad Khoshneshin; W. Nick Street
Recommendation systems suggest items based on user preferences. Collaborative filtering is a popular approach in which recommending is based on the rating history of the system. One of the most accurate and scalable collaborative filtering algorithms is matrix factorization, which is based on a latent factor model. We propose a novel Euclidean embedding method as an alternative latent factor model to implement collaborative filtering. In this method, users and items are embedded in a unified Euclidean space where the distance between a user and an item is inversely proportional to the rating. This model is comparable to matrix factorization in terms of both scalability and accuracy while providing several advantages. First, the result of Euclidean embedding is more intuitively understandable for humans, allowing useful visualizations. Second, the neighborhood structure of the unified Euclidean space allows very efficient recommendation queries. Finally, the method facilitates online implementation requirements such as mapping new users or items in an existing model. Our experimental results confirm these advantages and show that collaborative filtering via Euclidean embedding is a promising approach for online recommender systems.
Online evolutionary collaborative filtering BIBAFull-Text 95-102
  Nathan N. Liu; Min Zhao; Evan Xiang; Qiang Yang
Collaborative filtering algorithms attempt to predict a user's interests based on his past feedback. In real world applications, a user's feedback is often continuously collected over a long period of time. It is very common for a user's interests or an item's popularity to change over a long period of time. Therefore, the underlying recommendation algorithm should be able to adapt to such changes accordingly. However, most existing algorithms do not distinguish current and historical data when predicting the users' current interests. In this paper, we consider a new problem -- online evolutionary collaborative filtering, which tracks user interests over time in order to make timely recommendations. We extended the widely used neighborhood based algorithms by incorporating temporal information and developed an incremental algorithm for updating neighborhood similarities with new data. Experiments on two real world datasets demonstrated both improved effectiveness and efficiency of the proposed approach.

All about groups

Affiliation recommendation using auxiliary networks BIBAFull-Text 103-110
  Vishvas Vasuki; Nagarajan Natarajan; Zhengdong Lu; Inderjit S. Dhillon
Social network analysis has attracted increasing attention in recent years. In many social networks, besides friendship links amongst users, the phenomenon of users associating themselves with groups or communities is common. Thus, two networks exist simultaneously: the friendship network among users, and the affiliation network between users and groups. In this paper, we tackle the affiliation recommendation problem, where the task is to predict or suggest new affiliations between users and communities, given the current state of the friendship and affiliation networks. More generally, affiliations need not be community affiliations -- they can be a user's taste, so affiliation recommendation algorithms have applications beyond community recommendation. In this paper, we show that information from the friendship network can indeed be fruitfully exploited in making affiliation recommendations. Using a simple way of combining these networks, we suggest two models of user-community affinity for the purpose of making affiliation recommendations: one based on graph proximity, and another using latent factors to model users and communities. We explore the two classes of affiliation recommendation algorithms suggested by these models. We evaluate these algorithms on two real world networks -- Orkut and YouTube. In doing so, we motivate and propose a way of evaluating recommenders, by measuring how good the top 50 recommendations are for the average user, and demonstrate the importance of choosing the right evaluation strategy. The algorithms suggested by the graph proximity model turn out to be the most effective and efficient. This use of link prediction techniques for the purpose of affiliation recommendation is, to our knowledge, novel.
Group-based recipe recommendations: analysis of data aggregation strategies BIBAFull-Text 111-118
  Shlomo Berkovsky; Jill Freyne
Collaborative filtering recommendations were designed primarily for individual user models and recommendations. However, nowadays more and more scenarios evolve, in which the recommended items are consumed by groups of users rather than by individuals. This raises the need to uncover the most appropriate group-based collaborative filtering recommendation strategy. In this work we investigate the use of aggregated group data in collaborative filtering recipe recommendations. We present results of a study that exploits recipe ratings provided by families of users, in order to evaluate the accuracy of several group recommendation strategies and weighting models, and analyze the impact of switching strategies, data aggregation heuristics, and group characteristics on the performance of recommendations.
Group recommendations with rank aggregation and collaborative filtering BIBAFull-Text 119-126
  Linas Baltrunas; Tadas Makcinskas; Francesco Ricci
The majority of recommender systems are designed to make recommendations for individual users. However, in some circumstances the items to be selected are not intended for personal usage but for a group; e.g., a DVD could be watched by a group of friends. In order to generate effective recommendations for a group the system must satisfy, as much as possible, the individual preferences of the group's members.
   This paper analyzes the effectiveness of group recommendations obtained aggregating the individual lists of recommendations produced by a collaborative filtering system. We compare the effectiveness of individual and group recommendation lists using normalized discounted cumulative gain. It is observed that the effectiveness of a group recommendation does not necessarily decrease when the group size grows. Moreover, when individual recommendations are not effective a user could obtain better suggestions looking at the group recommendations. Finally, it is shown that the more alike the users in the group are, the more effective the group recommendations are.

Recommending in social networks

Interactive recommendations in social endorsement networks BIBAFull-Text 127-134
  Theodoros Lappas; Dimitrios Gunopulos
An increasing number of social networking platforms are giving users the option to endorse entities that they find appealing, such as videos, photos, or even other users. We define this model as a Social Endorsement Network, visualized as a bipartite graph with edges (endorsements) from users to endorsed entities. In this work, we formalize the problem of interactive recommendations in social endorsement networks: given a query of tags and a social endorsement network, the problem is to recommend entities that match the query and also share a significant number of common endorsers. We propose an efficient search engine for the solution of the problem, able to produce high-quality and explainable recommendations. The entire framework is designed in a principled and efficient manner, making it ideal for large-scale systems. In a thorough experimental evaluation on real datasets, we illustrate the efficacy of our methods and provide some valuable insight on social endorsement networks.
A matrix factorization technique with trust propagation for recommendation in social networks BIBAFull-Text 135-142
  Mohsen Jamali; Martin Ester
Recommender systems are becoming tools of choice to select the online information relevant to a given user. Collaborative filtering is the most popular approach to building recommender systems and has been successfully employed in many applications. With the advent of online social networks, the social network based approach to recommendation has emerged. This approach assumes a social network among users and makes recommendations for a user based on the ratings of the users that have direct or indirect social relations with the given user. As one of their major benefits, social network based approaches have been shown to reduce the problems with cold start users. In this paper, we explore a model-based approach for recommendation in social networks, employing matrix factorization techniques. Advancing previous work, we incorporate the mechanism of trust propagation into the model. Trust propagation has been shown to be a crucial phenomenon in the social sciences, in social network analysis and in trust-based recommendation. We have conducted experiments on two real life data sets, the public domain Epinions.com dataset and a much larger dataset that we have recently crawled from Flixster.com. Our experiments demonstrate that modeling trust propagation leads to a substantial increase in recommendation accuracy, in particular for cold start users.
Who is talking about what: social map-based recommendation for content-centric social websites BIBAFull-Text 143-150
  Shiwan Zhao; Michelle X. Zhou; Quan Yuan; Xiatian Zhang; Wentao Zheng; Rongyao Fu
Content-centric social websites, such as discussion forums and blog sites, have flourished during the past several years. These sites often contain overwhelming amounts of information that are also being updated rapidly. To help users locate their interests at such sites (e.g., interesting blogs to read or discussion forums to join), researchers have developed a number of recommendation technologies. However, it is difficult to make effective recommendations for new users (a.k.a. the cold start problem) due to a lack of user information (e.g., preferences and interests). Furthermore, the complexity of recommendation algorithms often prevents users from comprehending let alone trusting the recommended results. To tackle the above two challenges, we are building a social map-based recommender system called Pharos. A social map summarizes users' content-related social behavior over time (e.g., reading, writing, and commenting behavior during the past week) as a set of latent communities. Each community is characterized by the theme of the content being discussed and the key people involved. By discovering, ranking, and displaying the most "popular" latent communities, Pharos creates a visual social map of a website. This enables new users to obtain a quick overview of the site, alleviating the cold start problem. Furthermore, we use the social map as a context to help explain Pharos-recommended content and people. Users can also interactively explore the social map to locate their interested content or people that are not being explicitly recommended, compensating for the imperfection in the recommendation algorithms. We have deployed Pharos within our company and our preliminary evaluation shows the usefulness of Pharos.

