Machine learning based psychotic behaviors prediction from Facebook status updates

Ali, M., Baqir, A., Sherazi, H. H. R., Hussain, A., Alshehri, A. H. and Imran, M. A. (2022) Machine learning based psychotic behaviors prediction from Facebook status updates. Computers, Materials and Continua, 72(2), pp. 2411-2472. (doi: 10.32604/cmc.2022.024704)

[img] Text
264059.pdf - Published Version
Available under License Creative Commons Attribution.

379kB

Abstract

With the advent of technological advancements and the widespread Internet connectivity during the last couple of decades, social media platforms (such as Facebook, Twitter, and Instagram) have consumed a large proportion of time in our daily lives. People tend to stay alive on their social media with recent updates, as it has become the primary source of interaction within social circles. Although social media platforms offer several remarkable features but are simultaneously prone to various critical vulnerabilities. Recent studies have revealed a strong correlation between the usage of social media and associated mental health issues consequently leading to depression, anxiety, suicide commitment, and mental disorder, particularly in the young adults who have excessively spent time on social media which necessitates a thorough psychological analysis of all these platforms. This study aims to exploit machine learning techniques for the classification of psychotic issues based on Facebook status updates. In this paper, we start with depression detection in the first instance and then expand on analyzing six other psychotic issues (e.g., depression, anxiety, psychopathic deviate, hypochondria, unrealistic, and hypomania) commonly found in adults due to extreme use of social media networks. To classify the psychotic issues with the user's mental state, we have employed different Machine Learning (ML) classifiers i.e., Random Forest (RF), Support Vector Machine (SVM), Naïve Bayes (NB), and K-Nearest Neighbor (KNN). The used ML models are trained and tested by using different combinations of features selection techniques. To observe the most suitable classifiers for psychotic issue classification, a cost-benefit function (sometimes termed as ‘Suitability’) has been used which combines the accuracy of the model with its execution time. The experimental evidence argues that RF outperforms its competitor classifiers with the unigram feature set.

Item Type:Articles
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Sherazi, Hafiz Husnain Raza and Imran, Professor Muhammad
Authors: Ali, M., Baqir, A., Sherazi, H. H. R., Hussain, A., Alshehri, A. H., and Imran, M. A.
College/School:College of Science and Engineering > School of Engineering > Autonomous Systems and Connectivity
Journal Name:Computers, Materials and Continua
Publisher:Tech Science Press
ISSN:1546-2218
ISSN (Online):1546-2226
Published Online:29 March 2022
Copyright Holders:Copyright © The Author(s) 2022
First Published:First published in Computers, Materials and Continua 72(2): 2411-2472
Publisher Policy:Reproduced under a Creative Commons licence
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record