Feedback dynamics in Politics: The interplay between sentiment and engagement

2025-11-04

AI Summary

This study investigates whether political actors dynamically adjust the emotional valence of their Twitter posts in response to public feedback. Method: Leveraging over 1.5 million tweets from Members of Parliament in the UK, Spain, and Greece in 2021, we apply fine-grained sentiment analysis and interpretable linear modeling to quantify feedback-driven emotional adaptation. Contribution/Results: We identify a statistically significant feedback-regulated emotional modulation mechanism: opposition politicians amplify negative sentiment in response to negative engagement, whereas governing-party actors increase positive expression following positive feedback. Building on these findings, we propose the first control-theoretic model of political communication adaptation. This work provides the first empirical evidence of a closed-loop “emotion–engagement” co-evolutionary process on social media, demonstrating that audience feedback not only shapes individual strategic behavior but also drives self-reinforcing dynamics within the public discourse ecosystem.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Humans and AI: Emotional Intelligence
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Social Networks and Social Media: Media and governance, opinion dynamics, filter bubbles, polarization
• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization

Abstract

We investigate feedback mechanisms in political communication by testing whether politicians adapt the sentiment of their messages in response to public engagement. Using over 1.5 million tweets from Members of Parliament in the United Kingdom, Spain, and Greece during 2021, we identify sentiment dynamics through a simple yet interpretable linear model. The analysis reveals a closed-loop behavior: engagement with positive and negative messages influences the sentiment of subsequent posts. Moreover, the learned coefficients highlight systematic differences across political roles: opposition members are more reactive to negative engagement, whereas government officials respond more to positive signals. These results provide a quantitative, control-oriented view of behavioral adaptation in online politics, showing how feedback principles can explain the self-reinforcing dynamics that emerge in social media discourse.

Problem

• Analyzing how politicians adapt message sentiment based on public engagement feedback
• Identifying systematic differences in engagement responses between government and opposition
• Quantifying self-reinforcing feedback dynamics in political social media communication

Innovation

• Using interpretable linear model for sentiment analysis
• Analyzing engagement impact on political message sentiment
• Identifying role-based differences in feedback responsiveness