Social Story Frames: Contextual Reasoning about Narrative Intent and Reception

2025-12-17

AI Summary

Existing computational models lack fine-grained capacity to model readers’ multifaceted responses—including intention inference, affective reactions, and value judgments—to narrative content. To address this, we propose SocialStoryFrames (SSF), a formal framework introducing the first unified reader-response taxonomy integrating narratology, pragmatics, and psychology. We design a dual-model architecture—SSF-Generator and SSF-Classifier—that leverages prompt engineering, fine-tuned language models, and rigorous human annotation (N=382 crowdworkers plus domain experts), augmented by statistical analysis, to achieve context-sensitive narrative understanding. Evaluated on 6,140 socially situated stories drawn from diverse online communities, SSF enables robust quantification of narrative intention distributions and cross-community pragmatic variation. Our framework provides both a theoretical foundation and scalable computational infrastructure for large-scale, interpretable online narrative research.

Technology Category

• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Application Domains: Humanities & Computational Social Science
• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Reading stories evokes rich interpretive, affective, and evaluative responses, such as inferences about narrative intent or judgments about characters. Yet, computational models of reader response are limited, preventing nuanced analyses. To address this gap, we introduce SocialStoryFrames, a formalism for distilling plausible inferences about reader response, such as perceived author intent, explanatory and predictive reasoning, affective responses, and value judgments, using conversational context and a taxonomy grounded in narrative theory, linguistic pragmatics, and psychology. We develop two models, SSF-Generator and SSF-Classifier, validated through human surveys (N=382 participants) and expert annotations, respectively. We conduct pilot analyses to showcase the utility of the formalism for studying storytelling at scale. Specifically, applying our models to SSF-Corpus, a curated dataset of 6,140 social media stories from diverse contexts, we characterize the frequency and interdependence of storytelling intents, and we compare and contrast narrative practices (and their diversity) across communities. By linking fine-grained, context-sensitive modeling with a generic taxonomy of reader responses, SocialStoryFrames enable new research into storytelling in online communities.

Problem

• Develop computational models for analyzing reader responses to narratives
• Create formalism to infer narrative intent and affective reader reactions
• Enable large-scale study of storytelling practices across online communities

Innovation

• Formalism distills reader responses using narrative theory and psychology
• Two models validated through human surveys and expert annotations
• Applied to social media dataset to analyze storytelling intents and practices