Suchergebnisse

This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in RecSys '14 Proceedings of the 8th ACM Conference on Recommender systems, http://dx.doi.org/10.1145/2645710.2645746 ; Recommender systems research is often based on comparisons of predictive accuracy: the better the evaluation scores, the better the recommender. However, it is difficult to compare results from different recommender systems due to the many options in design and implementation of an evaluation strategy. Additionally, algorithmic implementations can diverge from the standard formulation due to manual tuning and modifications that work better in some situations. In this work we compare common recommendation algorithms as implemented in three popular recommendation frameworks. To provide a fair comparison, we have complete control of the evaluation dimensions being benchmarked: dataset, data splitting, evaluation strategies, and metrics. We also include results using the internal evaluation mechanisms of these frameworks. Our analysis points to large differences in recommendation accuracy across frameworks and strategies, i.e. the same baselines may perform orders of magnitude better or worse across frameworks. Our results show the necessity of clear guidelines when reporting evaluation of recommender systems to ensure reproducibility and comparison of results. ; This work was partly carried out during the tenure of an ERCIM "Alain Bensoussan" Fellowship Programme. The research leading to these results has received funding from the European Union Seventh Framework Programme (FP7/2007-2013) under grant agreements n◦246016 and n◦610594, and the Spanish Ministry of Science and Innovation (TIN2013-47090-C3-2)

There is an increasing consensus in the Recommender Systems community that the dominant error-based evaluation metrics are insufficient, and mostly inadequate, to properly assess the practical effectiveness of recommendations. Seeking to evaluate recommendation rankings—which largely determine the effective accuracy in matching user needs—rather than predicted rating values, Information Retrieval metrics have started to be applied for the evaluation of recommender systems. In this paper we analyse the main issues and potential divergences in the application of Information Retrieval methodologies to recommender system evaluation, and provide a systematic characterisation of experimental design alternatives for this adaptation. We lay out an experimental configuration framework upon which we identify and analyse specific statistical biases arising in the adaptation of Information Retrieval metrics to recommendation tasks, namely sparsity and popularity biases. These biases considerably distort the empirical measurements, hindering the interpretation and comparison of results across experiments. We develop a formal characterisation and analysis of the biases upon which we analyse their causes and main factors, as well as their impact on evaluation metrics under different experimental configurations, illustrating the theoretical findings with empirical evidence. We propose two experimental design approaches that effectively neutralise such biases to a large extent. We report experiments validating our proposed experimental variants, and comparing them to alternative approaches and metrics that have been defined in the literature with similar or related purposes ; This work was partially supported by the national Spanish Government (grants nr. TIN2013-47090-C3-2 and TIN2016-80630-P). We wish to express our gratitude to the anonymous reviewers whose insightful and generous feedback guided us in producing an enhanced version of the paper beyond the amendmentof flaws and shortcomings

This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in RecSys '13 Proceedings of the 7th ACM conference on Recommender systems, http://dx.doi.org/10.1145/2507157.2507191. ; Relevance-Based Language Models are an effective IR approach which explicitly introduces the concept of relevance in the statistical Language Modelling framework of Information Retrieval. These models have shown to achieve state-of-the-art retrieval performance in the pseudo relevance feedback task. In this paper we propose a novel adaptation of this language modeling approach to rating-based Collaborative Filtering. In a memory-based approach, we apply the model to the formation of user neighbourhoods, and the generation of recommendations based on such neighbourhoods. We report experimental results where our method outperforms other standard memory-based algorithms in terms of ranking precision. ; This work was funded by Secretaría de Estado de Investigación, Desarrollo e Innovación from the Spanish Government under projects TIN2012-33867 and TIN2011-28538-C02.

