Living with arsenic in the environment: An examination of current awareness of farmers in the Bengal basin using hybrid feature selection and machine learning

•A comprehensive arsenic awareness index (CAAI) was developed.•15 key awareness drivers (KADs) were derived using hybrid feature selection.•Bangladesh farmers were less aware of the food component of CAAI.•Stakeholder interventions and cropping practices influenced arsenic awareness.•CART and SCT models achieved an overall prediction accuracy of 84%. High levels of arsenic in drinking water and food materials continue to pose a global health challenge. Over 127 million people alone in Bangladesh (BD) and West Bengal (WB) state of India are exposed to elevated levels of arsenic in drinking water. Despite decades of research and outreach, arsenic awareness in communities continue to be low. Specifically, very few studies reported arsenic awareness among low-income farming communities. A comprehensive approach to assess arsenic awareness is a key step in identifying research and development priorities so that appropriate stakeholder engagement may be designed to tackle arsenic menace. In this study, we developed a comprehensive arsenic awareness index (CAAI) and identified key awareness drivers (KADs) of arsenic to help evaluate farmers’ preferences in dealing with arsenic in the environment. The CAAI and KADs were developed using a questionnaire survey in conjunction with ten machine learning (ML) models coupled with a hybrid feature selection approach. Two questionnaire surveys comprising of 73 questions covering health, water and community, and food were conducted in arsenic-affected areas of WB and BD. Comparison of CAAIs showed that the BD farmers were generally more arsenic-aware (CAAI = 7.7) than WB farmers (CAAI = 6.8). Interestingly, the reverse was true for the awareness linked to arsenic in the food chain. Application of hybrid feature selection identified 15 KADs, which included factors related to stakeholder interventions and cropping practices instead of commonly perceived factors such as age, gender and income. Among ML algorithms, classification and regression trees and single C5.0 tree could estimate CAAIs with an average accuracy of 84%. Both communities agreed on policy changes on water testing and clean water supply. The CAAI and KADs combination revealed a contrasting arsenic awareness between the two farming communities, albeit their cultural similarities. Specifically, our study shows the need for increasing awareness of risks through the food chain in BD, whereas awareness campaigns should be strengthened to raise overall awareness in