EXPLORING GENDER-BASED VIOLENCE IN NIGERIA THROUGH A COMPUTATIONAL SOCIOLOGICAL LENS

Abstract

Gender-based violence (GBV) in Nigeria remains a critical social issue rooted in complex intersections of patriarchy, cultural norms, and socio-economic inequality. This study adopts a computational sociological framework to examine the structural and behavioral dimensions of GBV across Nigerian communities. We integrate sentiment analysis (VADER, TextBlob), geospatial mapping (QGIS), and machine learning models (Random Forest) to analyze social media discourse, crime data, and national surveys spanning 2000–2023. Findings reveal that GBV hotspots strongly correlate with regions marked by low female literacy and high poverty rates, while sentiment analysis of online discourse highlights polarized narratives oscillating between outrage, solidarity, and victim-blaming. By merging sociological theory with data science tools, this interdisciplinary approach enables real-time tracking, predictive modeling, and targeted interventions providing a scalable, evidence-based platform for advocacy, policymaking, and survivor-centered reform. The study underscores the importance of integrating computational tools into sociological research to dismantle systemic violence and inform culturally nuanced responses to GBV in Nigeria and similar socio-cultural contexts