Depression Sentiment Analysis using Machine Learning Techniques:A Review

Depression is one of the habitual psychological well-being diseases and a significant number of depressed individuals end their lives. People suffering from depression don’t ask for help from psychological doctors due to hesitation or unawareness about depression that causes a delay in diagnosis and treatment. A lot of people share their opinions and emotions on social networking sites. Several studies of social networking site posts related to depression rely upon Facebook, Twitter, Blogs, and other social networks because they help in recording behavioral attributes which are related to a person’s thinking, socialization, communication, etc. Datasets from various social networking sites are useful for depression sentiment analysis. Various machine learning and deep learning techniques like Naïve Bayes, maximum entropy, Support Vector Machine (SVM), and Decision Tree classifiers neural networks, deep neural networks, recurrent neural networks etc. have been used for depression detection. This paper presents a review on sentiment analysis performed on social media platforms for detection of depression The datasets utilized are also discussed. A comparative analysis of existing work in the area of depression detection is provided to get a clear understanding of the techniques used. Finally, challenges and future work which can be done in the field of depression detection is also discussed