The final publication is available at Springer via http://dx.doi.org/10.1007/s10791-012-9214-z ; When speaking of information retrieval, we often mean text retrieval. But there exist many other forms of information retrieval applications. A typical example is collaborative filtering that suggests interesting items to a user by taking into account other users' preferences or tastes. Due to the uniqueness of the problem, it has been modeled and studied differently in the past, mainly drawing from the preference prediction and machine learning view point. A few attempts have yet been made to bring back collaborative filtering to information (text) retrieval modeling and subsequently new interesting collaborative filtering techniques have been thus derived. In this paper, we show that from the algorithmic view point, there is an even closer relationship between collaborative filtering and text retrieval. Specifically, major collaborative filtering algorithms, such as the memory-based, essentially calculate the dot product between the user vector (as the query vector in text retrieval) and the item rating vector (as the document vector in text retrieval). Thus, if we properly structure user preference data and employ the target user's ratings as query input, major text retrieval algorithms and systems can be directly used without any modification. In this regard, we propose a unified formulation under a common notational framework for memory-based collaborative filtering, and a technique to use any text retrieval weighting function with collaborative filtering preference data. Besides confirming the rationale of the framework, our preliminary experimental results have also demonstrated the effectiveness of the approach in using text retrieval models and systems to perform item ranking tasks in collaborative filtering. ; This work is supported by the Spanish Government (TIN2011-28538- C02-01) and the Regional Government of Madrid (S2009TIC-1542). We also thank the anonymous reviewers for their valuable comments.

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-642-20161-5_30 ; Proceedings of 33rd European Conference on IR Research, ECIR 2011, Dublin, Ireland, April 18-21, 2011. ; Collaborative Filtering (CF) aims at predicting unknown ratings of a user from other similar users. The uniqueness of the problem has made its formulation distinctive to other information retrieval problems. While the formulation has proved to be effective in rating prediction tasks, it has limited the potential connections between these algorithms and Information Retrieval (IR) models. In this paper we propose a common notational framework for IR and rating-based CF, as well as a technique to provide CF data with a particular structure, in order to be able to use any IR weighting function with it. We argue that the flexibility of our approach may yield to much better performing algorithms. In fact, in this work we have found that IR models perform well in item ranking tasks, along with different normalization strategies. ; This work was supported by the Spanish Ministry of Science and Innovation (TIN2008-06566-C04-02), and the Regional Government of Madrid (S2009TIC-1542)

Also published online by CEUR Workshop Proceedings (CEUR-WS.org, ISSN 1613-0073) ; Late-Breaking Results, Project Papers and Workshop Proceedings of the 21st Conference on User Modeling, Adaptation, and Personalization, UMAP 2013 ; We present a preliminary study on the relations between personality types and user preferences in multiple entertainment domains, namely movies, TV shows, music, and books. We analyze a total of 53,226 Facebook user profiles composed of both personality scores (openness, conscientiousness, extraversion, agreeableness, neuroticism) from the Five Factor model, and explicit interests about 16 genres in each of the above domains. As a result of our analysis, we extract personality-based user stereotypes and association rules for some of the considered domain genres, and infer similarities of personality types related to genres in different domains. ; This work was supported by the Spanish Government (TIN2011-28538-C02) and the Regional Government of Madrid (S2009TIC-1542). The authors sincerely thank the members of myPersonality project for their kind attention and help on downloading and processing the provided data.

Also published online by CEUR Workshop Proceedings (CEUR-WS.org, ISSN 1613-0073) ; Proceedings of the Workshop on Semantic Adaptive Social Web 2011 ; In this paper, we present an algorithmic framework to identify the semantic meanings and contexts of social tags within a particular folksonomy, and exploit them for building contextualised tag-based user and item profiles. We also present its implementation in a system called cTag, with which we preliminary analyse semantic meanings and contexts of tags belonging to Delicious and MovieLens folksonomies. ; This work was supported by the Spanish Ministry of Science and Innovation (TIN2008-06566-C04-02), and the Regional Government of Madrid (S2009TIC- 1542).

This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in CAMRa '11 Proceedings of the 2nd Challenge on Context-Aware Movie Recommendation, http://dx.doi.org/10.1145/2096112.2096118. ; In this paper, we describe the experiments conducted by the Information Retrieval Group at the Universidad Autónoma de Madrid (Spain) to tackle the Identifying Ratings (track 2) task of the CAMRa 2011 Challenge. The experiments performed include time-frequency probabilistic strategies, heuristic collaborative filtering (CF) and a model-based CF approach. Results show that probabilistic classifiers based on temporal behavior of users have better performance than traditional recommendation-based strategies, thus reflecting that temporal information is a valuable source for the identification or discrimination of user ratings. ; This work is supported by the Spanish Government (TIN 2008-06566-C04-02) and by the Comunidad de Madrid and Universidad Aut´onoma de Madrid (CCG10-UAM/TIC-5877). The authors acknowledge support from CCC at UAM.

