Mimicking the Mavens: Agent-based Opinion Synthesis and Emotion Prediction for Social Media Influencers
This addresses the problem of anticipating societal trends for strategic responses in social media, but it is incremental as it builds on existing LLM and agent-based methods.
The study tackled predicting social media influencers' opinions and public emotional reactions by developing a computational framework with an automated 5W1H question engine and 60 opinion leader agents using enhanced LLMs and RAG, achieving an average GPT-4 score of 8.83/10 for the engine and 6.85/10 for the agents in a case study on the Russia-Ukraine War.
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.