Personality Differences Drive Conversational Dynamics: A High-Dimensional NLP Approach

2024-10-14

Proceedings of the Second Workshop on Social Influence in Conversations (SICon 2024)

AI Summary

This study investigates how personality traits—specifically openness and extraversion—drive topic evolution, linguistic alignment, and emotional dynamics in stranger conversations. To address this, we introduce “topic entropy” as a novel metric quantifying thematic diversity, and integrate text embedding trajectory modeling, nonlinear dimensionality reduction (t-SNE), and time-resolved cosine similarity analysis to capture dynamic, real-time couplings among personality, discourse, and emotion. Our method enables the first fine-grained, interpretable characterization of these triadic interactions. Results show that interlocutor differences in openness positively predict topic breadth, whereas differences in extraversion accelerate the decay of linguistic alignment and significantly moderate the amplitude of emotional fluctuations. The framework provides both a theoretically grounded, computationally tractable model and empirical evidence for individual-difference effects in social interaction, advancing computational social science and human–computer interaction research.

Technology Category

• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Application Domains: Humanities & Computational Social Science
• Natural Language Processing: Discourse, Pragmatics & Argument Mining

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Web Mining and Content Analysis: Topic discovery and tracking
• Social Networks and Social Media: Computational social science

Abstract

This paper investigates how the topical flow of dyadic conversations emerges over time and how differences in interlocutors' personality traits contribute to this topical flow. Leveraging text embeddings, we map the trajectories of $N = 1655$ conversations between strangers into a high-dimensional space. Using nonlinear projections and clustering, we then identify when each interlocutor enters and exits various topics. Differences in conversational flow are quantified via $ extit{topic entropy}$, a summary measure of the"spread"of topics covered during a conversation, and $ extit{linguistic alignment}$, a time-varying measure of the cosine similarity between interlocutors' embeddings. Our findings suggest that interlocutors with a larger difference in the personality dimension of openness influence each other to spend more time discussing a wider range of topics and that interlocutors with a larger difference in extraversion experience a larger decrease in linguistic alignment throughout their conversation. We also examine how participants' affect (emotion) changes from before to after a conversation, finding that a larger difference in extraversion predicts a larger difference in affect change and that a greater topic entropy predicts a larger affect increase. This work demonstrates how communication research can be advanced through the use of high-dimensional NLP methods and identifies personality difference as an important driver of social influence.

Problem

• Personality Differences
• Topic Variability
• Emotional Impact

Innovation

• High-dimensional NLP
• Personality Impact
• Conversation Analysis