Recommending non-standard items

Breaking out of the box of recommendations: from items to packages BIBAFull-Text 151-158
  Min Xie; Laks V. S. Lakshmanan; Peter T. Wood
Classical recommender systems provide users with a list of recommendations where each recommendation consists of a single item, e.g., a book or DVD. However, several applications can benefit from a system capable of recommending packages of items, in the form of sets. Sample applications include travel planning with a limited budget (price or time) and twitter users wanting to select worthwhile tweeters to follow given that they can deal with only a bounded number of tweets. In these contexts, there is a need for a system that can recommend top-k packages for the user to choose from.
   Motivated by these applications, we consider composite recommendations, where each recommendation comprises a set of items. Each item has both a value (rating) and a cost associated with it, and the user specifies a maximum total cost (budget) for any recommended set of items. Our composite recommender system has access to one or more component recommender system, focusing on different domains, as well as to information sources which can provide the cost associated with each item. Because the problem of generating the top recommendation (package) is NP-complete, we devise several approximation algorithms for generating top-k packages as recommendations. We analyze their efficiency as well as approximation quality. Finally, using two real and two synthetic data sets, we subject our algorithms to thorough experimentation and empirical analysis. Our findings attest to the efficiency and quality of our approximation algorithms for top-k packages compared to exact algorithms.
Automatically building research reading lists BIBAFull-Text 159-166
  Michael D. Ekstrand; Praveen Kannan; James A. Stemper; John T. Butler; Joseph A. Konstan; John T. Riedl
All new researchers face the daunting task of familiarizing themselves with the existing body of research literature in their respective fields. Recommender algorithms could aid in preparing these lists, but most current algorithms do not understand how to rate the importance of a paper within the literature, which might limit their effectiveness in this domain. We explore several methods for augmenting existing collaborative and content-based filtering algorithms with measures of the influence of a paper within the web of citations. We measure influence using well-known algorithms, such as HITS and PageRank, for measuring a node's importance in a graph. Among these augmentation methods is a novel method for using importance scores to influence collaborative filtering. We present a task-centered evaluation, including both an offline analysis and a user study, of the performance of the algorithms. Results from these studies indicate that collaborative filtering outperforms content-based approaches for generating introductory reading lists.
Learning in efficient tag recommendation BIBAFull-Text 167-174
  Marek Lipczak; Evangelos Milios
The objective of a tag recommendation system is to propose a set of tags for a resource to ease the tagging process done manually by a user. Tag recommendation is an interesting and well defined research problem. However, while solving it, it is easy to forget about its practical implications. We discuss the practical aspects of tag recommendation and propose a system that successfully addresses the problem of learning in tag recommendation, without sacrificing efficiency. Learning is realized in two aspects: adaptation to newly added posts and parameter tuning. The content of each added post is used to update the resource and user profiles as well as associations between tags. Parameter tuning allows the system to automatically adjust the way tag sources (e.g., content related tags or user profile tags) are combined to match the characteristics of a specific collaborative tagging system. The evaluation on data from three collaborative tagging systems confirmed the importance of both learning methods. Finally, an architecture based on text indexing makes the system efficient enough to serve in real time collaborative tagging systems with number of posts counted in millions, given limited computing resources.
Recommender algorithms in activity motivating games BIBAFull-Text 175-182
  Shlomo Berkovsky; Jill Freyne; Mac Coombe; Dipak Bhandari
Physical activity motivating game design encourages players to perform real physical activity in order to gain virtual game rewards. Previous research into activity motivating games showed that they have the potential to motivate players to perform physical activity, while retaining the enjoyment of playing. However, it was discovered that a uniform motivating approach resulted in different levels of activity performed by players of varying gaming skills. In this work we present and evaluate two adaptive recommendation-based techniques, which aim to balance the amount of physical activity performed by players by adapting the level of motivation to their observed gaming skills. Experimental evaluation showed that the adaptive techniques not only increase the amount of activity performed and retain the enjoyment of playing, but also balance the amount of activity performed by players of varying gaming skills and allow for game difficulty to be set in a player-dependent manner.

