Narrative Sharpens Gender Gaps: Surveying Film Characters with LLM Agents

2026-05-21

AI Summary

This study addresses the lack of effective quantitative tools for analyzing gendered values encoded in mainstream films and their potential impact on AI systems. By transforming 734 fictional characters from 160 U.S. films released between 1990 and 2019 into LLM-based agents grounded in script dialogues and scene descriptions, the authors simulate responses to gender-attitude items from the World Values Survey, thereby enabling the first automatic inference of gender attitudes directly from narrative content. The results reveal that these agents reproduce systematic gender differences even without explicit gender prompts, exhibiting larger attitude gaps and greater temporal volatility than real-world populations. These findings suggest that gender disparities emerge from behavioral portrayals rather than identity labels alone, challenging the cultural cultivation theory’s assumption of uniform media input.

Abstract

Mainstream film is one of the richest sources of cultural content that AI systems learn from. Yet we have few tools for measuring the gender values it encodes. We present a proof-of-concept framework that turns fictional film characters into surveyable LLM agents. Using 160 U.S. films (1990--2019), we build 734 character agents from script dialogue and scene descriptions, condense their personas via expert-style reflections, and simulate World Values Survey gender-attitude responses. Agents reproduce systematic gender differences without explicit demographic prompting, suggesting attitudes emerge from behavior rather than identity labels. Benchmarked against historical survey data, agents exaggerate gender gaps and show greater decade-to-decade volatility than real populations. Narrative sharpens rather than homogenizes gender contrasts, complicating the consistent-input assumption underlying cultivation theory's mainstreaming mechanism. AI systems trained on such corpora may inherit this stylization before any model-level amplification occurs.

Problem

• gender bias
• film narratives
• AI training data
• cultural content
• gender attitudes

Innovation

• LLM agents
• gender attitudes
• film narrative
• cultivation theory
• persona simulation