Incentivizing High-Quality Content in Online Recommender Systems
This addresses a critical issue for online platforms like TikTok and YouTube, where recommendation algorithms affect content quality, offering a novel solution to mitigate negative incentives.
The paper tackles the problem of online learning algorithms in recommender systems incentivizing low-quality content from producers, showing that standard algorithms like Hedge and EXP3 lead to zero effort in the long run, and proposes new algorithms that encourage high effort and improve user welfare.
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.