Towards User Profile-based Interfaces for Exploration of Large Collections of Items Claudia Becerra Universidad Nacional de Colombia Bogotá - Colombia www.unal.edu.co cjbecerrac@unal.edu.co Sergio Jimenez Universidad Nacional de Colombia Bogotá - Colombia www.unal.edu.co sgjimenezv@unal.edu.co Alexander Gelbukh Instituto Politécnico Nacional, Centro de Investigación en Computación, Mexico, D.F http://nlp.cic.ipn.mx/ gelbukh@cic.ipn.mx ABSTRACT Collaborative tagging systems allow users to describe and organize items using labels in a free-shared vocabulary (tags), improving their browsing experience in large collections of items. At present, the most accurate collaborative filtering techniques build user profiles in latent factor spaces that are not interpretable by users. In this paper, we propose a general method to build linear-interpretable user profiles that can be used for user interaction in a recommender system, using the well-known simple additive weighting model (SAW) for multi-attribute decision making. In experiments, two kinds of user profiles where tested: one from free contributed tags and other from keywords automatically extracted from textual item descriptions. We compare them for their ability to predict ratings and their potential for user interaction. As a test bed, we used a subset of the database of the University of Minnesota’s movie review system— Movielens, the social tags proposed by Vig et al. (2012) in their work “The Tag Genome”, and movie synopses extracted from the Netflix’s API. We found that, in “warm” scenarios, the proposed tag and keyword-based user profiles produce equal or better recommendations that those based on latent-factors obtained using matrix factorization. Particularly, the keyword-based approach obtained 5.63% of improvement. In cold-start conditions—movies without rating information, both approaches perform close to average. Moreover, a user profile visualization is proposed arising an accuracy vs. interpretability tradeoff between tag and keyword- based profiles. While keyword-based profiles produce more accurate recommendations, tag-based profiles seems to be more readable, meaningful and convenient for creating profile-based user interfaces. Categories and Subject Descriptors H.3.3 [Information Storage and Retrieval| Information Search and Retrieval]: Selection process; H.5.3 [Information Interfaces and Presentation]: Group and Organization Interfaces– Collaborative computing; H.5.2 [Information Interfaces and Presentation]: User Interfaces General Terms Algorithms, Experimentation. Keywords Recommender systems, collaborative filtering, collaborative tagging systems, social tagging, user interfaces 1. INTRODUCTION An approach for improving the exploration of large collections of items such as books (librarything.com), films (netflix.com), pictures (flickr.com), research papers (citeulike.com) and web bookmarks (del.icio.us) is the leveraging of collaborative information from the users. This approach allows the knowledge of certain individuals on certain items in the collection propagates towards other users. In this way, a self-generated collaborative intelligence guides users in their exploration by recommendations tailored to their preferences and away from dislikes. Currently, collaborative filtering approaches derive user profiles and produce recommendations based primarily on user feedback whether explicit (e.g. ratings, “likes”, tagging, reviews) or implicit (e.g. web logs). As the time goes by, user profiles grow while their preferences evolve. Generally, users are allowed to update their explicitly given information with the aim of adjusting their profiles to get better recommendations. In this scenario, when a user wants to update his (her) profile, it depends—for instance— on a large number of ratings making of this a difficult and even overwhelming task. The users should make a significant number of targeted edits in their profiles to obtain the desired effect. The situation worsens in systems based on implicit feedback where user profiles are not interpretable nor accessible by users. Most of the state-of-the-art methods for collaborative filtering build user profiles projected in latent factor spaces. These latent factors reduce considerably the dimensionality of the user profiles providing more accurate recommendations at the expense of interpretability. Unfortunately, users cannot make modifications on these low-dimensional and highly informative profiles. A first step to tackle this issue could be the design of interfaces based on interpretable user profiles. For instance Lops et al. [16] proposed a system where the user profiles are defined in a space indexed by keywords automatically extracted from textual item descriptions —keyword-based user profiles. However, in many cases the number of extracted keywords is similar or even larger than the number of items in the collection making it difficult the interaction of users with their profiles. Alternatively, user profiles can also be built using tags [2]—tag- based user profiles. These tags come from collaboratively tagging systems [29], which allows users in large collections to label items using a shared free vocabulary. As a result of this social indexing process [10], the system gradually collects a social index, which enables users to classify, visualize and query items in a way that is both personalized and social. Unfortunately, social indexes suffer of misspellings, typographical errors and extremely particular tags, making of them a noisy resource for the Decisions@Recsys’13. October 12--16, 2013, Hong Kong, China. Paper presented at the 2013 Decisions@RecSys workshop in conjunction with the 7th ACM conference on Recommender Systems. Copyright 2013 for the individual papers by the papers' authors. Copying permitted for private and academic purposes. This volume is published and copyrighted by its editors.