An Intelligent System for Detection of Mental Stress Using Machine Learning

Abstract

Tens of millions of people experience depression each year, yet only a small percentage of them receive timely, effective therapy. So, it is essential to timely identify human tension and relaxation through social media. It is crucial to identify and control stress before it becomes a serious issue. Daily posts to blogs, discussion forums, and social networking sites total in millions of casual communications. This essay outlines a method for identifying stress using data from social media networking sites like Twitter. Using sentiment analysis to uncover emotions or feelings about daily life, this research proposes a method to find expressions of tension and relaxation in tweeter datasets. Sentiment analysis automatically extracts information about sentiment from text. Here, sentiment strength from the informal English language is extracted using the TensiStrength framework for sentiment strength identification on social networking sites. TensiStrength is a technology that analyzes social media text messages to identify the levels of tension and relaxation that are being conveyed. With the purpose of identifying both overt and covert signs of tension or relaxation, TensiStrength employs a linguistic approach and a set of rules. According to the strength scale from -5 to +5, this categorizes both pleasant and negative emotions. Stressed and relaxed sentences from the dialogue are both taken into consideration. TensiStrength is a robust system that may be used in a number of social media scenarios. TensiStrength's efficacy is based on the content of the tweets. Humans have the innate capacity to distinguish between the various meanings of a word in a specific situation, but machines just function as directed. Word Sense Disambiguation is the main flaw in machine translation. A single word might really have several different meanings or "senses," as the case may be. Pre-processing analyzes part-of-speech disambiguation, and the suggested technique uses unigrams, bigrams, and trigrams to get around WSD's shortcomings and get better results with ambiguous terms. SVM with Ngram provides a superior outcome in this case. Recall is 67% and Precision is 65%. But, this technique's primary goal is to identify the explicit and implicit levels of tension and relaxation reflected in tweets.