Friends and lovers

Transitive node similarity for link prediction in social networks with positive and negative links BIBAFull-Text 183-190
  Panagiotis Symeonidis; Eleftherios Tiakas; Yannis Manolopoulos
Online social networks (OSNs) like Facebook, and Myspace recommend new friends to registered users based on local features of the graph (i.e. based on the number of common friends that two users share). However, OSNs do not exploit the whole structure of the network. Instead, they consider only pathways of maximum length 2 between a user and his candidate friends. On the other hand, there are global approaches, which detect the overall path structure in a network, being computationally prohibitive for huge-size social networks. In this paper, we define a basic node similarity measure that captures effectively local graph features. We also exploit global graph features introducing transitive node similarity. Moreover, we derive variants of our method that apply in signed networks. We perform extensive experimental comparison of the proposed method against existing recommendation algorithms using synthetic and real data sets (Facebook, Hi5 and Epinions). Our experimental results show that our FriendTNS algorithm outperforms other approaches in terms of accuracy and it is also time efficient. We show that a significant accuracy improvement can be gained by using information about both positive and negative edges.
A lightweight privacy preserving SMS-based recommendation system for mobile users BIBAFull-Text 191-198
  Elisa Baglioni; Luca Becchetti; Lorenzo Bergamini; Ugo Colesanti; Luca Filipponi; Andrea Vitaletti; Giuseppe Persiano
In this paper we propose a fully decentralized approach for recommending new contacts in the social network of mobile phone users. With respect to existing solutions, our approach is characterized by some distinguishing features. In particular, the application we propose does not assume any centralized coordination: it transparently collects and processes user information that is accessible in any mobile phone, such as the log of calls, the list of contacts or the inbox/outbox of short messages and exchanges it with other users. This information is used to recommend new friendships to other users. Furthermore, the information needed to perform recommendation is collected and exchanged between users in a privacy preserving way. Finally, information necessary to implement the application is exchanged transparently and opportunistically, by using the residual space in standard short messages occasionally exchanged between users. As a consequence, we do not ask users to change their habits in using SMS.
Recommending twitter users to follow using content and collaborative filtering approaches BIBAFull-Text 199-206
  John Hannon; Mike Bennett; Barry Smyth
Recently the world of the web has become more social and more real-time. Facebook and Twitter are perhaps the exemplars of a new generation of social, real-time web services and we believe these types of service provide a fertile ground for recommender systems research. In this paper we focus on one of the key features of the social web, namely the creation of relationships between users. Like recent research, we view this as an important recommendation problem -- for a given user, UT which other users might be recommended as followers/followees -- but unlike other researchers we attempt to harness the real-time web as the basis for profiling and recommendation. To this end we evaluate a range of different profiling and recommendation strategies, based on a large dataset of Twitter users and their tweets, to demonstrate the potential for effective and efficient followee recommendation.
RECON: a reciprocal recommender for online dating BIBAFull-Text 207-214
  Luiz Pizzato; Tomek Rej; Thomas Chung; Irena Koprinska; Judy Kay
The reciprocal recommender is a class of recommender system that is important for several tasks where people are both the subjects and objects of the recommendation. Some examples are: job recommendation, mentor-mentee matching, and online dating. Despite the importance of this type of recommender, our work is the first to distinguish it and define its properties. We have implemented RECON, a reciprocal recommender for online dating, and have evaluated it on a large dataset from a major Australian dating website. We investigated the predictive power gained by taking account of reciprocity, finding that it is substantial, for example it improved the success rate of the top ten recommendations from 23% to 42% and also improved the recall at the same time. We also found reciprocity to help with the cold start problem obtaining a success rate of 26% for the top ten recommendations for new users. We discuss the implications of these results for broader uses of our approach for other reciprocal recommenders.

Closing keynote

Recommendation analytics: the business view, and the business case BIBAFull-Text 215-216
  Edouard Servan-Schreiber
This talk will cover how businesses perceive the value of analytics and recommendation analytics in particular. Amidst the tremendous progress in the techniques of recommendation analytics, businesses are noticing that effective recommendations must take into account the product type, inventory constraints, and delivery conditions.
   An effective recommendation must integrate context about the customer, the selection channel, and the particular timing. The ongoing revolutions in payment mechanisms and multi-channel shopping systems are introducing new, and often ignored, challenges to recommendation systems which this talk hopes to expose.

