HEART-felt Narratives: Tracing Empathy and Narrative Style in Personal Stories with LLMs

TL;DR

This paper introduces the HEART taxonomy to analyze how narrative style influences empathy in personal stories, using large language models and crowdsourcing to quantify and understand this relationship.

Contribution

The study presents a novel, theory-based taxonomy called HEART for analyzing narrative style and demonstrates how LLMs can extract these elements to predict empathy in stories.

Findings

LLMs can reliably extract narrative elements like vividness and plot volume.

Narrative style elements significantly correlate with empathy judgments.

The taxonomy enables large-scale, human-centered analysis of storytelling and empathy.

Abstract

Empathy serves as a cornerstone in enabling prosocial behaviors, and can be evoked through sharing of personal experiences in stories. While empathy is influenced by narrative content, intuitively, people respond to the way a story is told as well, through narrative style. Yet the relationship between empathy and narrative style is not fully understood. In this work, we empirically examine and quantify this relationship between style and empathy using LLMs and large-scale crowdsourcing studies. We introduce a novel, theory-based taxonomy, HEART (Human Empathy and Narrative Taxonomy) that delineates elements of narrative style that can lead to empathy with the narrator of a story. We establish the performance of LLMs in extracting narrative elements from HEART, showing that prompting with our taxonomy leads to reasonable, human-level annotations beyond what prior lexicon-based methods can do. To show empirical use of our taxonomy, we collect a dataset of empathy judgments of stories via a large-scale crowdsourcing study with N=2,624 participants. We show that narrative elements extracted via LLMs, in particular, vividness of emotions and plot volume, can elucidate the pathways by which narrative style cultivates empathy towards personal stories. Our work suggests that such models can be used for narrative analyses that lead to human-centered social and behavioral insights.