Domestic Violence

Domestic violence research is increasingly focusing on understanding its multifaceted nature, moving beyond the traditionally emphasized female victimization to include male victims and exploring diverse contexts. Current studies utilize machine learning techniques, including convolutional neural networks, ensemble models (like CatBoost and RoBERTa), and explainable AI methods (SHAP and LIME), to analyze data from various sources, such as social media and mobile phone location data, to identify risk factors and improve prediction models. This work is significant for informing the development of targeted interventions and policies aimed at preventing and mitigating domestic violence, ultimately improving public health and safety. The use of readily available data sources, like anonymized mobile phone location data, offers promising avenues for large-scale analysis and prediction.

Papers

March 22, 2024

Analyzing Male Domestic Violence through Exploratory Data Analysis and Explainable Machine Learning Insights
Md Abrar Jahin, Saleh Akram Naife, Fatema Tuj Johora Lima, M. F. Mridha, Jungpil Shin
Exploratory Data Analysis Male Victim Domestic Violence

October 6, 2022

Feasibility on Detecting Door Slamming towards Monitoring Early Signs of Domestic Violence
Osian Morgan, Hakan Kayan, Charith Perera
Convolutional Neural Network TinyML Model Task Feasibility Audio Data Early Stage Door Status Domestic Violence

September 22, 2022

AIR-JPMC@SMM4H'22: Classifying Self-Reported Intimate Partner Violence in Tweets with Multiple BERT-based Models
Alec Candidato, Akshat Gupta, Xiaomo Liu, Sameena Shah
BERT Model Twitter Resource Twitter Tweet Tweet Text RoBERTa Model Domestic Violence

February 26, 2022

The role of alcohol outlet visits derived from mobile phone location data in enhancing domestic violence prediction at the neighborhood level
Ting Chang, Yingjie Hu, Dane Taylor, Brian M. Quigley
Integral Role Neighborhood Level Location Data Alcohol Consumption Domestic Violence

Domestic Violence

Papers

Analyzing Male Domestic Violence through Exploratory Data Analysis and Explainable Machine Learning Insights

Feasibility on Detecting Door Slamming towards Monitoring Early Signs of Domestic Violence

AIR-JPMC@SMM4H'22: Classifying Self-Reported Intimate Partner Violence in Tweets with Multiple BERT-based Models

The role of alcohol outlet visits derived from mobile phone location data in enhancing domestic violence prediction at the neighborhood level