Context-Aware Sentiment Forecasting via LLM-based Multi-Perspective Role-Playing Agents
Fanhang Man, Huandong Wang, Jianjie Fang, Zhaoyi Deng, Baining Zhao, Xinlei Chen, Yong Li
Abstract
User sentiment on social media reveals underlying social trends, crises, and needs. Researchers have analyzed users’ past messages to track the evolution of sentiments and reconstruct sentiment dynamics. However, predicting the imminent sentiment response of users to ongoing events remains understudied. In this paper, we address the problem of sentiment forecasting on social media to predict users’ future sentiment based on event developments. We extract sentiment-related features to enhance modeling and propose a multi-perspective role-playing framework to simulate human response processes. Our preliminary results show significant improvements in sentiment forecasting at both microscopic and macroscopic levels.
BibTeX
@inproceedings{man-etal-2025-context,
title = "Context-Aware Sentiment Forecasting via {LLM}-based Multi-Perspective Role-Playing Agents",
author = "Man, Fanhang and
Wang, Huandong and
Fang, Jianjie and
Deng, Zhaoyi and
Zhao, Baining and
Chen, Xinlei and
Li, Yong",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.136/",
doi = "10.18653/v1/2025.acl-long.136",
pages = "2687--2703",
ISBN = "979-8-89176-251-0"
}