From Individuals to Crowds: Dual-Level Public Response Prediction in Social Media

2025-08-01

AI Summary

Existing social media public response prediction methods suffer from two key limitations: insufficient micro-level personalization and inadequate macro-level modeling of collective sentiment. To address these, this paper proposes SocialAlign—a unified framework enabling dual-level modeling that jointly optimizes individual response generation and alignment with population-level sentiment distributions. SocialAlign introduces a PAC-LoRA multi-expert architecture to jointly perform personalized content understanding and response generation. It integrates SocialLLM with LoRA-based fine-tuning to jointly model user preferences, topic-aware analysis, and population sentiment distribution learning grounded in real-world social data. Evaluated on the SentiWeibo and LaMP benchmarks, SocialAlign achieves significant improvements over state-of-the-art methods, enhancing prediction accuracy, interpretability, and cross-scenario generalization capability.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Natural Language Processing: (Large) Language Models

Application Category

• User Modeling, Personalization and Recommendation: Social recommender systems and personalization for the social Web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Public response prediction is critical for understanding how individuals or groups might react to specific events, policies, or social phenomena, making it highly valuable for crisis management, policy-making, and social media analysis. However, existing works face notable limitations. First, they lack micro-level personalization, producing generic responses that ignore individual user preferences. Moreover, they overlook macro-level sentiment distribution and only deal with individual-level sentiment, constraining them from analyzing broader societal trends and group sentiment dynamics. To address these challenges, we propose SocialAlign, a unified framework that predicts real-world responses at both micro and macro levels in social contexts. At the micro level, SocialAlign employs SocialLLM with an articulate Personalized Analyze-Compose LoRA (PAC-LoRA) structure, which deploys specialized expert modules for content analysis and response generation across diverse topics and user profiles, enabling the generation of personalized comments with corresponding sentiments. At the macro level, it models group sentiment distributions and aligns predictions with real-world sentiment trends derived from social media data. To evaluate SocialAlign in real-world scenarios, we introduce SentiWeibo, a large-scale dataset curated from authentic social interactions on the Weibo platform. Experimental results on our SentiWeibo and related LaMP benchmark demonstrate that SocialAlign surpasses strong baselines, showing improved accuracy, interpretability, and generalization in public response prediction. We hope our work inspires further research in public response prediction and computational social science: https://github.com/Znull-1220/SocialAlign.

Problem

• Predicts public responses at individual and group levels in social media
• Addresses lack of personalization in existing response prediction methods
• Models sentiment distribution to analyze societal trends and group dynamics

Innovation

• Dual-level prediction for individual and group responses
• Personalized Analyze-Compose LoRA for micro-level personalization
• Alignment with real-world sentiment trends at macro level