What is Stigma Attributed to? A Theory-Grounded, Expert-Annotated Interview Corpus for Demystifying Mental-Health Stigma
This work addresses the pervasive social problem of mental-health stigma, which hampers treatment-seeking and recovery, by providing a new dataset for computational detection and neutralization, though it is incremental as it builds on existing methods with new data.
The authors tackled the problem of limited resources for training neural models to classify mental-health stigma by creating an expert-annotated, theory-informed corpus of 4,141 interview snippets from 684 participants. They benchmarked state-of-the-art models and identified challenges in stigma detection, making the dataset openly available to facilitate research.
Mental-health stigma remains a pervasive social problem that hampers treatment-seeking and recovery. Existing resources for training neural models to finely classify such stigma are limited, relying primarily on social-media or synthetic data without theoretical underpinnings. To remedy this gap, we present an expert-annotated, theory-informed corpus of human-chatbot interviews, comprising 4,141 snippets from 684 participants with documented socio-cultural backgrounds. Our experiments benchmark state-of-the-art neural models and empirically unpack the challenges of stigma detection. This dataset can facilitate research on computationally detecting, neutralizing, and counteracting mental-health stigma. Our corpus is openly available at https://github.com/HanMeng2004/Mental-Health-Stigma-Interview-Corpus.