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

24 July 2021

The latest content available from Springer
  • Preface to the special issue on fair, accountable, and transparent recommender systems
  • Personality-based approach for tailoring persuasive mental health applications


    Persuasive mental health applications (apps) are effective tools for promoting behavior change. Tailoring persuasive interventions can boost their effectiveness. Research has shown that there is a relationship between individuals’ personality traits and their susceptibility to various features of a persuasive app. The aim of this paper was twofold. First, we explore the relationships between personality and features of a persuasive app for promoting mental and emotional well-being. Second, we explore possible domain-dependent variability on the relation between personality and persuasive features across various domains (e.g., habit formation, fitness, risky behaviors change, transportation habits). Specifically, to advance research in the area of personality and computing app design, first, we reviewed 103 mental health apps from the app stores and uncovered the various persuasive features employed in their design. Second, we conducted focus-group studies of 32 participants to uncover more insights about the mental health app features. Finally, we implemented the common features that emerged from these two studies in persuasive mental health app prototypes and conducted a large-scale study of 561 users to evaluate their persuasiveness depending on people’s personalities. The results of the large-scale study show that people’s personality traits play a significant role in the perceived persuasiveness of different features—the app features that appeal to various individuals. Conscientious people tend to be motivated by apps that offer relaxation audios, encouragement, suggestions and trusted information, contact for help; Neurotic people are more inclined to apps that provide some relaxation exercises and audios, social support, and apps with a clear privacy policy; People who are more open to experience tend to be motivated by self-monitoring, relaxation exercises and audios, and social support. Finally, we provide a comparative analysis of the relationship between personality traits and persuasive features across various domains to show domain dependency of persuasive feature effectiveness and offer design guidelines for tailoring persuasive and behavior change apps based on an individual’s personality.

  • Personalized rehabilitation for children with cerebral palsy


    Over the years, there has been an ongoing increase in the use of virtual gaming (VG) implemented via a range of technologies for the rehabilitation of children with disabilities including cerebral palsy (CP). While many VG-based devices have been developed over the past decade, many have been tested primarily for post-stroke therapy and included limited adaptation capabilities, not to mention personalization. When adaptation was included, it was not implemented dynamically in real-time but rather used to adjust the game parameters before a session. The goal and novel contribution of this study was to examine the potential of dynamic, within-session adaptation of virtual game parameters to support the rehabilitation of children with CP. The iVG4Rehab (Intelligent therapeutic Virtual Gaming System for Rehabilitation) system was designed and developed in collaboration with a team of clinicians. We aimed to demonstrate and evaluate the potential of a personalized virtual gaming system to support and enhance treatment of children with CP by real-time adaptations of game parameters to the children’s abilities and therapeutic needs. Our results validated the hypothesis that personalized system as a tool that has great potential for upper extremity (UE) therapy for children with CP and contributes to a more comprehensive understanding of their underlying performance, usability and kinematics in this unique context.

  • Personalized task difficulty adaptation based on reinforcement learning


    Traditionally, the task difficulty level is often determined by domain experts based on some hand-crafted rules. However, with the adoption of Massive Open Online Courses (MOOCs), it has become harder to manually personalize task difficulty as the system designers are faced with a very large question bank and a user base of individuals with diverse backgrounds and ability levels. This research focuses on developing a data-driven method to adaptively adjust difficulty levels in order to maintain a target user performance level over a series of tasks whose difficulty level is highly variable among different individuals. Specifically, the issue of difficulty adaptation was formulated as a reinforcement learning problem. To ensure responsiveness of the interactive systems, a novel bootstrapped policy gradient (BPG) framework was developed, which can incorporate prior knowledge of difficulty ranking into policy gradient to enhance sample efficiency. To obtain high-quality prior information on difficulty ranking, a clustering-based approach was proposed which can learn a personalized difficulty ranking to capture users’ individual differences. To evaluate the effectiveness of the difficulty adaptation method, we focused on a visual memory training problem with a large question bank and a diverse user base. Specifically, the proposed algorithms were combined and applied to a real-world application consisting of an online visual-spatial memory recall game and were shown to outperform the traditional rule-based adaptation approach in adapting to the slow players while achieving comparable performance in adapting to the fast players.

  • The role of transparency in multi-stakeholder educational recommendations


    Recommender systems have been successfully applied to alleviate the problem of information overload and assist users’ decision makings. Multi-stakeholder recommender systems produce the item recommendations to the end user by considering the perspective of multiple stakeholders. Existing research on multi-stakeholder recommendations relies on the offline evaluations only, and the online studies are still under investigation. This paper made the first attempt to examine the multi-stakeholder recommendations through online studies. On the one hand, we use online user studies to compare different recommendation models. On the other hand, we develop novel user interfaces to enhance the transparency and exploit the role of transparency in multi-stakeholder recommender systems. We collect our own dataset in educational learning and use it as case study to perform the online studies in multi-stakeholder recommendations. We observe that the explanation of the key parameters in the recommendation models can enhance the transparency, which further affects the decision making of different stakeholders.