Context-Aware Sentiment Forecasting via LLM-based Multi-Perspective Role-Playing Agents

TL;DR

This paper introduces a novel multi-perspective role-playing framework using large language models to predict future social media user sentiments during ongoing events, improving forecasting accuracy.

Contribution

It presents a new LLM-based role-playing approach for sentiment forecasting that incorporates multiple perspectives to better simulate human responses.

Findings

Significant improvement in sentiment prediction accuracy

Effective modeling of both individual and collective sentiment dynamics

Demonstrated potential for real-time social media analysis

Abstract

User sentiment on social media reveals the underlying social trends, crises, and needs. Researchers have analyzed users' past messages to trace the evolution of sentiments and reconstruct sentiment dynamics. However, predicting the imminent sentiment of an ongoing event is rarely studied. In this paper, we address the problem of \textbf{sentiment forecasting} on social media to predict the user's future sentiment in response to the development of the event. We extract sentiment-related features to enhance the modeling skill and propose a multi-perspective role-playing framework to simulate the process of human response. Our preliminary results show significant improvement in sentiment forecasting on both microscopic and macroscopic levels.