Indirect Identification of Psychosocial Risks from Natural Language
This addresses the challenge of screening for stigmatized health risks in perinatal care, offering incremental improvements through indirect questioning to complement existing methods.
The study tackled the problem of identifying perinatal psychosocial risks like depression and intimate partner violence by analyzing indirect methods such as diary entries and multiple-choice questions, finding that text-based features performed almost as well as direct questions for depression prediction but were less effective for violence detection.
During the perinatal period, psychosocial health risks, including depression and intimate partner violence, are associated with serious adverse health outcomes for parents and children. To appropriately intervene, healthcare professionals must first identify those at risk, yet stigma often prevents people from directly disclosing the information needed to prompt an assessment. We examine indirect methods of eliciting and analyzing information that could indicate psychosocial risks. Short diary entries by peripartum women exhibit thematic patterns, extracted by topic modeling, and emotional perspective, drawn from dictionary-informed sentiment features. Using these features, we use regularized regression to predict screening measures of depression and psychological aggression by an intimate partner. Journal text entries quantified through topic models and sentiment features show promise for depression prediction, with performance almost as good as closed-form questions. Text-based features were less useful for prediction of intimate partner violence, but moderately indirect multiple-choice questioning allowed for detection without explicit disclosure. Both methods may serve as an initial or complementary screening approach to detecting stigmatized risks.