What makes for an enjoyable protagonist? An analysis of character warmth and competence

2026-01-10

arXiv.org

AI Summary

This study investigates how the perceived warmth and competence of film protagonists influence audience ratings and examines the heterogeneity of this effect across film genres. Drawing on psychological and narrative theories, we present the first large-scale integration of a large language model (GPT-4.1-Mini) with psychological constructs, employing the LLM_annotate toolkit to annotate protagonist traits in 2,858 films. Bayesian regression analyses reveal that both warmth and competence exert small but theoretically consistent positive effects on IMDb ratings. Notably, films featuring male protagonists—despite their slightly lower warmth scores—receive significantly higher ratings, an effect substantially larger than that of personality traits themselves. Inter-rater reliability between human and LLM annotations was high (r = .83). This work establishes a reproducible paradigm for AI-driven research at the intersection of humanities and psychological science.

Technology Category

Humans and AI: Emotional IntelligenceCognitive Modeling & Cognitive Systems: Simulating Human BehaviorNatural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining

Application Category

Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactionsEconomics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labelingUser Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Drawing on psychological and literary theory, we investigated whether the warmth and competence of movie protagonists predict IMDb ratings, and whether these effects vary across genres. Using 2,858 films and series from the Movie Scripts Corpus, we identified protagonists via AI-assisted annotation and quantified their warmth and competence with the LLM_annotate package ([1]; human-LLM agreement: r = .83). Preregistered Bayesian regression analyses revealed theory-consistent but small associations between both warmth and competence and audience ratings, while genre-specific interactions did not meaningfully improve predictions. Male protagonists were slightly less warm than female protagonists, and movies with male leads received higher ratings on average (an association that was multiple times stronger than the relationships between movie ratings and warmth/competence). These findings suggest that, although audiences tend to favor warm, competent characters, the effects on movie evaluations are modest, indicating that character personality is only one of many factors shaping movie ratings. AI-assisted annotation with LLM_annotate and gpt-4.1-mini proved effective for large-scale analyses but occasionally fell short of manually generated annotations.

Problem

• protagonist
• warmth
• competence
• audience ratings
• genre

Innovation

• AI-assisted annotation
• LLM_annotate
• large-scale character analysis
• personality quantification
• gpt-4.1-mini