Ziegler, J., & Loepp, B. (2023).
In Augstein, M., Herder, E., & Wörndl, W. (Eds.), Personalized Human-Computer Interaction (pp. 33–58). Berlin, Germany: De Gruyter Oldenbourg.
Abstract:
Recommender systems aim at facilitating users’ search and decision-making when they are faced with a large number of available options, such as buying products online or selecting music tracks to listen to. A broad range of machine learning models and algorithms has been developed that aim at predicting users’ assessment of unseen items and at recommending items that best match their interests. However, it has been shown that optimizing the system in terms of algorithm accuracy often does not result in a correspondingly high level of user satisfaction. Therefore, a more user-centric approach to developing recommender systems is needed that better takes into account users’ actual goals, the current context and their cognitive demands. In this chapter, we discuss a number of techniques and design aspects that can contribute to increasing transparency, user understanding and interactive control of recommender systems. Furthermore, we present methods for evaluating systems from a user perspective and point out future research directions.
Resources: