Reproduce “Emotion Dynamics in Movie Dialogues” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Will E. Hipson, Saif M. Mohammad

The paper introduces the Utterance Emotion Dynamics (UED) framework, operationalizing psychological concepts to quantify how individual characters' emotions unfold in movie dialogues. It applies this framework to thousands of movie characters, demonstrating systematic patterns where negative emotions and character-character discordance peak around 91% into the narrative.

Key insights

  • Complex psychological concepts of emotion dynamics can be effectively translated into measurable computational metrics derived from individual character utterances in narrative texts.
  • Individual character emotional trajectories and interactions in narratives exhibit systematic, non-random trends, providing empirical support for literary theories about common story arcs.
  • Character-character emotional discordance increases towards the narrative climax, largely correlated with an overall rise in negative emotional expressions.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.