Depression and related mental disorders are on the rise, significantly deteriorating individuals' daily lives. Depression and anxiety disorders often occur frequently and remain untreated, as people tend to face stress from various factors such as education, family issues, and social problems. The impacts of depression include effects on mental health, education, work, and social relationships. To address these issues, we aim to develop effective tools using Natural Language Processing (NLP) models, such as BERT (Bidirectional Encoder Representations from Transformers) or LDA (Latent Dirichlet Allocation). These tools can be applied to text analysis, enhancing the accuracy and efficiency of detecting and classifying depression. This approach aims to analyze trends and the context of text mentioning depression from sources like social media, medical articles, or online forums. The findings from using LDA or BERTopic can be utilized to develop tools that help analyze and identify types of depression from texts posted or written by users.

Nantapong Keandoungchun