CompRes: A Dataset for Narrative Structure in News

TL;DR

This paper introduces CompRes, a novel dataset for analyzing narrative structures in news articles, and demonstrates models that can identify narrative elements with promising accuracy, advancing understanding of news storytelling.

Contribution

We created the first dataset tailored for narrative analysis in news media, with a new annotation scheme and trained models achieving up to 0.7 F1 score.

Findings

Achieved up to 0.7 F1 score in identifying narrative elements

Developed a new annotation scheme for news narratives

Constructed the first dataset for narrative structure in news

Abstract

This paper addresses the task of automatically detecting narrative structures in raw texts. Previous works have utilized the oral narrative theory by Labov and Waletzky to identify various narrative elements in personal stories texts. Instead, we direct our focus to news articles, motivated by their growing social impact as well as their role in creating and shaping public opinion. We introduce CompRes -- the first dataset for narrative structure in news media. We describe the process in which the dataset was constructed: first, we designed a new narrative annotation scheme, better suited for news media, by adapting elements from the narrative theory of Labov and Waletzky (Complication and Resolution) and adding a new narrative element of our own (Success); then, we used that scheme to annotate a set of 29 English news articles (containing 1,099 sentences) collected from news and partisan websites. We use the annotated dataset to train several supervised models to identify the different narrative elements, achieving an $F_1$ score of up to 0.7. We conclude by suggesting several promising directions for future work.