Evaluating and predicting social behavior of arsenic affected communities: Towards developing arsenic resilient society

This study uses six machine learning (ML) algorithms to evaluate and predict individuals' social resilience towards arsenicosis-affected people in an arsenic-risk society of rural India. Over 50% of the surveyed communities were found to be resilient towards arsenicosis patients. Logistic regression with inbuilt cross-validation (LRCV) model scored the highest accuracy (76%), followed by Gaussian distribution-based naïve Bayes (GNB) model (74%), C-Support Vector (SVC) (74%), K-neighbors (Kn) (73%), Random Forest (RF) (72%), and Decision Tree (DT) (67%). The LRCV also scored the highest kappa value of 0.52, followed by GNB (0.48), SVC (0.48), Kn (0.46), RF (0.42), and DT (0.31). Caste, education, occupation, housing status, sanitation behaviors, trust in others, non-profit and private organizations, social capital, and awareness played a key role in shaping social resilience towards arsenicosis patients. The authors opine that LRCV and GNB could be promising methods to develop models on similar data generated from a risk society.