facebook

linkedin

User Modeling and User-Adapted Interaction (UMUAI) provides an interdisciplinary forum for the dissemination of new research results on interactive computer systems that can be adapted or adapt themselves to their current users, and on the role of user models in the adaptation process.

UMUAI has been published since 1991 by Kluwer Academic Publishers (now merged with Springer Verlag).

UMUAI homepage with description of the scope of the journal and instructions for authors.

Springer UMUAI page with online access to the papers.

Latest Results for User Modeling and User-Adapted Interaction

21 January 2019

The latest content available from Springer
  • Addressing the user cold start with cross-domain collaborative filtering: exploiting item metadata in matrix factorization

    Abstract

    Providing relevant personalized recommendations for new users is one of the major challenges in recommender systems. This problem, known as the user cold start has been approached from different perspectives. In particular, cross-domain recommendation methods exploit data from source domains to address the lack of user preferences in a target domain. Most of the cross-domain approaches proposed so far follow the paradigm of collaborative filtering, and avoid analyzing the contents of the items, which are usually highly heterogeneous in the cross-domain setting. Content-based filtering, however, has been successfully applied in domains where item content and metadata play a key role. Such domains are not limited to scenarios where items do have text contents (e.g., books, news articles, scientific papers, and web pages), and where text mining and information retrieval techniques are often used. Potential application domains include those where items have associated metadata, e.g., genres, directors and actors for movies, and music styles, composers and themes for songs. With the advent of the Semantic Web, and its reference implementation Linked Data, a plethora of structured, interlinked metadata is available on the Web. These metadata represent a potential source of information to be exploited by content-based and hybrid filtering approaches. Motivated by the use of Linked Data for recommendation purposes, in this paper we present and evaluate a number of matrix factorization models for cross-domain collaborative filtering that leverage metadata as a bridge between items liked by users in different domains. We show that in case the underlying knowledge graph connects items from different domains and then in situations that benefit from cross-domain information, our models can provide better recommendations to new users while keeping a good trade-off between recommendation accuracy and diversity.

  • Acknowledgment to reviewers
  • Validating gameplay activity inventory (GAIN) for modeling player profiles

    Abstract

    In the present study, we validated Gameplay Activity Inventory (GAIN), a short and psychometrically sound instrument for measuring players’ gameplay preferences and modeling player profiles. In Study 1, participants in Finland ( \(N=879\) ) responded to a 52-item version of GAIN. An exploratory factor analysis was used to identify five latent factors of gameplay activity appreciation: Aggression, Management, Exploration, Coordination, and Caretaking. In Study 2, respondents in Canada ( \(N=1322\) ) and Japan ( \(N=1178\) ) responded to GAIN, and the factor structure of a 15-item version was examined using a Confirmatory Factor Analysis. The results showed that the short version of GAIN has good construct validity, convergent validity, and discriminant validity in Japan and in Canada. We demonstrated the usefulness of GAIN by conducting a cluster analysis to identify player types that differ in both demographics and game choice. GAIN can be used in research as a tool for investigating player profiles. Game companies, publishers and analysts can utilize GAIN in player-centric game development and targeted marketing and in generating personalized game recommendations.

  • Evaluation of session-based recommendation algorithms

    Abstract

    Recommender systems help users find relevant items of interest, for example on e-commerce or media streaming sites. Most academic research is concerned with approaches that personalize the recommendations according to long-term user profiles. In many real-world applications, however, such long-term profiles often do not exist and recommendations therefore have to be made solely based on the observed behavior of a user during an ongoing session. Given the high practical relevance of the problem, an increased interest in this problem can be observed in recent years, leading to a number of proposals for session-based recommendation algorithms that typically aim to predict the user’s immediate next actions. In this work, we present the results of an in-depth performance comparison of a number of such algorithms, using a variety of datasets and evaluation measures. Our comparison includes the most recent approaches based on recurrent neural networks like gru4rec, factorized Markov model approaches such as fism or fossil, as well as simpler methods based, e.g., on nearest neighbor schemes. Our experiments reveal that algorithms of this latter class, despite their sometimes almost trivial nature, often perform equally well or significantly better than today’s more complex approaches based on deep neural networks. Our results therefore suggest that there is substantial room for improvement regarding the development of more sophisticated session-based recommendation algorithms.

  • Identifying factors that influence the acceptability of smart devices: implications for recommendations

    Abstract

    This paper presents results from a web-based study that investigates users’ attitudes toward smart devices, focusing on acceptability. Specifically, we conducted a survey that elicits users’ ratings of devices in isolation and devices in the context of tasks potentially performed by these devices. Our study led to insights about users’ attitudes towards devices in isolation and in the context of tasks, and about the influence of demographic factors and factors pertaining to technical expertise and experience with devices on users’ attitudes. The insights about users’ attitudes provided the basis for two recommendation approaches based on principal components analysis (PCA) that alleviate the new-user and new-item problems: (1) employing latent features identified by PCA to predict ratings given by existing users to new devices, and by new users to existing devices; and (2) identifying a relatively small set of key questions on the basis of PCs, whose answers account to a large extent for new users’ ratings of devices in isolation and in the context of tasks. Our results show that taking into account latent features of devices, and asking a relatively small number of key questions about devices in the context of tasks, lead to rating predictions that are significantly more accurate than global and demographic predictions, and substantially reduce prediction error, eventually matching the performance of strong baselines.