Beyond Self-Interest: How Group Strategies Reshape Content Creation in Recommendation Platforms?

We employ a game-theoretic framework to study the impact of a specific strategic behavior among creators---group behavior---on recommendation platforms. In this setting, creators within a group collaborate to maximize their collective utility.We show that group behavior has a limited effect on the game's equilibrium when the group size is small. However, when the group size is large, group behavior can significantly alter content distribution and user welfare.Specifically, in a top-$K$ recommendation system with exposure-based rewards, we demonstrate that user welfare can suffer a significant loss due to group strategies, and user welfare does not necessarily increase with larger values of $K$ or more random matching, contrasting sharply with the individual creator case. Furthermore, we investigate user welfare guarantees through the lens of the Price of Anarchy (PoA). In the general case, we establish a negative result on the bound of PoA with exposure rewards, proving that it can be arbitrarily large. We then investigate a user engagement rewarding mechanism, which mitigates the issues caused by large group behavior, showing that $\text{PoA}\leq K+1$ in the general case and $\text{PoA}\leq 2$ in the binary case. Empirical results from simulations further support the effectiveness of the user engagement rewarding mechanism.

Online content platforms like Instagram, YouTube, and TikTok use recommendation systems to match users with content. While much research has focused on individual creators' strategies, many creators now work in groups to maximize collective benefits. This shift can significantly change how content is distributed, but its impact on user satisfaction and fairness is not well understood. We use a game-theoretic framework to study the effects of group behavior on recommendation systems. Our findings show that small groups have limited impact, but large groups can significantly alter content distribution, often reducing user satisfaction. We also investigate how platform parameters in a top-$K$ recommendation system influence these outcomes. We demonstrate that a rewarding mechanism based on user engagement can mitigate the negative effects of group behavior. Our work provides insights for online platforms on how to adjust recommendation systems to reduce user welfare loss caused by strategic group actions.