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

arXiv: https://arxiv.org/abs/2505.24331 · HTML: https://mlsanity.com/paper/2505.24331/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 64 references that are in the map.
- First posted on arXiv 30 May 2025.

## Builds on (most cited first, 17 of 17)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Character-LLM: A Trainable Agent for Role-Playing](https://mlsanity.com/paper/2310.10158/) (2023)
- [Is ChatGPT a Good Sentiment Analyzer? A Preliminary Study](https://mlsanity.com/paper/2304.04339/) (2023)
- [Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions](https://mlsanity.com/paper/2312.02913/) (2023)
- [How to Enable LLM with 3D Capacity? A Survey of Spatial Reasoning in LLM](https://mlsanity.com/paper/2504.05786/) (2025)
- [CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global Memory](https://mlsanity.com/paper/2505.05622/) (2025)
- [Learning and Forecasting Opinion Dynamics in Social Networks](https://mlsanity.com/paper/1506.05474/) (2015)
- [Balanced Token Pruning: Accelerating Vision Language Models Beyond Local Optimization](https://mlsanity.com/paper/2505.22038/) (2025)
- [Multimodal Sentiment Analysis To Explore the Structure of Emotions](https://mlsanity.com/paper/1805.10205/) (2018)
- [Learning Opinion Dynamics From Social Traces](https://mlsanity.com/paper/2006.01673/) (2020)
- [Performance of Social Network Sensors During Hurricane Sandy](https://mlsanity.com/paper/1402.2482/) (2014)
- [Understanding and Evaluating Hallucinations in 3D Visual Language Models](https://mlsanity.com/paper/2502.15888/) (2025)
- [AR-BERT: Aspect-relation enhanced Aspect-level Sentiment Classification with Multi-modal Explanations](https://mlsanity.com/paper/2108.11656/) (2021)
- [Predicting the 2020 US Presidential Election with Twitter](https://mlsanity.com/paper/2107.09640/) (2021)
- [Leveraging Explainable AI to Analyze Researchers' Aspect-Based Sentiment about ChatGPT](https://mlsanity.com/paper/2308.11001/) (2023)

## Built on by (most cited first, 1 of 1)

- [SocietyBench: Forecasting Counterfactual Social-World Evolution](https://mlsanity.com/paper/2608.04009/) (2026)

## Abstract (arXiv)

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 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.