I analyze the long-term effects of current recommender system (RS) designs on the stakeholders involved (e.g., users, items, platforms, society) and identify interventions that can lead to better outcomes. Currently, I investigate emerging platforms and architectures that empower stakeholders to actively participate in the RSs' design and evaluation.
Recommender systems, moderation, search, sort, filter, and decision-support systems have largely been developed in parallel, despite aiming to solve similar computational problems over shared item universes. Together, these tools comprise visibility allocation systems that decide which (processed) data to present a human user with. I investigate (1) how to unify the language for these different tools through formal definitions of the computational problems they solve, (2) present common frameworks and methodologies for holistic impact evaluation, and (3) showcase examples of how to apply these frameworks in real-world applications.
I analyze how emergent technological systems can incentivize users to transition to new behaviors and what phenomena emerge. Currently, I am also investigating new system designs that promote better equilibria among agents.