Comparing Sentiment Contagion in AI-Agent and Human Social Networks: Evidence from MOLTBOOK

2026-06-04

AI Summary

This study investigates whether emotions—particularly negative affect—exhibit human-like contagion within AI agent social networks. Leveraging 2.9 million posts and 1.5 million comments from the MOLTBOOK platform, it presents the first systematic comparison of emotional transmission mechanisms between AI-driven and human social networks. The findings reveal that although negative posts elicit higher engagement, AI agents predominantly respond with neutral sentiment, resulting in negligible cross-day propagation of negative emotions. This suggests that large language model–powered AI social networks possess an intrinsic mechanism that suppresses emotional polarization, markedly contrasting with the emotion-amplifying dynamics commonly observed in human networks.

Abstract

AI agents are beginning to interact not only with people, but also with one another. We investigate what happens to sentiment in such an AI-only social network: does negativity spread, or do replies calm it down? We study MOLTBOOK, a social network made up of autonomous language-model agents, using almost 2.9 million posts and 1.5 million comments. Negative posts receive many more replies than neutral or positive posts, so negativity still attracts attention. However, replies to negative content usually do not stay negative. They most often become neutral, and there is meager evidence that negative sentiment spreads across days. The main pattern is therefore not a cycle of negativity, but negative attention followed by neutralisation. These findings suggest that AI-agent networks may behave differently from human social networks: they may dampen emotional extremes, while still depending strongly on how interactions are organised.

Problem

• sentiment contagion
• AI-agent social networks
• emotional dynamics
• negativity spread
• human vs AI interaction

Innovation

• AI-agent social networks
• sentiment contagion
• emotional neutralisation
• autonomous language models
• MOLTBOOK