From Modeling and Profiling to Auditing: the Evolving Role of the User in Recommender System Research

The tutorial offers the UMAP community a structured journey from traditional user modeling to algorithmic auditing of recommender systems, examining how the field’s conceptual foundations have evolved and where its boundaries remain contested. We begin with a retrospective on the established fields of user profiling and modeling, covering both their historical origins and the technical milestones that have shaped how user preferences are captured and exploited by personalized systems. We then analyze the evolving conceptual framework and terminology of the field to resolve ambiguities regarding the interpretation of key notions. As the core of the tutorial, we examine the recent shift from passive profiling toward participatory auditing frameworks, where users actively engage in surfacing biases and systemic harms in recommender systems. Specifically, we discuss advancements in the following areas: the move toward pseudo-explicit profiling, the emergence of universal user representations, and the growing body of user-led auditing methodologies. Throughout, attendees are invited to contribute through discussion and Q&A, making the session as much a collective inquiry as a presentation.