Mimicking the Mavens: Agent-based Opinion Synthesis and Emotion Prediction for Social Media Influencers

TL;DR

This paper presents a computational framework combining agent-based modeling, large language models, and retrieval-augmented generation to predict social media influencers' opinions and public emotional responses to trending topics.

Contribution

It introduces an innovative 5W1H question formulation engine and a multi-agent system for opinion and emotion prediction, advancing methods for analyzing online social dynamics.

Findings

High fidelity of the 5W1H module with GPT-4 score of 8.83/10

Influencer agents achieved an average GPT-4 rating of 6.85/10

Accurate prediction of perspectives and emotions in the Russia-Ukraine War case study

Abstract

Predicting influencers' views and public sentiment on social media is crucial for anticipating societal trends and guiding strategic responses. This study introduces a novel computational framework to predict opinion leaders' perspectives and the emotive reactions of the populace, addressing the inherent challenges posed by the unstructured, context-sensitive, and heterogeneous nature of online communication. Our research introduces an innovative module that starts with the automatic 5W1H (Where, Who, When, What, Why, and How) questions formulation engine, tailored to emerging news stories and trending topics. We then build a total of 60 anonymous opinion leader agents in six domains and realize the views generation based on an enhanced large language model (LLM) coupled with retrieval-augmented generation (RAG). Subsequently, we synthesize the potential views of opinion leaders and predicted the emotional responses to different events. The efficacy of our automated 5W1H module is corroborated by an average GPT-4 score of 8.83/10, indicative of high fidelity. The influencer agents exhibit a consistent performance, achieving an average GPT-4 rating of 6.85/10 across evaluative metrics. Utilizing the 'Russia-Ukraine War' as a case study, our methodology accurately foresees key influencers' perspectives and aligns emotional predictions with real-world sentiment trends in various domains.