We introduce Taxonomy-Free Character Role Labeling (TF-CRL); a novel task that assigns open-ended narrative role labels to characters in news stories based on their functional role in the narrative. Unlike fixed taxonomies, TF-CRL enables more nuanced and comparative analysis by generating compositional labels (e.g., Resilient Leader, Scapegoated Visionary). We evaluate several large language models (LLMs) on this task using human preference rankings and ratings across four criteria: faithfulness, relevance, informativeness, and generalizability. LLMs almost uniformly outperform human annotators across all dimensions. We further show how TF-CRL supports rich narrative analysis by revealing novel latent taxonomies and enabling cross-domain narrative comparisons. Our approach offers new tools for studying media portrayals, character framing, and the socio-political impacts of narrative roles at-scale.

In this study, we explore the use of Large Language Models (LLMs) such as GPT-4 to extract and analyze the latent narrative messaging in climate change-related news articles from North American and Chinese media. By defining “narrative messaging” as the intrinsic moral or lesson of a story, we apply our model to a dataset of approximately 15,000 news articles in English and Mandarin, categorized by climate-related topics and ideological groupings. Our findings reveal distinct differences in the narrative values emphasized by different cultural and ideological contexts, with North American sources often focusing on individualistic and crisis-driven themes, while Chinese sources emphasize developmental and cooperative narratives. This work demonstrates the potential of LLMs in understanding and influencing climate communication, offering new insights into the collective belief systems that shape public discourse on climate change across different cultures.

Stories are not only designed to entertain but encode lessons reflecting their authors’ beliefs about the world. In this paper, we propose a new task of narrative schema labelling based on the concept of “story morals” to identify the values and lessons conveyed in stories. Using large language models (LLMs) such as GPT-4, we develop methods to automatically extract and validate story morals across a diverse set of narrative genres, including folktales, novels, movies and TV, personal stories from social media and the news. Our approach involves a multi-step prompting sequence to derive morals and validate them through both automated metrics and human assessments. The findings suggest that LLMs can effectively approximate human story moral interpretations and offer a new avenue for computational narrative understanding. By clustering the extracted morals on a sample dataset of folktales from around the world, we highlight the commonalities and distinctiveness of narrative values, providing preliminary insights into the distribution of values across cultures. This work opens up new possibilities for studying narrative schemas and their role in shaping human beliefs and behaviors.