Incentivizing High-Quality Content in Online Recommender Systems
- Xinyan Hu, UC Berkeley
- Time: 2024-07-05 14:00
- Host: Turing Class Research Committee
- Venue: Room 204, Courtyard No.5, Jingyuan
Abstract
In content recommender systems such as TikTok and YouTube, the platform's recommendation algorithm shapes content producer incentives. Many platforms employ online learning, which generates intertemporal incentives, since content produced today affects recommendations of future content. We study the game between producers and analyze the content created at equilibrium. We show that standard online learning algorithms, such as Hedge and EXP3, unfortunately incentivize producers to create low-quality content, where producers' effort approaches zero in the long run for typical learning rate schedules. Motivated by this negative result, we design learning algorithms that incentivize producers to invest high effort and achieve high user welfare. At a conceptual level, our work illustrates the unintended impact that a platform's learning algorithm can have on content quality and introduces algorithmic approaches to mitigating these effects.
Biography
Xinyan Hu is a 2nd year PhD student in CS at UC Berkeley, where she is advised by Prof. Michael I. Jordan and a member of the Berkeley AI Research (BAIR) Lab. Previously, she received her B.S. in CS at Peking University, where she was advised by Prof. Xiaotie Deng and she also worked with Prof. Zhiwei Steven Wu (CMU) and Dr. Aleksandrs Slivkins (MSR). She has broad interests in the intersection of machine learning and economics, especially in online learning and game theory. Recently, she is also interested in LLM interpretability and alignment.