Do Large Language Models Understand Verbal Indicators of Romantic Attraction?

2024-06-23

arXiv.org

AI Summary

This study investigates whether large language models (LLMs) can detect implicit signals of romantic attraction from speed-dating conversations. Using a dataset of 964 real speed-dating dyads, we conducted zero-shot inference with ChatGPT and Claude 3 to predict both objective matching outcomes (contact exchange) and subjective attraction ratings. Results show LLMs achieve modest but significant predictive accuracy (r = 0.12–0.23), matching expert human raters and substantially outperforming participants’ self-predictions. Crucially, this work provides the first evidence that LLMs capture non-explicit conversational dynamics—such as rhythmic alignment and lexical entrainment—whose representations exhibit neural–behavioral overlap with human judgments, partially independent of predictive performance. Moreover, approximately 50% of the variance in LLM predictions remains unexplained by conventional semantic features (e.g., sentiment polarity), indicating their capacity to model deep, socially grounded interactional cues beyond surface-level semantics.

Technology Category

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

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

What makes people 'click' on a first date and become mutually attracted to one another? While understanding and predicting the dynamics of romantic interactions used to be exclusive to human judgment, we show that Large Language Models (LLMs) can detect romantic attraction during brief getting-to-know-you interactions. Examining data from 964 speed dates, we show that ChatGPT (and Claude 3) can predict both objective and subjective indicators of speed dating success (r=0.12-0.23). ChatGPT's predictions of actual matching (i.e., the exchange of contact information) were not only on par with those of human judges who had access to the same information but incremental to speed daters' own predictions. While some of the variance in ChatGPT's predictions can be explained by common content dimensions (such as the valence of the conversations) the fact that there remains a substantial proportion of unexplained variance suggests that ChatGPT also picks up on conversational dynamics. In addition, ChatGPT's judgments showed substantial overlap with those made by the human observers (mean r=0.29), highlighting similarities in their representation of romantic attraction that is, partially, independent of accuracy.

Problem

• Can AI detect romantic attraction in human conversations
• Evaluating ChatGPT's accuracy in predicting speed dating success
• Comparing AI and human judgments on romantic attraction cues

Innovation

• Using ChatGPT to detect romantic attraction cues
• Analyzing linguistic patterns in speed dating conversations
• Comparing AI and human judgment accuracy