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

TL;DR

This work investigates how narrative style influences empathy toward personal stories by introducing HEART, a theory-driven taxonomy of narrative elements. It demonstrates that large language models can extract HEART features that align with expert judgments and uses a large crowdsourced dataset ($N=2624$) to analyze how style, reader traits, and interaction effects drive narrative empathy. Key findings show that vivid emotional expression, character development, and plot volume favor empathy, but responses are highly personalized and moderated by reader characteristics like trait empathy and perceived similarity. The study provides a scalable framework for narrative analysis with implications for social and behavioral insights and emphasizes reproducibility and ethical considerations in modeling 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.

Figures (6)

• Figure 1: Narrative empathy can be evoked through the way a story is told (narrative style). This work introduces Heart, a theory-driven taxonomy of narrative elements that contribute to empathy.
• Figure 2: Narrative Empathy and Style Taxonomy delineating aspects of narrative style that theoretically relate to empathy towards a narrative.
• Figure 3: Visualization of how narrative style elements and reader characteristics influence the experience a reader has with a narrative (narrative-reader interaction effects). All of these components combined in turn influence downstream narrative empathy.
• Figure 4: Structural equation modeling of how narrative style elements lead to narrative transportation, combined with effects of the reader sharing a similar experience with the narrator and the reader's baseline trait empathy.
• Figure 5: Comparing average empathy across high vs low presence of each narrative feature, we show that there are significant increases in empathy for stories with more character development and plot volume.