Working paper number:2021-61
Paper Abstract:Despite the volume of studies leveraging big data to explore socio-demographic phenomena, we still know little about the intersection of digital information and the social problem of intimate partner violence (IPV). This is an important knowledge gap, as IPV remains a pressing public-health concern worldwide, with 35% of women having experienced it over their lifetime and cases rising dramatically in the wake of global crises such as the current COVID-19 pandemic. This study addresses the question of whether online data from Google Trends might help to reach “hard-to-reach” populations such as victims of IPV using Italy as a case-study. We ask the following questions: Can digital traces help predict instances of IPV — both potential threat and actual violent cases — in Italy? Is their predictive power weaker or stronger in the aftermath of crises such as COVID-19? Our results combined suggest that online Google searches using selected keywords measuring different aspects of IPV are a powerful tool to track potential threats of IPV before and after global-level crises such as the current COVID-19 pandemic — with stronger predictive power post-crisis — while online searches help to predict actual violence only in post-crises scenarios.