2023/05/18 by Junwei Kuang, Kuang, Junwei, Jiaheng Xie +3 · 2 citations
Psychology · #Artificial Intelligence (cs.AI) #Computers and Society (cs.CY) #Digital Mental Health Interventions #FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (cs.LG) #Mental Health Research Topics #Mental Health via Writing #Quantitative Methods (q-bio.QM)
paper · pdf · doi:10.48550/arxiv.2305.13127
openalex publication_date 2023/05/18 · openalex created_date 2023/05/24 · openalex updated_date 2026/07/28
The early identification and intervention of latent depression are of significant societal importance for mental health governance. While current automated detection methods based on social media have shown progress, their decision-making processes often lack a clinically interpretable framework, particularly in capturing the duration and dynamic evolution of depressive symptoms. To address this, this study introduces a semantic parsing network integrated with multi-scale temporal prototype learning. The model detects depressive states by capturing temporal patterns and semantic prototypes in users' emotional expression, providing a duration-aware interpretation of underlying symptoms. Validated on a large-scale social media dataset, the model outperforms existing state-of-the-art methods. Analytical results indicate that the model can identify emotional expression patterns not systematically documented in traditional survey-based approaches, such as sustained narratives expressing admiration for an "alternative life." Further user evaluation demonstrates the model's superior interpretability compared to baseline methods. This research contributes a structurally transparent, clinically aligned framework for depression detection in social media to the information systems literature. In practice, the model can generate dynamic emotional profiles for social platform users, assisting in the targeted allocation of mental health support resources.