The IUP Journal of Computer Sciences
Deep Learning Techniques for Detecting Depression Signs from Text Messages: A Review

Article Details
Pub. Date : Oct, 2022
Product Name : The IUP Journal of Computer Sciences
Product Type : Article
Product Code : IJCS021022
Author Name : Divya Dewangan, Smita Selot and Sreejit Panicker
Availability : YES
Subject/Domain : Management
Download Format : PDF Format
No. of Pages : 25



Depression is a mental disorder and is deeply self-damaging. A depressed person not only hurts himself but also causes more damage. The affected people show different behaviors and actions. As new technologies are introduced and the virtual environments are improving, intelligent technologies have replaced important people like therapists. Since the last decade, various state-of-the-art techniques have been proposed by researchers for the detection of depression moods in text messages. The paper reviews and analyzes various Deep Learning models and techniques that have already been utilized in earlier research and presents a comparison based on their accuracy of detection. The study observes that the transformer model and deep hybrid neural network model have arrived as the state-of-the-art and these are highly superior and provide much better accuracy compared to other algorithms.


According to WHO, there are over approximately 280 million people in the world suffering from depressive disorder as of 2021, and it is a leading cause of disability, and over 700,000 people die every year due to severe major depressive disorder. It can cause depressed people to suffer from a persistent feeling of guilt, sadness and hopelessness, and lose interest in activities they once enjoyed. Apart from the sentimental problems caused by depression, individuals may also face physical problems such as chronic pain or digestive issues (World Health Organization, 2021).

Based on the Diagnostic and Statistical Manual of Mental Disorders (DSM-5) Diagnostic criteria, the individual must be dealing with five or more symptoms during the same 2-week period and at least one of the symptoms should be either (1) depressed mood or (2) loss of interest (Truschel, 2022).

One of the most important and impactful issues that the application of technology and data can address is access to healthcare. Many studies have shown that treating patients with online psychotherapy is as effective as face-to-face psychotherapy interviews.


Deep Learning techniques, Depression detection, Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), Long Short Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), Bidirectional Encoder Representations from Transformers (BERT), Deep hybrid neural network