Depression detection aims to detect the depression state of the sufferer using their shared information on the social media platform. Binary depression classification deals with whether the sufferer is depressed or not whereas, multiclass depression classification focus on classifying the depression state into different levels. Multi-class depression classification aims to classify the different depression levels and also categorize the depression disorders. Categorization of depression level is a crucial task, and it is necessary to analyze the patterns of shared user information closely.
Aspect level extraction identifies and extracts relevant depressive features from the text information shared by the user. Aspect-based depressive feature extraction classifies the in-depth categorization of the depressive level of the suffers that helps them to prevent future disorders. Aspect-based depressive feature extraction improves the performance and accuracy of the multi-class depression classification model.