Posters

A belief propagation based recommender system for online services BIBAFull-Text 217-220
  Erman Ayday; Faramarz Fekri
In this paper we report our progress in the first application of iterative probabilistic algorithms in the design and evaluation of recommender systems. The proposed iterative recommender system (referred to as BPRS) is based on the belief propagation, a powerful decoding algorithm for turbo codes and Low-Density Parity-Check (LDPC) codes. The belief propagation algorithm relies on a graph-based representation of an appropriately chosen factor graph for the recommender systems. The factor graph representation of the recommender systems turned out to be a bipartite graph, where the users and products are arranged as two sets of variable and factor nodes that are connected via some edges. Recommendations (predicted ratings) for each particular user can be computed by probabilistic message passing between nodes in the graph. We provide an evaluation of BPRS via computer simulations using the MovieLens dataset. We observed that BPRS iteratively reduces the error in the predicted ratings of the users until it converges. Further, our initial results indicate an improvement in the Mean Average Error (MAE) and Root Mean Square Error (RMSE) over the Item Averaging. Therefore, we are confident that the belief propagation is a new promising approach which will offer robustness and accuracy for the recommender systems.
Using self-defined group activities for improving recommendations in collaborative tagging systems BIBAFull-Text 221-224
  Danielle H. Lee; Peter Brusilovsky
This paper aims to combine information about users' self-defined social connections with traditional collaborative filtering (CF) to improve recommendation quality. Specifically, in the following, the users' social connections in consideration were groups. Unlike other studies which utilized groups inferred by data mining technologies, we used the information about the groups in which each user explicitly participated. The group activities are centered on common interests. People join a group to share and acquire information about a topic as a form of community of interest or practice. The information of this group activity may be a good source of information for the members. We tested whether adding the information from the users' own groups or group members to the traditional CF-based recommendations can improve the recommendation quality or not. The information about groups was combined with CF using a mixed hybridization strategy. We evaluated our approach in two ways, using the Citeulike data set and a real user study.
Evaluating the dynamic properties of recommendation algorithms BIBAFull-Text 225-228
  Robin Burke
Collaborative recommendation algorithms are typically evaluated on a static matrix of user rating data. However, when users experience a recommender system, it is dynamic, constantly evolving as new items and new users arrive. The dynamic properties of collaborative recommendation have become important as prediction algorithms based on the interactions of rating histories have been proposed, and as researchers seek to understand problems of robustness and maintenance in rating databases.
   This paper proposes a new evaluation method for the dynamic aspects of collaborative algorithms, the "temporal leave-one-out" approach, which can provide insight into both user-specific and system-level evolution of recommendation behavior. As a case study, the methodology is applied to the Influence Limiter algorithm [12], showing that its robustness to attack comes at a high accuracy cost.
Hydra: an open framework for virtual-fusion of recommendation filters BIBAFull-Text 229-232
  Savvas Karagiannidis; Stefanos Antaris; Christos Zigkolis; Athena Vakali
Today's web commercial applications demand more powerful recommendation systems due to the rapid increase in the number of both consumers and available products. Searching for the best algorithm with the highest accuracy and realistic complexity is, most of the time, a very costly process in terms of both time and resources. In this paper we suggest an alternative framework called Hydra which enables the virtual fusion of any and as many currently available recommendation algorithms in such a distributed manner that algorithms' complexities are not summarized but parallelized. Therefore, we utilize the available algorithms and technologies aiming to achieve better accuracy in order to surpass even the most state of the art algorithms. In addition, Hydra can be used to find how algorithms interact with each other in order to estimate the resulting accuracy towards inventing a more precise algorithm diminishing the risk of a failed investment. Hydra can be adjusted and integrated in any recommendation application while it is also open to new functionalities which can be embedded easily and in a transparent manner.
Recommending based on rating frequencies BIBAFull-Text 233-236
  Fatih Gedikli; Dietmar Jannach
Since the development of the comparably simple neighborhood-based methods in the 1990s, a plethora of techniques has been developed to improve various aspects of collaborative filtering recommender systems like predictive accuracy, scalability to large problem instances or the capability to deal with sparse data sets. Many of the recent algorithms rely on sophisticated methods which are based, for instance, on matrix factorization techniques or advanced probabilistic models and/or require a computationally intensive model-building phase. In this work, we evaluate the accuracy of a new and extremely simple prediction method (RF-Rec) that uses the user's and the item's most frequent rating value to make a rating prediction. The evaluation on three standard test data sets shows that the accuracy of the algorithm is on a par with the standard collaborative filtering algorithms on dense data sets and outperforms them on sparse rating databases. At the same time, the algorithm's implementation is trivial, has a high prediction coverage, requires no complex offline pre-processing or model-building phase and can generate predictions in constant time.
Content-based recommendation in social tagging systems BIBAFull-Text 237-240
  Iván Cantador; Alejandro Bellogín; David Vallet
We present and evaluate various content-based recommendation models that make use of user and item profiles defined in terms of weighted lists of social tags. The studied approaches are adaptations of the Vector Space and Okapi BM25 information retrieval models. We empirically compare the recommenders using two datasets obtained from Delicious and Last.fm social systems, in order to analyse the performance of the approaches in scenarios with different domains and tagging behaviours.
Merging multiple criteria to identify suspicious reviews BIBAFull-Text 241-244
  Guangyu Wu; Derek Greene; Pádraig Cunningham
Assessing the trustworthiness of reviews is a key issue for the maintainers of opinion sites such as TripAdvisor, given the rewards that can be derived from posting false or biased reviews. In this paper we present a number of criteria that might be indicative of suspicious reviews and evaluate alternative methods for integrating these criteria to produce a unified "suspiciousness" ranking. The criteria derive from characteristics of the network of reviewers and also from analysis of the content and impact of reviews and ratings. The integration methods that are evaluated are singular value decomposition and the unsupervised hedge algorithm. These alternatives are evaluated in a user study on TripAdvisor reviews, where volunteers were asked to rate the suspiciousness of reviews that have been highlighted by the criteria.
Personalizing the settings for Cf-based recommender systems BIBAFull-Text 245-248
  Il Im; Byung Ho Kim
In this paper, we propose a new method for collaborative filtering (CF)-based recommender systems. Traditional CF-based recommendation algorithms have applied constant settings such as a reference group (neighborhood) size and a significance level to all users. In this paper we develop a new method that identifies optimal personalized settings for each user and applies them to generating recommendations for individual users. Personalized parameters are identified through iterative simulations with 'training' and 'verification' datasets. The method is compared with traditional 'constant settings' methods using Netflix data. The results show that the new method outperforms traditional, ordinary CF. Implications and future research directions are also discussed.
Do clicks measure recommendation relevancy?: an empirical user study BIBAFull-Text 249-252
  Hua Zheng; Dong Wang; Qi Zhang; Hang Li; Tinghao Yang
Evaluation have been an important subject since the early days of recommender systems. In online test, the click-through rate (CTR) is often adopted as the metric. However, recommended items with higher CTR does not imply higher relevance of two items since factors like item popularity or item serendipity may influence user's click behavior. We argue that the relevance of recommendation system is also desirable in many real applications. Here relevant means relevance in a human perceptible way. Relevant recommendations not only increase the users' trust to the system but are extremely useful for the vast number of anonymous user as their recommendations may only be made based on the current item. In this paper, we empirically examine the relation between the relevance of recommendations and the corresponding CTR with a few representative ItemCF algorithms through online data from a TV show/movie website, Hulu. Experiments show that algorithms with higher overall CTR may not correspond to higher relevance. Thus CTR may not be the optimal metric for online evaluation of recommender systems if producing relevant recommendations is of importance.
A supervised machine learning link prediction approach for academic collaboration recommendation BIBAFull-Text 253-256
  Nesserine Benchettara; Rushed Kanawati; Céline Rouveirol
In this work we tackle the problem of link prediction in co-authoring network. We apply a topological dyadic supervised machine learning approach for that purpose. A co-authoring network is actually obtained by the projection of a two-mode graph (an authoring graph linking authors to publications they have signed) over the authors set. We show that link prediction performances can be substantially enhanced by analyzing not only the co-authoring network, but also the dual graph obtained by projecting the original two-mode network over the set of publications.
