Implementation of machine learning techniques for depression in text messages: a survey

Abstract

Depression is a disease or problem associated with high levels of stress seen in humans. It is uncomfortable in talking to parents, psychologists, and healthcare professionals in general. So a virtual platform is much more suitable for sharing your emotions, for example, a chatbot that provides the user with a comfort zone, acting as a friend or well-wisher. Extracting and identifying emotions from text messages to detect depressive mood is a challenging task because it involves removing natural language ambiguities. Over the past decade, researchers have proposed various state-ofthe- art methods for detecting depressive moods in text. This paper aims to analyze such methods and present a comparison based on detection accuracy. The virtual platform provides an end-user interface for communication. The system understands the meaning and context of a sentence using Natural Language Processing (NLP), word embedding, and machine learning techniques. NLP does the preprocessing and extracts the mental health-related keywords. Word embedding converts the extracted keywords into embedding vectors that can be understood by Machine learning algorithms, it can also analyze and extract users' feelings by examining and calculating levels of depression and classifying the user as depressed or not. This paper showed that the support vector machine is the preferred algorithm over other machine learning algorithms and provides higher accuracy.