Mental Health Stigma
Mental health stigma significantly hinders access to care and recovery, prompting research focused on identifying and mitigating its manifestations across various platforms, particularly online. Current studies leverage large language models (LLMs) and machine learning algorithms to analyze text data from social media, aiming to detect stigmatizing language and develop methods for its remediation, including the creation of de-stigmatizing responses. This work highlights the complex interplay between language, bias, and social perception, offering valuable insights for improving mental health support and informing the development of more equitable AI systems.
Papers
Enhancing Suicide Risk Detection on Social Media through Semi-Supervised Deep Label Smoothing
Matthew Squires, Xiaohui Tao, Soman Elangovan, U Rajendra Acharya, Raj Gururajan, Haoran Xie, Xujuan Zhou
Exploring the Potential of Human-LLM Synergy in Advancing Qualitative Analysis: A Case Study on Mental-Illness Stigma
Han Meng, Yitian Yang, Yunan Li, Jungup Lee, Yi-Chieh Lee