Gendered Mental Health Stigma in Masked Language Models

By Inna Wanyin Lin, Lucille Njoo, Anjalie Field, Ashish Sharma, K. Reinecke, Tim Althoff, Yulia Tsvetkov. 2022

35 citations recorded by the source corpus.

Mental health stigma prevents many individuals from receiving the appropriate care, and social psychology studies have shown that mental health tends to be overlooked in men. In this work, we investigate gendered mental health stigma in masked language models. In doing so, we operationalize mental health stigma by developing a framework grounded in psychology research: we use clinical psychology literature to curate prompts, then evaluate the models’ propensity to generate gendered words. We find that masked language models capture societal stigma about gender in mental health: models are consistently more likely to predict female subjects than male in sentences about having a mental health condition (32% vs. 19%), and this disparity is exacerbated for sentences that indicate treatment-seeking behavior. Furthermore, we find that different models capture dimensions of stigma differently for men and women, associating stereotypes like anger, blame, and pity more with women with mental health conditions than with men. In showing the complex nuances of models’ gendered mental health stigma, we demonstrate that context and overlapping dimensions of identity are important considerations when assessing computational models’ social biases.

Subfields: Clinical Psychology, Public Health, Environmental and Occupational Health, Social Psychology, Large Language Models, AI Ethics, Fairness & Society

Citations in the corpus

• From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models (2023, unknown): “Probing Language Models For encoder-based language models, our approach of mask in-filling is widely adopted in numerous existing works (Petroni et al., 2019; Lin et al., 2022).”