Digital Voices of Survival: From Social Media Disclosures to Support Provisions for Domestic Violence Victims

2025-09-15

AI Summary

Domestic violence (DV) poses a critical public health challenge, and survivors increasingly disclose experiences on social media to seek support; however, existing research lacks a systematic understanding of the relationship between online help-seeking behaviors and community responses. This study proposes the first four-stage computational analytical framework—integrating natural language processing, text clustering, topic summarization, and support-behavior extraction—to automatically identify heterogeneous help-seeking signals, cluster narrative themes, and model community response patterns from large-scale social media data. It establishes the first fine-grained mapping between DV survivors’ digital disclosures and corresponding support mechanisms, revealing prototypical help-seeking pathways and characteristics of effective responses. The framework provides a reusable methodological foundation and empirical evidence for designing survivor-centered, AI-enabled intervention tools.

Technology Category

Application Domains: Humanities & Computational Social ScienceHumans and AI: Crowd Sourcing and Human ComputationNatural Language Processing: Safety and Robustness

Application Category

Social Networks and Social Media: Analysis of web-mediated communications, communities, and crowdsResponsible Web: Algorithmic accountability and transparency on the webWeb Mining and Content Analysis: Community question answering

Abstract

Domestic Violence (DV) is a pervasive public health problem characterized by patterns of coercive and abusive behavior within intimate relationships. With the rise of social media as a key outlet for DV victims to disclose their experiences, online self-disclosure has emerged as a critical yet underexplored avenue for support-seeking. In addition, existing research lacks a comprehensive and nuanced understanding of DV self-disclosure, support provisions, and their connections. To address these gaps, this study proposes a novel computational framework for modeling DV support-seeking behavior alongside community support mechanisms. The framework consists of four key components: self-disclosure detection, post clustering, topic summarization, and support extraction and mapping. We implement and evaluate the framework with data collected from relevant social media communities. Our findings not only advance existing knowledge on DV self-disclosure and online support provisions but also enable victim-centered digital interventions.

Problem

• Detecting domestic violence self-disclosures on social media
• Mapping support provisions for domestic violence victims
• Understanding connections between disclosures and support mechanisms

Innovation

• Computational framework for DV support-seeking
• Self-disclosure detection and post clustering
• Topic summarization and support mapping