From Social Division to Cohesion with AI Message Suggestions in Online Chat Groups

2025-10-24

AI Summary

In ideologically diverse online group chats, enhancing social cohesion through AI constitutes a critical challenge. This paper proposes a relationship-oriented large language model (LLM) message suggestion mechanism that diverges from conventional personalized recommendation paradigms. Instead of optimizing for individual preference alone, our approach dynamically integrates user-specific preferences with collective group stances and employs linguistic style adaptation to foster cross-position understanding. Empirical evaluation demonstrates that the method significantly improves conversational inclusivity, reduces opinion segregation, and strengthens group identification and collaborative intent. Crucially, this work is the first to systematically demonstrate how shifting AI-mediated communication support—from “individual adaptation” to “relational bridging”—exerts positive structural effects on social cohesion. It thereby provides both a theoretically grounded framework and an implementable technical pathway for cultivating more resilient digital public spheres.

Technology Category

• Humans and AI: Learning Human Values and Preferences
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Social cohesion is difficult to sustain in societies marked by opinion diversity, particularly in online communication. As large language model (LLM)-driven messaging assistance becomes increasingly embedded in these contexts, it raises critical questions about its societal impact. We present an online experiment with 557 participants who engaged in multi-round discussions on politically controversial topics while freely reconfiguring their discussion groups. In some conditions, participants received real-time message suggestions generated by an LLM, either personalized to the individual or adapted to their group context. We find that subtle shifts in linguistic style during communication, mediated by AI assistance, can scale up to reshape collective structures. While individual-focused assistance leads users to segregate into like-minded groups, relational assistance that incorporates group members' stances enhances cohesion through more receptive exchanges. These findings demonstrate that AI-mediated communication can support social cohesion in diverse groups, but outcomes critically depend on how personalization is designed.

Problem

• AI message suggestions impact social cohesion in diverse online chat groups
• Personalized versus group-adapted AI assistance shapes opinion segregation or integration
• Linguistic style shifts through AI mediation reshape collective discussion structures

Innovation

• LLM provides real-time personalized message suggestions
• AI assistance adapts to group context for cohesion
• Subtle linguistic shifts reshape collective discussion structures