Depression can be defined as a mental health disorder characterized by persistently depressed mood, loss of interest in activities, causing significant impairment in daily life. Technical intervention to screen depression in non-clinical population which records, classify depression on the basis of severity and provide features or predictors that discriminate the classification of depression among non-clinical population comprising of college students is the main area of the study. Beck Depression Inventory – II (BDI-II), as per Diagnostic and Statistical manual of Mental disorder (DSM IV) is used to screen depression and its severity. Indicators are determined on the basis of how well the features or predictors can discriminate the classes of depression severity. Providing quality indicators which help in supporting the process can be considered as symptoms for screening depression. Descriptive analytics is used in order to find the underlying pattern of the responses captured, factor analysis groups variables on the basis of correlation between patterns of the responses to reduce dimension. The approach for supervised descriptive analysis method that takes BDI-II questions as features and refine the features using information gain and linear discriminant analysis as feature selection algorithm. The classification of severity of depression is done using Support vector machine (SVM)..
Read full abstract