Beyond accuracy: evaluating recommender systems by coverage and serendipity BIBAFull-Text 257-260
  Mouzhi Ge; Carla Delgado-Battenfeld; Dietmar Jannach
When we evaluate the quality of recommender systems (RS), most approaches only focus on the predictive accuracy of these systems. Recent works suggest that beyond accuracy there is a variety of other metrics that should be considered when evaluating a RS. In this paper we focus on two crucial metrics in RS evaluation: coverage and serendipity. Based on a literature review, we first discuss both measurement methods as well as the trade-off between good coverage and serendipity. We then analyze the role of coverage and serendipity as indicators of recommendation quality, present novel ways of how they can be measured and discuss how to interpret the obtained measurements. Overall, we argue that our new ways of measuring these concepts reflect the quality impression perceived by the user in a better way than previous metrics thus leading to enhanced user satisfaction.
Recommending structure in collaborative semistructured information systems BIBAFull-Text 261-264
  Eva Zangerle; Wolfgang Gassler; Günther Specht
Semistructured data provides the users of a community-based information system with the flexibility to store information without having to adhere to any predefined, rigid schema. However, such flexibility needs to be used with caution as it can lead to a very heterogeneous data structure and is therefore not feasible in terms of unified data access and search functionality. We present an approach which avoids such proliferation of substructures and provides the inserting user with recommendations, which are responsible for the creation of a commonly used structure. The presented recommendation algorithm adapts the recommendations to the stored information and its structure created by the community.
Iterative voting under uncertainty for group recommender systems BIBAFull-Text 265-268
  Lihi Naamani Dery; Meir Kalech; Lior Rokach; Bracha Shapira
Group Recommendation Systems (GRS) aim at recommending items that are relevant for the joint interest of a group of users. Voting mechanisms assume that users rate all items in order to identify an item that suits the preferences of all group members. This assumption is not feasible in sparse rating scenarios which are common in the recommender systems domain. In this paper we examine an application of voting theory to GRS. We propose a method to accurately determine the winning item while using a minimal set of the group members ratings, assuming that the recommender system has probabilistic knowledge about the distribution of users' ratings of items in the system. Since computing the optimal minimal set of ratings is computationally intractable, we propose two heuristic algorithms that proceed iteratively that aiming atto minimizing the number of required ratings, until identifying a "winning item". Experiments with the Netflix data show that the proposed algorithms reduce the required number of ratings for identifying the "winning item" by more than 50%.
List-wise learning to rank with matrix factorization for collaborative filtering BIBAFull-Text 269-272
  Yue Shi; Martha Larson; Alan Hanjalic
A ranking approach, ListRank-MF, is proposed for collaborative filtering that combines a list-wise learning-to-rank algorithm with matrix factorization (MF). A ranked list of items is obtained by minimizing a loss function that represents the uncertainty between training lists and output lists produced by a MF ranking model. ListRank-MF enjoys the advantage of low complexity and is analytically shown to be linear with the number of observed ratings for a given user-item matrix. We also experimentally demonstrate the effectiveness of ListRank-MF by comparing its performance with that of item-based collaborative recommendation and a related state-of-the-art collaborative ranking approach (CoFiRank).
Nantonac collaborative filtering: a model-based approach BIBAFull-Text 273-276
  Toshihiro Kamishima; Shotaro Akaho
A recommender system has to collect users' preference data. To collect such data, rating or scoring methods that use rating scales, such as good-fair-poor or a five-point-scale, have been employed. We replaced such collection methods with a ranking method, in which objects are sorted according to the degree of a user's preference. We developed a technique to convert the rankings to scores based on order statistics theory. This technique successfully improved the accuracy of ranking recommended items. However, we targeted only memory-based recommendation algorithms. To test whether or not the use of ranking methods and our conversion technique are effective for wide variety of recommenders, we apply our conversion technique to model-based algorithms.
Social networking feeds: recommending items of interest BIBAFull-Text 277-280
  Jill Freyne; Shlomo Berkovsky; Elizabeth M. Daly; Werner Geyer
The success of social media has resulted in an information overload problem, where users are faced with hundreds of new contributions, edits and communications at every visit. A prime example of this in social networks is the news or activity feeds, where the actions (friending, commenting, photo sharing, etc) of friends on the network are presented to users in order to inform them of the network activity. In this work we endeavour to reduce the burden on individuals of identifying interesting updates in social network news feeds by automatically identifying and recommending relevant items to individuals where item relevance is based on the observed interactions of the individual with the social network. The results of our offline study show that combining short term interest models, exploiting previous viewing behavior of users, and long-term models, exploiting previous viewing of network actions, was the best predictor of feed item relevance.
Time dependency of data quality for collaborative filtering algorithms BIBAFull-Text 281-284
  Toon De Pessemier; Simon Dooms; Tom Deryckere; Luc Martens
The efficiency of personal suggestions generated by collaborative filtering techniques is highly dependent on the quality and quantity of the available consumption data. Extending data sets with additional consumption data (from the past) might enrich the user profiles and generally leads to more accurate recommendations. Although if a considerable amount of profile information is already available and detailed personal preferences can be derived, supplementary consumption data may not have any (or a very limited) added value for the recommendation algorithm. These additional consumption data increase the required storage capacity and the computational load to generate the personal recommendations. Moreover, since personal preferences and the relevance of content items may vary over time, older consumption data might be outdated and lead to inaccurate recommendations. Therefore, we investigate which consumption data are (the most) relevant to feed the conventional collaborative filtering algorithms. For provider-generated content systems, we demonstrate that the accuracy of collaborative filtering algorithms increases by extending user profiles with additional older consumption data. In contrast, we witness the opposite effect for user-generated content systems: involving older consumption data has a negative influence on the recommender accuracy. These results are important for website owners who intend to employ a recommendation system at a minimum storage and computation cost.
MED-StyleR: METABO diabetes-lifestyle recommender BIBAFull-Text 285-288
  Stephan Hammer; Jonghwa Kim; Elisabeth André
Lifestyle plays an essential role in controlling diabetes and in both the prevention and management of diabetes. Many reports from clinical research support the theory that healthy eating and regular exercise are much more effective at managing diabetes than traditional medication. In this paper we introduce an innovative approach to the multimodal recommender system conceived in the EU METABO project. The most important feature of the METABO Diabetes-Lifestyle Recommender (MED-StyleR) is to generate highly personalized recommendations that satisfy medical prescriptions for patients' long-term health alongside and short-term preferences of patients in their daily lives.
Towards context-aware personalization and a broad perspective on the semantics of news articles BIBAFull-Text 289-292
  Jeremy Jancsary; Friedrich Neubarth; Harald Trost
We analyze preferences and the reading flow of users of a popular Austrian online newspaper. Unlike traditional news filtering approaches, we postulate that a user's preference for particular articles depends not only on the topic and on propositional contents, but also on the user's current context and on more subtle attributes. Our assumption is motivated by the observation that many people read newspapers because they actually enjoy the process. Such sentiments depend on a complex variety of factors. The present study is part of an ongoing effort to bring more advanced personalization to online media. Towards this end, we present a systematic evaluation of the merit of contextual and non-propositional features based on real-life clickstream and postings data. Furthermore, we assess the impact of different recommendation strategies on the learning performance of our system.
The YouTube video recommendation system BIBAFull-Text 293-296
  James Davidson; Benjamin Liebald; Junning Liu; Palash Nandy; Taylor Van Vleet; Ullas Gargi; Sujoy Gupta; Yu He; Mike Lambert; Blake Livingston; Dasarathi Sampath
We discuss the video recommendation system in use at YouTube, the world's most popular online video community. The system recommends personalized sets of videos to users based on their activity on the site. We discuss some of the unique challenges that the system faces and how we address them. In addition, we provide details on the experimentation and evaluation framework used to test and tune new algorithms. We also present some of the findings from these experiments.
Increasing consumers' understanding of recommender results: a preference-based hybrid algorithm with strong explanatory power BIBAFull-Text 297-300
  Paul Marx; Thorsten Hennig-Thurau; André Marchand
