Virtual Reality Game-Based Classification of Arachnophobia: A Two-Step Clustering Approach

Fear is a multifaceted emotion, challenging to define and assess accurately. Biologically, it is an innate response to threats, whereas psychologically, it is shaped by individual experiences and societal influences, sometimes evolving into specific phobias. One such phobia, arachnophobia (the fear of spiders), is particularly widespread and can vary widely in intensity among individuals. This paper presents a prototypal system that classifies the severity of arachnophobia using Machine Learning (ML) algorithms within a Virtual Reality (VR) game-based environment. The proposed system utilizes a two-stage clustering approach to analyze the behavioral data collected during VR exposure. Additionally, participants' self-reported fear levels are measured using the Spider Phobia Questionnaire (SPQ), to provide a comprehensive assessment. Preliminary results suggest that this method could be effectively used to classify arachnophobia intensity level, thus offering potential applications in both clinical settings and video games.