Detection and Sentiment Analysis Based on Mental Disorders Aspects Using Bidirectional Gated Recurrent Unit and Semantic Similarity

Mental disorders significantly impact daily life and are among the leading causes of suicide. Despite numerous studies on detecting mental disorders on social media, the focus has primarily been on identifying the presence or absence of indications in posts, with most studies concentrating solely on one specific mental disorder, particularly depression. There is a lack of comprehensive analysis of the detection results. Therefore, this study analyzes mental disorders in more detail by applying detection and sentiment analysis based on five aspects, namely ADHD (attention-deficit hyperactivity disorder), anxiety, bipolar, depression, and PTSD (post-traumatic stress disorder). The detection process utilizes bidirectional encoder representations from transformers (BERT) embedding and the bidirectional gated recurrent unit (BiGRU) model. Subsequently, aspect categorization employs semantic similarity, which assesses the resemblance between terms generated from hidden topic extraction via non-negative matrix factorization (NMF) and keywords linked to the five mental disorder aspects, extracted using a combination of term extraction methods. Additionally, sentiment classification leverages BERT embedding and the BiGRU model. The proposed method successfully identifies mental disorders, categorizes aspects, and classifies sentiment accurately. Optimal performance is achieved in mental disorders detection (0.9009) using BERT embedding + BiGRU, aspect categorization (0.8507) employing semantic similarity + BiGRU, and sentiment classification (0.8717) through BERT embedding + BiGRU. The analysis results unveil that texts related to mental disorders often convey negative sentiments, with the depression aspect exhibiting higher percentages of negative sentiment compared to other mental disorder aspects.