Abstract
BackgroundMachine learning techniques can explore low prevalence data to offer insight into identification of factors associated with non-marital sexual violence (NMSV). NMSV in India is a health and human rights concern that disproportionately affects adolescents, is under-reported, and not well understood or addressed in the country.MethodsWe applied machine learning methods to retrospective cross-sectional data from India's nationally-representative National Family Health Survey 4, a demographic and health study conducted in 2015–16, which offers 4000+ variables as potential independent variables. We used Least Absolute Shrinkage and Selection Operator (lasso) or L-1 regularized logistic regression models as well as L-2 regularized logistic regression or ridge models; we conducted an iterative thematic analysis (ITA) of variables generated from a series of regularized models.FindingsThematic analysis of regularized models highlight that past exposure to violence was most predictive of NMSV, followed by geography, sexual behavior, and poor sexual and reproductive health knowledge. After these, indicators largely related to resources and autonomy (e.g., access to health services, and income generating) were associated with NMSV. Exploratory analysis with the subsample of never married adolescents 15–19 years old, a population with higher representation of recent NMSV, further emphasized the role of wealth and mobility as key correlates of NMSV, along with poor HIV knowledge, tobacco use, higher fertility preferences, and attitudes accepting of marital violence.InterpretationFindings indicate the validity of machine learning with iterative theme analysis (ITA) to identify factors associated with violence. Findings were consistent with prior work demonstrating associations between NMSV and other violence experiences, but also showed novel correlates such as lower SRH knowledge and service utilization and, for girls, norms and preferences suggesting more restrictive gender norms. Sexual and reproductive health, gender equity and safety focused interventions are important for addressing NMSV in India, particularly for adolescents.
Highlights
Population-based survey data is a cornerstone of public health research, allowing for examination of social and behavioural health indicators as well as clinical indicators for a more comprehensive analysis of public health risk factors and outcomes
Findings from our analysis with never married adolescent girls found the above noted correlates seen for the full sample, and found that poorer, rural, and marginalized caste girls were more likely to report non-marital sexual violence (NMSV), the latter finding seen in prior demographic research using these data, [12] again validating our machine learning approach
These findings build on prior evidence indicating the validity of machine learning for identification of potential risk factors for gender-based violence indicators using large-scale survey data with a wide set of variables
Summary
Population-based survey data is a cornerstone of public health research, allowing for examination of social and behavioural health indicators as well as clinical indicators for a more comprehensive analysis of public health risk factors and outcomes. This study tests application of machine learning to understand non-marital sexual violence (NMSV) among women in India, an outcome that has received less attention from quantitative research, in part due to low reporting. Machine learning allows for better consideration of a wider array of potential risk factors by employing algorithms to parse data, running through multiple iterations of variables in the dataset to learn the optimum model for explaining the outcome of focus [1,3,8]. Focus on the adolescent subsample provides information specific to younger unmarried girls, a population more vulnerable to NMSV, it allows for additional validation of the approach These findings can guide application of machine learning methods to understand issues of gender-based violence via use of large-scale survey data, and can provide insights for NMSV prevention and intervention in India
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