This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in CIKM '12 Proceedings of the 21st ACM international conference on Information and knowledge management, http://dx.doi.org/10.1145/2396761.2398628. ; Popular online rental services such as Netflix and MoviePilot often manage household accounts. A household account is usually shared by various users who live in the same house, but in general does not provide a mechanism by which current active users are identified, and thus leads to considerable difficulties for making effective personalized recommendations. The identification of the active household members, defined as the discrimination of the users from a given household who are interacting with a system (e.g. an on-demand video service), is thus an interesting challenge for the recommender systems research community. In this paper, we formulate the above task as a classification problem, and address it by means of global and local feature selection methods and classifiers that only exploit time features from past item consumption records. The results obtained from a series of experiments on a real dataset show that some of the proposed methods are able to select relevant time features, which allow simple classifiers to accurately identify active members of household accounts. ; This work was supported by the Spanish Government (TIN2011-28538-C02). The authors thank Centro de Computación Científica at UAM for its technical support.

This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in ACM Transactions on Intelligent Systems and Technology, http://dx.doi.org/10.1145/2751565 ; Rating datasets are of paramount importance in recommender systems research. They serve as input for recommendation algorithms, as simulation data, or for evaluation purposes. In the past, public accessible rating datasets were not abundantly available, leaving researchers no choice but to work with old and static datasets like MovieLens and Netflix. More recently, however, emerging trends as social media and smart-phones are found to provide rich data sources which can be turned into valuable research datasets. While dataset availability is growing, a structured way for introducing and comparing new datasets is currently still lacking. In this work, we propose a five-step framework to introduce and benchmark new datasets in the recommender systems domain. We illustrate our framework on a new movie rating dataset-called Movie Tweetings-collected from Twitter. Following our framework, we detail the origin of the dataset, provide basic descriptive statistics, investigate external validity, report the results of a number of reproducible benchmarks, and conclude by discussing some interesting advantages and appropriate research use cases. ; This work is funded by a PhD grant to Simon Dooms of the Agency for Innovation by Science and Technology (IWT Vlaanderen) and the Spanish Ministry of Science and Innovation (TIN2013-47090-C3-2). Part of this work was carried out during the tenure of an ERCIM "Alain Bensoussan" Fellowship Programme, funded by European Comission FP7 grant agreement no. 246016. The experiments in this work were carried out using the Stevin Supercomputer Infrastructure at Ghent University, funded by Ghent University, the Hercules Foundation, and the Flemish Government - department EWI.

This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in CAMRa '10 Proceedings of the Workshop on Context-Aware Movie Recommendation, http://dx.doi.org/10.1145/1869652.1869660 ; In this paper, we describe the experiments conducted by the Information Retrieval Group at the Universidad Autónoma de Madrid (Spain) in order to better recommend movies for the 2010 CAMRa Challenge edition. Experiments were carried out on the dataset corresponding to social Filmtipset track. To obtain the movies recommendations we have used different algorithms based on Random Walks, which are well documented in the literature of collaborative recommendation. We have also included a new proposal in one of the algorithms in order to get better results. The results obtained have been computed by means of the trec_eval standard NIST evaluation procedure. ; This research was supported by the Spanish Ministry of Science and Innovation (TIN2008-06566-C04-02) and the Scientific Computing Institute at UAM. The third author also wants to acknowledge support from the Chilean Government through the Becas-Chile scholarship program

This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in CAMRa '10 Proceedings of the Workshop on Context-Aware Movie Recommendation, http://dx.doi.org/10.1145/1869652.1869655. ; In this paper, we describe the experiments conducted by the Information Retrieval Group at the Universidad Autónoma de Madrid (Spain) in order to better recommend movies for the 2010 CAMRa Challenge edition. Experiments were carried out on the dataset corresponding to weekly Filmtipset track. We consider simple strategies for taking into account the temporal context for movie recommendations, mainly based on variations of the KNN algorithm, which has been deeply studied in the literature, and one ad-hoc strategy, taking advantage of particular information in the weekly Filmtipset track. Results show that the usage of information near to the recommendation date alone can help improving recommendation results, with the additional benefit of reducing the information overload of the recommender engine. Furthermore, the use of social interaction information shows also a contribution in order to better predict a part of users' tastes. ; This research was supported by the Spanish Ministry of Science and Innovation (TIN2008-06566-C04-02) and the Scientific Computing Institute at UAM. The first author acknowledges support from the Chilean Government through the Becas-Chile scholarship program