Open AccessPsychological Analysis Using Social Media Data
Author(s) -
Shriya Gawade,
Riya Sawant,
Aakash Rathod,
Prof. Chhaya Dhavale
Publication year - 2022
Publication title -
international journal for research in applied science and engineering technology
Language(s) - English
Resource type - Journals
ISSN - 2321-9653
DOI - 10.22214/ijraset.2022.41510
Subject(s) - stress (linguistics) , scale (ratio) , computer science , artificial intelligence , support vector machine , mental state , social media , stability (learning theory) , perceived stress scale , machine learning , state (computer science) , natural language processing , psychology , applied psychology , linguistics , world wide web , algorithm , philosophy , physics , quantum mechanics
Mental Stress is an important aspect of our life that is given the least importance. We tend to ignore the fact that we need to be emotionally stable along with physical stability. To keep your mental state sound, we proposed this system where the psychological state of a person is being predicted. One such place where a person comes up and shares his/her thoughts, through texts is on social media with their friends. To detect such a state, we made use of NLP techniques accompanied by a reliable scale, the Perceived Stress Scale (PSS) developed by Cohen, Kamarck and Mermelstein. The huge texts were cleaned using text processing methods. In Machine Learning, there are many ways for sentimental analysis such: decision-based systems, Bayesian classifiers, support vector machines, neural networks and sample-based methods. We have performed sentimental analysis and in order to give the severity of the condition we made use of the Perceived Stress Scale (PSS). The model will be predicting whether the given text indicates stress or not and further classifies it as low, medium or high-level stress. Keywords: TF-IDF, Natural Language Processing (NLP), Stress, WordCloud, Perceived Stress Scale