Towards Long-Term User Welfare in Recommender Systems via Creator-Oriented Information Revelation

2025-10-12

AI Summary

This work addresses the inherent tension between long-term user welfare—such as sustained engagement—and short-term recommendation accuracy in recommender systems. Instead of relying on algorithmic re-ranking, it introduces a novel information-disclosure paradigm targeting content creators. Methodologically, it proposes LoRe, the first Bayesian persuasion–based framework for long-term welfare optimization in recommendation, bridging information economics and recommender systems. It models creators’ bounded rationality via a Markov decision process and employs reinforcement learning to optimize disclosure policies. Experiments on two real-world datasets demonstrate that LoRe significantly outperforms fairness-aware re-ranking and existing information-disclosure baselines, markedly improving long-term user engagement and system-wide welfare. Crucially, LoRe achieves the first mechanism-based, implicit incentive alignment for creators—guiding their behavior without explicit intervention or reward engineering.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Machine Learning: Learning Preferences or Rankings
• Multiagent Systems: Mechanism Design

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Improving the long-term user welfare (e.g., sustained user engagement) has become a central objective of recommender systems (RS). In real-world platforms, the creation behaviors of content creators plays a crucial role in shaping long-term welfare beyond short-term recommendation accuracy, making the effective steering of creator behavior essential to foster a healthier RS ecosystem. Existing works typically rely on re-ranking algorithms that heuristically adjust item exposure to steer creators' behavior. However, when embedded within recommendation pipelines, such a strategy often conflicts with the short-term objective of improving recommendation accuracy, leading to performance degradation and suboptimal long-term welfare. The well-established economics studies offer us valuable insights for an alternative approach without relying on recommendation algorithmic design: revealing information from an information-rich party (sender) to a less-informed party (receiver) can effectively change the receiver's beliefs and steer their behavior. Inspired by this idea, we propose an information-revealing framework, named Long-term Welfare Optimization via Information Revelation (LoRe). In this framework, we utilize a classical information revelation method (i.e., Bayesian persuasion) to map the stakeholders in RS, treating the platform as the sender and creators as the receivers. To address the challenge posed by the unrealistic assumption of traditional economic methods, we formulate the process of information revelation as a Markov Decision Process (MDP) and propose a learning algorithm trained and inferred in environments with boundedly rational creators. Extensive experiments on two real-world RS datasets demonstrate that our method can effectively outperform existing fair re-ranking methods and information revealing strategies in improving long-term user welfare.

Problem

• Optimizing long-term user welfare in recommender systems
• Addressing conflicts between short-term accuracy and creator behavior steering
• Developing information revelation framework to guide creator actions

Innovation

• Uses Bayesian persuasion for information revelation
• Models information revelation as Markov Decision Process
• Trains algorithm with boundedly rational creators