Chatbot for Mental Health Diagnosis Using NLP and Deep Learning

Abstract

In the discussion of health, human rights, and equality, mental disability and mental health care have been overlooked. This is puzzling considering that 8% of the world's population suffers from mental impairments, which are widespread. A scalable option that offers an interactive way to engage consumers in behavioral health interventions powered by artificial intelligence might be chatbots. Although several chatbots have showed early efficacy results that are encouraging, there is little data on how people really utilize these chatbots. Understanding chatbot usage trends for mental health issues such as depression, anxiety, stress, etc. provides a critical first step in enhancing chatbot design and revealing the advantages and disadvantages of the chatbots. In this paper a customized chatbot framework is proposed with a blended neural network design. The dataset used is completely scraped and prepared manually to inculcate the various mental health diseases and the appropriate responses provided by professionals. The dataset upon preprocessing undergoes various state of the art deep learning models such as Logistic Regression, Decision Tree, Random Forest, and Naive Bayes. Performance of the proposed mechanism is further compared with the simulated outcomes of the other existing models. Nevertheless to mention, the results show promising rate of efficiency.