Unveiling Frequently Co-Occurring Reasons of Attitudinal Acceptance of Intimate Partner Violence against Women: A Behavioral Data Science Perspective

Abstract

The results of gender equality indicators across the world in the form of prevalence of intimate partner violence (IPV) against women are striking and has thus drawn the attention of policy makers as well as necessitates the adoption of a comprehensive system to deal with. The situation of IPV in Pakistan is alarming. This study examines the acceptability attitude of women and men toward intimate partner violence against women through data science. It discovers and contrasts the frequently co-occurring reasons due to which husbands' behaviour of beating their wives is believed to be legitimate by both partners in the province of Punjab, Pakistan. Though the discovered frequently co-occurring reasons, such as "arguing with the husband and neglecting the children" altogether, are similar in both genders but the fraction of wives believing in such reasons are significantly greater than that of husbands. This psychological disparity across genders could help in identifying the social and cultural factors to whom this disparity is attributed. It is expected that the identified co-occurring groups of reasons would help to understand the problem to the next level and devise better strategies to mitigate them.

Keywords: behavioural data science (BDS); data mining; frequent itemset mining; gender-based violence; intimate partner violence (IPV); victimization.