User-centric Recommender Systems to help users achieve their goals

Recommender systems support users in finding content that fits with their (historical) preferences, which allows them to manage the information overload omnipresent in our digital society. However, as recommender systems aim to optimize prediction accuracy, they might still result in choice overload, as users are typically presented with long lists of highly attractive but similar options. We have studied one remedy to this, using a psychology-informed latent feature diversification. In several user studies we show that diversification, though somewhat reducing objective accuracy, reduces choice difficulty while improving perceived attractiveness and maintaining choice satisfaction, esp. for smaller lists of items. 

Diversification is also a means to help users explore around their current preferences. However, what if users have a goal to go beyond their current preferences and want to learn new genres or acquire new habits? Starting from users historical preferences, as recommender systems typically do, will be suboptimal in this case as it will still reinforce current behavior and will not allow users to attain such goals. As two alternative approaches, I will present our Rasch-based approach for energy saving and food recommendations to support behavioral change. I will also briefly discuss our work on music genre exploration, in which we help users explore new music genres in a personalized way.

Bild

Martijn Willemsen (www.martijnwillemsen.nl) is an Associate Professor on human decision making in interactive systems in the Human-Technology Interaction group at Eindhoven University of Technology (TU/e) and at the Jheronimus Academy of Data Science in Den Bosch (JADS), in The Netherlands. He researches the cognitive aspects of Human-Technology Interaction, with a strong focus on judgment and decision making in online environments. From a theoretical perspective, he has a special interest in process tracing technologies to capture and analyze information processing of decision makers. His applied research focuses on how (online) decisions can be supported by recommender systems, and includes domains such as movies, music, health-related decisions (food, lifestyle, exercise) and energy-saving measures. His recent focus is on interactive recommender systems that help users to move forward, developing new preferences and/or healthier behavior, rather than reinforcing their current behaviors. Such systems can provide personalized behavioral change. Martijn also focusses on interactive and explainable AI, with recent work studying health and sport coaches interacting with prediction models.