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

20 October 2020

The latest content available from Springer
  • Empirical analysis of session-based recommendation algorithms

    Abstract

    Recommender systems are tools that support online users by pointing them to potential items of interest in situations of information overload. In recent years, the class of session-based recommendation algorithms received more attention in the research literature. These algorithms base their recommendations solely on the observed interactions with the user in an ongoing session and do not require the existence of long-term preference profiles. Most recently, a number of deep learning-based (“neural”) approaches to session-based recommendations have been proposed. However, previous research indicates that today’s complex neural recommendation methods are not always better than comparably simple algorithms in terms of prediction accuracy. With this work, our goal is to shed light on the state of the art in the area of session-based recommendation and on the progress that is made with neural approaches. For this purpose, we compare twelve algorithmic approaches, among them six recent neural methods, under identical conditions on various datasets. We find that the progress in terms of prediction accuracy that is achieved with neural methods is still limited. In most cases, our experiments show that simple heuristic methods based on nearest-neighbors schemes are preferable over conceptually and computationally more complex methods. Observations from a user study furthermore indicate that recommendations based on heuristic methods were also well accepted by the study participants. To support future progress and reproducibility in this area, we publicly share the session-rec evaluation framework that was used in our research.

  • Meta-User2Vec model for addressing the user and item cold-start problem in recommender systems

    Abstract

    The cold-start scenario is a critical problem for recommendation systems, especially in dynamically changing domains such as online news services. In this research, we aim at addressing the cold-start situation by adapting an unsupervised neural User2Vec method to represent new users and articles in a multidimensional space. Toward this goal, we propose an extension of the Doc2Vec model that is capable of representing users with unknown history by building embeddings of their metadata labels along with item representations. We evaluate our proposed approach with respect to different parameter configurations on three real-world recommendation datasets with different characteristics. Our results show that this approach may be applied as an efficient alternative to the factorization machine-based method when the user and item metadata are used and hence can be applied in the cold-start scenario for both new users and new items. Additionally, as our solution represents the user and item labels in the same vector space, we can analyze the spatial relations among these labels to reveal latent interest features of the audience groups as well as possible data biases and disparities.

  • A serious game to extract Hofstede’s cultural dimensions at the individual level

    Abstract

    Cultural dimensions are an important aspect of a user model and useful for many applications such as adapting user interface, managing marketing campaigns, customer relationship management, and human resource management. Traditionally, these dimensions are measured through CVSCALE, which is a reliable and standard scale provided to measure Hofstede’s cultural dimensions at the individual level. The problems with the questionnaire-based data collection are low response rates, lack of willingness to complete, poor engagement of participants, and concern about the quality of data collected. To solve these problems, we present a serious video game called “Treasure Island” to measure the cultural dimensions of the player at the individual level (currently only for the Persian language). We have developed and validated a Persian-language version of CVSCALE applied to design the game. We developed the very first general game development process to build serious games for gathering the same data as a standard psychometric questionnaire. Treasure Island has been evaluated by statistical analysis of the data collected from a sample of 285 participants that have played the game and completed the questionnaire. The results indicate that Treasure Island is effective to measure the individual cultural dimensions. Moreover, the efficiency of the game has been tested in terms of task load imposed on the user during playing the game and completing the questionnaire. The results demonstrate that the game imposes less task load on the user, consequently, improves user satisfaction and engagement. Since individual cultural dimensions can be considered an important facet of a user model for certain applications, the proposed serious game can be applied for user modeling and personalization purposes.

  • The effects of controllability and explainability in a social recommender system

    Abstract

    In recent years, researchers in the field of recommender systems have explored a range of advanced interfaces to improve user interactions with recommender systems. Some of the major research ideas explored in this new area include the explainability and controllability of recommendations. Controllability enables end users to participate in the recommendation process by providing various kinds of input. Explainability focuses on making the recommendation process and the reasons behind specific recommendation more clear to the users. While each of these approaches contributes to making traditional “black-box” recommendation more attractive and acceptable to end users, little is known about how these approaches work together. In this paper, we investigate the effects of adding user control and visual explanations in a specific context of an interactive hybrid social recommender system. We present Relevance Tuner+, a hybrid recommender system that allows the users to control the fusion of multiple recommender sources while also offering explanations of both the fusion process and each of the source recommendations. We also report the results of a controlled study (N = 50) that explores the impact of controllability and explainability in this context.

  • Using scaffolding to formalize digital coach support for low-literate learners

    Abstract

    In this study, we attempt to specify the cognitive support behavior of a previously designed embodied conversational agent coach that provides learning support to low-literates. Three knowledge gaps are identified in the existing work: an incomplete specification of the behaviors that make up ‘support,’ an incomplete specification of how this support can be personalized, and unclear speech recognition rules. We use the socio-cognitive engineering method to update our foundation of knowledge with new online banking exercises, low-level scaffolding and user modeling theory, and speech recognition. We then refine the design of our coach agent by creating comprehensive cognitive support rules that adapt support based on learner needs (the ‘Generalized’ approach) and attune the coach’s support delay to user performance in previous exercises (the ‘Individualized’ approach). A prototype is evaluated in a 3-week within- and between-subjects experiment. Results show that the specified cognitive support is effective: Learners complete all exercises, interact meaningfully with the coach, and improve their online banking self-efficacy. Counter to hypotheses, the Individualized approach does not improve on the Generalized approach. Whether this indicates suboptimal operationalization or a deeper problem with the Individualized approach remains as future work.