Using LLMs to Infer Non-Binary COVID-19 Sentiments of Chinese Micro-bloggers

2025-01-09

AI Summary

This study investigates the dynamic evolution of Weibo users’ emotions and associated sociopolitical attitude polarization across distinct phases of the COVID-19 pandemic—pre-outbreak, outbreak, and early containment. To address the limitations of binary sentiment classification, we propose the first four-way non-binary sentiment taxonomy for Chinese social media (positive, negative, ironic, neutral). Leveraging Llama-3-8B, we develop an interpretable sentiment recognition pipeline integrating domain-adapted prompt engineering and a manually annotated dataset. Experimental results demonstrate that our method accurately captures policy-driven and event-triggered emotional shifts, significantly enhancing fine-grained public opinion tracking. The work fills a critical gap in multidimensional sentiment analysis of Chinese-language platforms during public health emergencies and establishes a timely, traceable analytical paradigm for digital public opinion governance.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Application Domains: Humanities & Computational Social Science
• Humans and AI: Voting

Application Category

• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• Social Networks and Social Media: Media and governance, opinion dynamics, filter bubbles, polarization
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

Studying public sentiment during crises is crucial for understanding how opinions and sentiments shift, resulting in polarized societies. We study Weibo, the most popular microblogging site in China, using posts made during the outbreak of the COVID-19 crisis. The study period includes the pre-COVID-19 stage, the outbreak stage, and the early stage of epidemic prevention. We use Llama 3 8B, a Large Language Model, to analyze users' sentiments on the platform by classifying them into positive, negative, sarcastic, and neutral categories. Analyzing sentiment shifts on Weibo provides insights into how social events and government actions influence public opinion. This study contributes to understanding the dynamics of social sentiments during health crises, fulfilling a gap in sentiment analysis for Chinese platforms. By examining these dynamics, we aim to offer valuable perspectives on digital communication's role in shaping society's responses during unprecedented global challenges.

Problem

• Sentiment Analysis
• COVID-19
• Social Media

Innovation

• Llama 3 8B
• COVID-19
• Chinese Social Media Sentiment Analysis