Recommender systems are intended to assist consumers by making choices from a large scope of items. While most recommender research focuses on improving the accuracy of recommender algorithms, this paper stresses the role of explanations for recommended items for gaining acceptance and trust. Specifically, we present a method which is capable of providing detailed explanations of recommendations while exhibiting reasonable prediction accuracy. The method models the users' ratings as a function of their utility part-worths for those item attributes which influence the users' evaluation behavior, with part-worth being estimated through a set of auxiliary regressions and constrained optimization of their results. We provide evidence that under certain conditions the proposed method is superior to established recommender approaches not only regarding its ability to provide detailed explanations but also in terms of prediction accuracy. We further show that a hybrid recommendation algorithm can rely on the content-based component for a majority of the users, switching to collaborative recommendation only for about one third of the user base.
The network effects of recommending social connections BIBAFull-Text 301-304
  Elizabeth M. Daly; Werner Geyer; David R. Millen
Social networking sites have begun to be used in the enterprise as a method of connecting employees. Recommender systems may be used to recommend social contacts in order to increase user engagement, encourage collaboration and facilitate expertise discovery. This paper evaluates the effects of four recommendation algorithms on the network as a whole and the social structure. We demonstrate that depending on the basis of the recommendation algorithm the effects on the network vary greatly and their potential impact should be understood. It is hoped this research can be used as guidance for future recommendation algorithms.
On the real-time web as a source of recommendation knowledge BIBAFull-Text 305-308
  Sandra Garcia Esparza; Michael P. O'Mahony; Barry Smyth
The so-called real-time web (RTW) is a web of opinions, comments, and personal viewpoints, often expressed in the form of short, 140-character text messages providing abbreviated and personalized commentary in real-time. Twitter is undoubtedly the king of the RTW. It boasts 100+ million users and generates in the region of 50m tweets per day. This RTW data is far from the structured data (ratings, product features, etc.) familiar to recommender systems research, but it is useful to consider its applicability to recommendation scenarios. In this short paper we describe an experiment to look at harnessing the real-time opinions of movie fans, expressed through the Twitter-like short textual reviews available on the Blippr service (www.blippr.com). In particular we describe how users and movies can be represented from the terms used in their associated reviews and describe a number of experiments to highlight the recommendation potential of this RTW data-source and approach.
LDA for on-the-fly auto tagging BIBAFull-Text 309-312
  Ernesto Diaz-Aviles; Mihai Georgescu; Avaré Stewart; Wolfgang Nejdl
In this paper, we propose a method for automatic tagging sparse and short textual resources. In the presence of a new resource, our method creates an ad hoc corpus of related resources, then applies Latent Dirichlet Allocation (LDA) to elicit latent topics for the resource and the associated corpus. This is done in order to automatically tag the resource based on the most likely tags derived from the latent topics identified. We evaluate our method, using an offline analysis on publicly available BibSonomy dataset and an online study, showing its effectiveness.
On-demand set-based recommendations BIBAFull-Text 313-316
  Suhrid Balakrishnan
This paper investigates the problem of generating on-demand recommendations over a dataset of items where the input is a selection of a few of the items. As an example in the context of a movie dataset, the user may wish to see a list of movies related to the three animation movies 'Finding Nemo', 'Up' and 'Spirited Away'. In this case, it would be expected that the list returned would contain other animation movies like 'Wall-E', 'Princess Mononoke' etc. Thus, this problem can be viewed as a type of "clustering on demand" problem [1]. It is the set form of input that distinguishes this problem from a standard information retrieval problem where the query is usually a single item or an abstraction of a single item in the dataset. In this paper, we present several new approaches to dealing with this problem. We also show some representative results on a movie text dataset.
Characterisation of explicit feedback in an online music recommendation service BIBAFull-Text 317-320
  Gawesh Jawaheer; Martin Szomszor; Patty Kostkova
In this paper, we present our study and characterisation of explicit and implicit feedback on Last.fm, an online music station and recommender service. The dataset consisted of explicit positive feedback (through loved tracks) and implicit positive feedback (the number of times a track is played). As one would expect, our analysis shows that explicit feedback is very scarce. However, we also found that the rate at which a user provides explicit feedback decreases with time, and that overall leaving explicit feedback has a negative effect on the user's behaviour.
An approach to situational market segmentation on on-line newspapers based on current tasks BIBAFull-Text 321-324
  Anne Gutschmidt
We discuss how a task-based situational market segmentation may be applied to on-line newspapers, distinguishing between fact finding, information gathering and browsing. During a period of four weeks we had 41 users keep a diary and recorded their surfing behavior on different on-line newspapers. The results of a Naive Bayes classification with feature selection indicate that content-related attributes such as the number of news categories browsed are indispensable for task recognition.
Incremental collaborative filtering via evolutionary co-clustering BIBAFull-Text 325-328
  Mohammad Khoshneshin; W. Nick Street
Collaborative filtering is a popular approach for building recommender systems. Current collaborative filtering algorithms are accurate but also computationally expensive, and so are best in static off-line settings. It is desirable to include the new data in a collaborative filtering model in an online manner, requiring a model that can be incrementally updated efficiently. Incremental collaborative filtering via co-clustering has been shown to be a very scalable approach for this purpose. However, locally optimized co-clustering solutions via current fast iterative algorithms give poor accuracy. We propose an evolutionary co-clustering method that improves predictive performance while maintaining the scalability of co-clustering in the online phase.
Modeling recommendation as a social choice problem BIBAFull-Text 329-332
  Massimiliano Albanese; Antonio d'Acierno; Vincenzo Moscato; Fabio Persia; Antonio Picariello
In the classical theory of social choice, a set of voters is called to rank a set of alternatives and a social ranking of the alternatives is generated. In this paper, we model recommendation in the context of browsing systems as a social choice problem, where the set of voters and the set of alternatives both coincide with the set of objects in the data collection. We then propose an importance ranking method that strongly resembles the well known PageRank ranking system, and takes into account both the browsing behavior of the users and the intrinsic features of the objects in the collection. We apply the proposed approach in the context of multimedia browsing systems and show that it can generate effective recommendations and can scale well for large data collections.
Social navigation for the spoken web BIBAFull-Text 333-336
  Robert G. Farrell; Nitendra Rajput; Rajarshi Das; Catalina Danis; Ketki Dhanesha
This paper describes our experiences deploying a recommender system for a mobile phone-based knowledge sharing application to farmers in rural India. Users of the system record questions and call back for answers left by other users and experts. We used collaborative filtering to derive relevant content for each user based on historical navigation patterns of the community. An empirical analysis of behavioral and interview data reveals key issues for future mobile recommender systems in developing regions of the world.
Common attributes in an unusual context: predicting the desirability of a social match BIBAFull-Text 337-340
  Julia M. Mayer; Sara Motahari; Richard P. Schuler; Quentin Jones
Social matching systems recommend people to other people. With the widespread adoption of smartphones, mobile social matching systems could potentially transform our social landscape. However, we have a limited understanding of what makes a good social match in the mobile context. We present a theoretical framework which outlines how a user's context and the rarity of different affinity measures in various contexts (match rarity) can be used to provide valuable social matches. We suggest that if a user attribute is very rare in a particular context, users will generally be more interested in an affinity match. We conducted a survey study to assess this framework with 117 respondents. We found that both context and match rarity significantly influence interest in a social match. These results validate the key aspects of the framework. We discuss the results in terms of implications for social matching system design.
Active learning driven by rating impact analysis BIBAFull-Text 341-344
  Carlos Eduardo Mello; Marie-Aude Aufaure; Geraldo Zimbrao
Many works have been proposed in order to improve the recommendation accuracy. Algorithms aiming to improve recommendation accuracy have been developed and evaluated. These algorithms usually work with training data sets which are learned and used to make predictions on users' tastes. The training data set choice is a difficult task not only due to the technical nature of the algorithm used, but also because of the user issues associated with the acquisition of their opinions, since the training data consist of users' opinions. In this work we show the importance of understanding which predictions are impacted when a rating is acquired by developing a naïve active learning criterion based on the number of impacted predictions. To do that, a Rating Impact Analysis method for the user-based collaborative filtering is proposed and applied to the active learning issue.

