DEPRESSION DETECTION USING NATURAL LANGUAGE PROCESSING

Abstract

Depression is viewed as the largest contributor lo global disability and a major reason for suicide. It has an impact on the language usage reflected in the written text. The key objective of our study is to examine Redd it users’ posts to detect any factors that may reveal the depression attitudes of relevant online users. For such purpose, we employ the Natural Language Processing (NLP) techniques and machine learning approaches to train the data and evaluate the efficiency of our proposed method. We identify a lexicon ofterms that are more common among depressed accounts. This application utilizes the RNN strategies to build up the application. The neural conversation model can cater to a variety of requests, as it generates the responses word by word as opposed to using canned responses. The hybrid system shows significant improvements over the existing baseline system ofrule-based approach and caters to complex queries with a domain-restricted neural model. Many various models ofNN are examined, and LSTM calculation was utilized in this application as its fit for shaping portrayals ofthe highlights which is inward in order. Automatic detection of depression has attracted increasing attention from researchers in psychology, computer science, linguistics, and related disciplines. As a result, promising depression detection systems have been reported. This paper surveys these efforts by presenting the first cross-modal review ofdepression detection systems and discusses best practices and most promising approaches to this task. This framework is intended to tweak the organization for an individual client. Proposals for future turn of events and ends are additionally remembered for the report.