A machine learning web application for screening social anxiety disorder based on participants' emotion regulation (ML-SAD).

Abstract

Social Anxiety Disorder (SAD) is called a neglected anxiety disorder since people do not realize its existence and the need to receive further treatment. Thus, it is essential to develop widely available self-screening systems to assess individuals and direct those who need further evaluation to appropriate resources. Consequently, this paper presents a web application based on machine learning to screen for SAD. The Web application comprises 10 multimedia scenarios that people with SAD may struggle with. Four hundred and eighty-eight young adults (18-35 years old) in Persian-speaking society were asked to consider themselves in these scenarios and rank their competency in dealing with each specific situation, considering three emotion regulation strategies. Participants were divided into two groups, SAD and non-SAD, based on their diagnostic history of SAD and their self-assessment of their anxiety level. Multiple machine learning models were trained and evaluated, achieving an accuracy rate of more than 80% and demonstrating the effectiveness of the tool in identifying individuals who need additional support.