Demos

Tagmantic: a social recommender service based on semantic tag graphs and tag clusters BIBAFull-Text 345-346
  János Moldvay; Ingo Bax; Alexander Frerichs; Mirko Schuh
Tagmantic.com is a web based social recommendation and search service which exploits the rich information within folksonomies. By developing multiple layers of organizational structure on top of folksonomies the relations between tags, users and resources can be utilized in order to create advanced recommender engines. The first layer of organizational structure is a tag graph which relates different entities within the folksonomy to each other. Its nodes are the concepts of the folksonomy presented by tags and the edges describe the relationships between these concepts. The second layer of organizational structure are tag clusters, which are build on top of the above mentioned tag graphs and represent the ontology of the underlying folksonomy. These Ontologies as well as the less complex tag graphs are utilized by the recommender algorithms within tagmantic in order to provide a unique and intuitive user experience of exploring and searching content in the internet. The methodology can be applied to different types of folksonomies which implies an enormous potential for future development of new recommender engines.
Geolocated movie recommendations based on expert collaborative filtering BIBAFull-Text 347-348
  Josep Bachs Barrio; Xavier Amatriain Rubio
In this demo, we propose to showcase a mobile application for personalized and geolocated movie recommendations. While there is a wide range of cinema and movies applications for mobile platforms such as iPhone, ours includes a Recommender System based on Expert Collaborative Filtering that provides recommendations tailored to the user's preferences.
Music recommendations with temporal context awareness BIBAFull-Text 349-352
  Toni Cebrián; Marc Planagumà; Paulo Villegas; Xavier Amatriain
We present a system capable of recommending music playlists that take into account the temporal context of the user, i.e. they select user preferences as learned for the concrete time situation of the request.
Reciprocal recommender system for online dating BIBAFull-Text 353-354
  Luiz Pizzato; Tomek Rej; Thomas Chung; Irena Koprinska; Kalina Yacef; Judy Kay
Reciprocal recommender is a class of recommender systems that is important for tasks where people are both the subject and the object of the recommendation; one such task is online dating. We have implemented RECON, a reciprocal recommender for online dating, and we have evaluated it on a major dating website. Results show an improved success rate for recommendations that consider reciprocity in comparison to recommendations that only consider the preferences of the users receiving the recommendations.
Integrating broadcast and web video content into personal tv channels BIBAFull-Text 355-356
  Verus Pronk; Mauro Barbieri; Jan Korst; Adolf Proidl
Despite, or exactly because of the wealth of video content available on the Web, it is often cumbersome to obtain access to exactly the content you like. It is an active process of filtering and making choices, often requiring searches through long lists of alternatives.
   Building upon the concept of personal TV channels, we demonstrate how Web video content can be seamlessly integrated with broadcast video content, thereby also providing personalized Web content.

Doctoral symposium

Design and user issues in personality-based recommender systems BIBAFull-Text 357-360
  Rong Hu
Recommender systems have emerged as an intelligent information filtering tool to help users effectively identify information items of interest from an overwhelming set of choices and provide personalized services. Studies show that personality influences human decision making process and interests. However, little research has ventured in incorporating it into recommender systems. The utilization of personality characteristics into recommender systems and the exploration of user perception to such systems are the focuses of my thesis. The overall goal is to develop an efficient personality-based recommender system and to arrive at a series of design guidelines from the perspective of human computer interaction. In this paper, I present my up-to-date results on a proposed personality-based music recommender prototype, user perception investigations, and my ongoing research about addressing new user problem by utilizing personality characteristics. Finally, I shall present future works.
Enhanced vector space models for content-based recommender systems BIBAFull-Text 361-364
  Cataldo Musto
The use of Vector Space Models (VSM) in the area of Information Retrieval is an established practice within the scientific community. The reason is twofold: first, its very clean and solid formalism allows us to represent objects in a vector space and to perform calculations on them. On the other hand, as proved by many contributions, its simplicity does not hurt the effectiveness of the model. Although Information Retrieval and Information Filtering undoubtedly represent two related research areas, the use of VSM in Information Filtering is much less analyzed.
   The goal of this work is to investigate the impact of vector space models in the Information Filtering area. Specifically, I will introduce two approaches: the first one, based on a technique called Random Indexing, reduces the impact of two classical VSM problems, this is to say its high dimensionality and the inability to manage the semantics of documents. The second extends the previous one by integrating a negation operator implemented in the Semantic Vectors1 open-source package. The results emerged from an experimental evaluation performed on a large dataset and the applicative scenarios opened by these approaches confirmed the effectiveness of the model and induced to investigate more these techniques.
Identifying and utilizing contextual data in hybrid recommender systems BIBAFull-Text 365-368
  Alan Said
Context-aware recommender systems are becoming a popular topic, still, there are many untouched aspects. In this paper, research involving context identification and the concepts related to hybrid and context-aware systems is presented. A conceptual architecture for a context-aware recommender system for movies and TV shows is furthermore introduced. The system consists of a number of processes for context identification and recommendation. Key contextual features are identified and used for the creation of several sets of recommendations, based on the predicted context. The main focus of the research presented here is the identification of context, which in turn is used for recommendation. The results will be evaluated and incorporated into the recommendation engine of movie and TV recommendation website Moviepilot.
Topic-based recommendations in enterprise social media sharing platforms BIBAFull-Text 369-372
  Rafael Schirru
Nowadays, many companies deploy social media technologies to foster the knowledge transfer in the enterprise. As the amount of available content in such systems grows, there is an increasing need for recommender systems that provide recommendations according to the knowledge workers' needs and preferences. We propose a topic-based recommender system for Enterprise 2.0 resource sharing platforms. The system identifies the knowledge workers' short-term and long-term topics of interest by applying algorithms from the domain of topic detection and tracking and generates recommendations with a high degree of inter-topic diversity.

