Identifying events from text has a long past in narrative analysis, but a short history in Natural Language Processing (NLP). In this position paper, a question is asked: given the telling of a sequence of real-world events by a news narrator, what do NLP event extraction models capture, and what do they miss? Insights from critical discourse analysis (CDA) and from a series of movements in literary criticism motivate us to model the narrated logic in news narratives.As a result, a computational framework is proposed to model the function of news narration, which shapes the narrated world, consumed by news narratees. As a simplification, we represent the causal logic between events depicted in the narrated world.

Automatic storytelling is a difficult NLP task that poses a challenge even for state-of-the-art large language models. This paper proposes a pipeline for interactive fairy tale generation in a mixed-initiative setting. Our approach introduces a story goal as a stopping condition, imposes minimal structure on the narrative in the form of a simple emotional arc, and controls the transition between the stages of the story via system prompt engineering. The resulting framework reconciles creating a structured and complete short-form narrative with retaining player agency and allowing users to influence the storyline through their input. We evaluate our approach with several proprietary and open-source language models and examine its transferability to different languages, specifically English and Russian.

This study explores the reception and understanding of the transmedia ensemble surrounding Bill Willingham’s Fables (2002-2015), a comic series reimagining fairytale characters in a modern setting. Fables expands its narrative across multiple media, including spin-off comics, a novel, and the video game The Wolf Among Us. This research investigates key questions: Can we identify a distinct group of transmedia consumers? What elements of the narrative sustain interest across media? A survey of 58 participants reveals that while most enter the franchise through the comic series, a significant number are introduced via the video game. The findings indicate that Fables fans are highly engaged transmedia consumers, with a majority exploring several parts of the franchise wanting to pursue narrative exploration. This study offers insights into how transmedia narratives are consumed, emphasizing the role of familiar story elements in encouraging cross-media engagement.

In this study, we explore the application of large language models (LLMs) to analyze narrative discourse within the framework established by the field of narratology. We develop a set of elementary narrative features derived from prior theoretical work that focus on core dimensions of narrative, including time, setting, and perspective. Through experiments with GPT-4 and fine-tuned open-source models like Llama3, we demonstrate the models’ ability to annotate narrative passages with reasonable levels of agreement with human annotators. Leveraging a dataset of human-annotated passages spanning 18 distinct narrative and non-narrative genres, our work provides empirical support for the deictic theory of narrative communication. This theory posits that a fundamental function of storytelling is the focalization of attention on distant human experiences to facilitate social coordination. We conclude with a discussion of the possibilities for LLM-driven narrative discourse understanding.

Evolving tools for narrative analysis present an opportunity to identify common structure in stories that are socially important to tell, such as stories of survival from domestic abuse. A greater structural understanding of such stories could lead to stronger protections against de-anonymization, as well as future tools to help survivors navigate the complex trade-offs inherent in trying to tell their stories safely. In this work we explore narrative patterns within a small set of domestic violence stories, identifying many similarities. We then propose a method to assess the safety of sharing a story based on a distance feature vector.

To understand how stories are structured, we would like to be able to analyze the architecture of narratives. This article reviews and compares existing annotation guidelines for scene and narrative level annotation. We propose new guidelines, based on existing ones, and show how these can be effectively extended from general-purpose to specialized contexts, such as mystery novels which feature unique narrative elements like red herrings and plot twists. This provides a controlled environment for examining genre-specific event structuring. Additionally, we present a newly annotated genre-specific dataset of mystery novels, offering valuable resources for training and evaluating models in narrative understanding. This study aims to enhance annotation practices and advance the development of computational models for narrative analysis.

We present a novel approach to classify causal micro-narratives from text. These narratives are sentence-level explanations of the cause(s) and/or effect(s) of a target subject. The approach requires only a subject-specific ontology of causes and effects, and we demonstrate it with an application to inflation narratives. Using a human-annotated dataset spanning historical and contemporary US news articles for training, we evaluate several large language models (LLMs) on this multi-label classification task. The best-performing model—a fine-tuned Llama 3.1 8B—achieves F1 scores of 0.87 on narrative detection and 0.71 on narrative classification. Comprehensive error analysis reveals challenges arising from linguistic ambiguity and highlights how model errors often mirror human annotator disagreements. This research establishes a framework for extracting causal micro-narratives from real-world data, with wide-ranging applications to social science research.

From a communications perspective, a frame defines the packaging of the language used in such a way as to encourage certain interpretations and to discourage others. For example, a news article can frame immigration as either a boost or a drain on the economy, and thus communicate very different interpretations of the same phenomenon. In this work, we argue that to explain framing devices we have to look at the way narratives are constructed. As a first step in this direction, we propose a framework that extracts events and their relations to other events, and groups them into high-level narratives that help explain frames in news articles. We show that our framework can be used to analyze framing in U.S. news for two different domains: immigration and gun control.

We investigate how NLP can help annotate the structure and complexity of oral narrative texts elicited via the Multilingual Assessment Instrument for Narratives (MAIN). MAIN is a theory-based tool designed to evaluate the narrative abilities of children who are learning one or more languages from birth or early in their development. It provides a standardized way to measure how well children can comprehend and produce stories across different languages and referential norms for children between 3 and 12 years old. MAIN has been adapted to over ninety languages and is used in over 65 countries. The MAIN analysis focuses on story structure and story complexity which are typically evaluated manually based on scoring sheets. We here investigate the automation of this process using BERT-based classification which already yields promising results.