Causally-Informed Reinforcement Learning for Adaptive Emotion-Aware Social Media Recommendation

TL;DR

This paper introduces an emotion-aware social media recommendation framework that personalizes content to improve users' emotional well-being while maintaining engagement, using a hybrid model combining emotion prediction and causally informed reinforcement learning.

Contribution

It presents a novel hybrid recommendation system integrating emotion prediction with causally informed reinforcement learning to enhance emotional well-being in social media users.

Findings

Improved emotional recovery and reduced emotional volatility.

Maintained strong engagement metrics over 30-day interactions.

Demonstrated effectiveness of causally informed rewards in RL.

Abstract

Social media recommendation systems play a central role in shaping users' emotional experiences. However, most systems are optimized solely for engagement metrics, such as click rate, viewing time, or scrolling, without accounting for users' emotional states. Repeated exposure to emotionally charged content has been shown to negatively affect users' emotional well-being over time. We propose an Emotion-aware Social Media Recommendation (ESMR) framework that personalizes content based on users' evolving emotional trajectories. ESMR integrates a Transformer-based emotion predictor with a hybrid recommendation policy: a LightGBM model for engagement during stable periods and a reinforcement learning agent with causally informed rewards when negative emotional states persist. Through behaviorally grounded evaluation over 30-day interaction traces, ESMR demonstrates improved emotional recovery, reduced volatility, and strong engagement retention. ESMR offers a path toward emotionally aware recommendations without compromising engagement performance.