Workshop program

Workshop on the practical use of recommender systems algorithms & technology BIBAFull-Text 373-374
  Jerome Picault; Dimitre Kostadinov; Pablo Castells; Alejandro Jaimes
User modeling, adaptation, and personalization techniques have hit the mainstream. The explosion of social network websites, on-line user-generated content platforms, and the tremendous growth in computational power of mobile devices are generating incredibly large amounts of user data, and an increasing desire of users to "personalize" (their desktop, e-mail, news site, phone). The potential value of personalization has become clear both as a commodity for the benefit or enjoyment of end-users, and as an enabler of new or better services -- a strategic opportunity to enhance and expand businesses. An exciting characteristic of recommender systems is that they draw the interest of industry and businesses while posing very interesting research and scientific challenges.
   In spite of significant progress in the research community, and industry efforts to bring the benefits of new techniques to end-users, there are still important gaps that make personalization and adaptation difficult for users. Research activities still often focus on narrow problems, such as incremental accuracy improvements of current techniques, sometimes with ideal hypotheses, or tend to overspecialize on a few applicative problems (typically TV or movie recommenders -- sometimes simply because of the availability of data). This restrains de facto the range of other applications where personalization technologies might be useful as well. Thus, we may have reached a good point to take a step back to seek perspective in the research done in recommender systems. This workshop contrives for a new uptake on past experiences and lessons learned. We propose an analytic outlook on new research directions, or ones that still require substantial research, with a special focus on their practical adoption in working applications, and the barriers to be met in this path.
   This workshop is an opportunity to bring together researchers and practitioners to discuss, on one hand, the main lessons drawn from successes but also from failures of recommender systems, and on the other hand, identify and analyze the major research areas in recommendation and personalization technologies that should be addressed in the future for a practical, effective take-up of the needs of vendors, consumers, and technology providers. Selected papers fall into the following areas.
   Limits of recommender systems: main bottlenecks, research dead ends and myths in recommender systems; missing technology pieces for wider adoption; social (privacy, culture) issue.
   Analytical view of personalization experiences: case studies of recommender system implementations & deployments; evaluation and user studies of recommender systems, scalability in large recommender systems, lessons learnt from your past experience, obstacles to massive deployment of recommendation solutions in industrial environment.
   Recommender systems in broader systems: place of recommender systems in complete systems, killer application are.Next needs in recommender systems: new business models related to recommendation, social and cultural impact of recommender systems, new paradigms to provide recommendations, new areas for recommendations, users' expectations about future recommender systems, beyond one-shot recommendations: recommendations of sequences, goal-oriented recommendations.
   The workshop combines short paper presentations with open discussion sessions. Papers are grouped by topics allowing us to organize an open discussion for every topic.
   The workshop has received twelve submissions. The list of accepted papers and the workshop schedule can be found at the workshop's homepage: http://ir.ii.uam.es/prsat201
Workshop on information heterogeneity and fusion in recommender systems (HetRec 2010) BIBFull-Text 375-376
  Peter Brusilovsky; Iván Cantador; Yehuda Koren; Tsvi Kuflik; Markus Weimer
Workshop on recommender systems for technology enhanced learning BIBAFull-Text 377-378
  Nikos Manouselis; Hendrik Drachsler; Katrien Verbert; Olga C. Santos
This workshop presents the current status related to the design, development and evaluation of recommender systems in educational settings. It emphasizes the importance of recommender systems for Technology Enhanced Learning (TEL) to support learners with personalized learning resources and suitable peer learners to improve their learning process. Moreover, it proposes a dataTEL challenge to obtain data sets from TEL applications that can be used to benchmark algorithms specifically for the TEL context.
2nd workshop on recommender systems and the social web BIBAFull-Text 379-380
  Werner Geyer; Jill Freyne; Bamshad Mobasher; Sarabjot Singha Anand; Casey Dugan
The exponential growth of the Social Web both poses challenges, and presents opportunities for Recommender System research. The Social Web has turned information consumers into active contributors who generate large volumes of rapidly changing online data. Recommender Systems strive to identify relevant content for users at the right time and in the right context but achieving this goal has become more difficult, in part due to the volume and nature of information contributed through the Social Web.
   The emergence of the Social Web marked a change in Web users' attitude to online privacy and sharing. Social media systems encourage users to implicitly and explicitly provide large volumes of information which previously they would have been reluctant to share. This information includes personal details such as location, age, and interests, friendship networks, bookmarks and tags, opinion and preferences which can be captured explicitly or more often by monitoring user interaction with the systems (e.g. commenting, friending, rating, tagging etc).
   These new sources of knowledge can be leveraged by Recommender Systems to improve existing techniques and develop new strategies which focus on social recommendation. In turn recommender technologies can play a huge part in fuelling the success of the Social Web phenomenon by reducing the information overload problem facing social media users.
   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. The topics of the submitted papers included, among others, the following main areas:
   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 system mash-ups, Web 2.0 user interfaces, rich media recommender systems. Recommender applications involving users and 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 and microformats. Empirical evaluation of social recommender techniques, success and failure measures. Social recommender systems in the enterprise
   The list of short papers, the workshop schedule and downloadable versions of the papers can be found at the workshop's homepage at: http://www.dcs.warwick.ac.uk/~ssanand/RSWEb.htm and are also published at: http://ftp.informatik.rwth-aachen.de/Publications/CEUR-WS/
Workshop report: WOMRAD 2010 BIBAFull-Text 381-382
  Amélie Anglade; Claudio Baccigalupo; Norman Casagrande; Òscar Celma; Paul Lamere
This is the workshop report for WOMRAD 2010, the Workshop on Music Recommendation and Discovery held on 26th September 2010 in conjunction with ACM RecSys in Barcelona Spain.
Workshop on user-centric evaluation of recommender systems and their interfaces BIBFull-Text 383-384
  Bart P. Knijnenburg; Lars Schmidt-Thieme; Dirk G. F. M. Bollen
Context-awareness in recommender systems: research workshop and movie recommendation challenge BIBAFull-Text 385-386
  Gediminas Adomavicius; Alexander Tuzhilin; Shlomo Berkovsky; Ernesto W. De Luca; Alan Said
CARS and CAMRa were organized under the Context-awareness in Recommendation Systems special event and gathered academic researchers as well as industrial practitioners in a workshop and challenge.