Music search, retrieval, and recommendation systems have experienced a boom during the past few years due to streaming services providing access to huge catalogs anywhere and anytime. These streaming services collect the user behavior in terms of actions on music items, such as play, skip, playlist creation, and modification. As a result, an abundance of user and usage data has been collected and is available to companies and academics, allowing for user profiling and to create personalized music search and recommendation systems. The importance and timeliness of research on such personalized music systems is evidenced by publications in venues including the ACM Conference on Recommender Systems, ACM Conference on User Modeling, Adaptation and Personalization, International Society for Music Information Retrieval Conference, the ACM Special Interest Group on Information Retrieval Conference, ACM CHI Conference on Human Factors in Computing Systems, and the ACM International Conference on Intelligent User Interfaces, as well as in journals including IEEE Transactions on Affective Computing and ACM Transactions on Intelligent Systems and Technology, in addition to UMUAI. On the other hand, there are still plenty of unsolved challenges. In particular, scholars have identified as some of the most vital ones: understanding and modeling users, personalization of recommendation and retrieval systems, user adaptivity in interfaces, and context awareness.
Papers in the Special Issue
This special issue contains articles that contribute to the state of the art on (a) personalized user interfaces for music (Jin et al. 2019; Narducci et al. 2019) and (b) playlist creation (Kamehkhosh et al. 2019).
The paper Effects of personal characteristics in control-oriented user interfaces for music recommender systems (Jin et al. 2019) deals with the personalization of control elements in user interfaces for music recommender systems. The authors explore personal characteristics and the user interface characteristics (controls, visualizations, and complexity) to identify the interplay of these variables on the perception of recommendations. In summary, they found that the user characteristic musical sophistication influences the acceptance of the recommendations.
The paper An investigation on the user interaction modes of conversational recommender systems for the music domain (Narducci et al. 2019) addresses the issue of how to design conversational recommender systems for music. The authors evaluated several approaches to the design of a conversational user interface and concluded, based on a user study, that the highest user acceptance of such an interface is when a mixed approach is used, i.e., allowing the user to interact both with natural language and buttons.
The paper Effects of recommendations on the playlist creation behavior of users (Kamehkhosh et al. 2019) investigates if and how recommendations influence the manual playlist creation process. The results of the authors’ user study indicate that the users indeed do use recommendations for playlist creation. However, they also identified a delicate balance, i.e., if the recommendations were too diverse, users tended not to use the recommended items in their playlists.
The papers in this special issue address specific challenges related to the user interaction and the influence of the recommendations on user behavior. While the included articles substantially contribute to the state of the art, they open even more research avenues.
A common theme in the special issue is that in music personalization, there are a lot of factors that influence the user experience. Hence, it is of utter importance to design the experiments in such a way that only the observed variables are isolated.
A related issue is also the lack of datasets, so the researchers needed to carry out expensive user studies. Although datasets are not always alternatives to user studies, especially if the research questions deal with unexplored features, it would be beneficial to have at disposal feature-rich datasets that would allow comparisons between similar studies.
Both the papers Narducci et al. (2019) and Kamehkhosh et al. (2019) show the importance of the user intent, which has been neglected in the past for the more accessible variables of context. Other user-centric variables, such as affect and personality, have also been identified in related work as important and will likely be up-and-coming topics in future research.
Jin, Y., Tintarev, N., Htun, N.N., Verbert, K.: Effects of personal characteristics in control-oriented user interfaces for music recommender systems. User Model. User-Adapt. Interact. (2019). https://doi.org/10.1007/s11257-019-09247-2
Kamehkhosh, I., Bonnin, G., Jannach, D.: Effects of recommendations on the playlist creation behavior of users. User Model. User-Adapt. Interact. (2019). https://doi.org/10.1007/s11257-019-09237-4
Narducci, F., Basile, P., de Gemmis, M., Lops, P., Semeraro, G.: An investigation on the user interaction modes of conversational recommender systems for the music domain. User Model. User-Adapt. Interact. (2019). https://doi.org/10.1007/s11257-019-09250-7
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
About this article
Cite this article
Tkalčič, M., Schedl, M. & Knees, P. Preface to the Special Issue on user modeling for personalized interaction with music. User Model User-Adap Inter 30, 195–198 (2020). https://doi.org/10.1007/s11257-020-09264-6