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

15 December 2018

The latest content available from Springer
  • 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.

  • A comparative analysis of recommender systems based on item aspect opinions extracted from user reviews

    Abstract

    In popular applications such as e-commerce sites and social media, users provide online reviews giving personal opinions about a wide array of items, such as products, services and people. These reviews are usually in the form of free text, and represent a rich source of information about the users’ preferences. Among the information elements that can be extracted from reviews, opinions about particular item aspects (i.e., characteristics, attributes or components) have been shown to be effective for user modeling and personalized recommendation. In this paper, we investigate the aspect-based top-N recommendation problem by separately addressing three tasks, namely identifying references to item aspects in user reviews, classifying the sentiment orientation of the opinions about such aspects in the reviews, and exploiting the extracted aspect opinion information to provide enhanced recommendations. Differently to previous work, we integrate and empirically evaluate several state-of-the-art and novel methods for each of the above tasks. We conduct extensive experiments on standard datasets and several domains, analyzing distinct recommendation quality metrics and characteristics of the datasets, domains and extracted aspects. As a result of our investigation, we not only derive conclusions about which combination of methods is most appropriate according to the above issues, but also provide a number of valuable resources for opinion mining and recommendation purposes, such as domain aspect vocabularies and domain-dependent, aspect-level lexicons.