Exploring nomophobia among university students: Identifying risk factors, correlates, and predictive insights through machine learning

Nomophobia is a term describing a growing fear in today’s world, the fear of being without a mobile device or beyond mobile phone contact. It is the biggest non-drug addiction of the 21st century and is mainly affected by teen-aged students. Those experiencing nomophobia may feel a sense of panic, anxiety, or distress when they are separated from their mobile phones. This work uses different statistical tools to identify the risk factor of nomophobia and machine learning techniques to propose a fresh way to measure and understand nomophobia. To create a predictive model for nomophobia, we gathered information from a broad sample (n = 357) of smartphone users and used a variety of machine learning methods. Using a questionnaire on 17 different factors and performing a statistically significant test (p<0.05) and ordinal logistic regression analysis on respondents age, level of education, CGPA, self-evaluation, per-day mobile phone usage, and use of media, we can recognize the most important features causative of nomophobia. The context of maximum phone usage is an important feature that highly affects nomophobia. About 201 respondents are at a moderate level. To develop a predictive model, decision tree (DT), random forest (RF), Gaussian Naïve Bayes (NB), and support vector machine (SVM) are utilized in this study for recognition of nomophobia addiction. Proposing an ensemble method to refine the predictive performance. From the analysis, we have found that the SVM feature selector with ensemble algorithm has classified the extent of smartphone addiction with a 57% accuracy rate. Our findings show that nomophobia tendencies can be accurately captured and predicted by machine learning approaches. The model distinguished between students who had symptoms of nomophobia and those who did not with remarkable accuracy. This study of machine learning-based methods presents a viable tool for diagnosing and treating nomophobia in students, eventually assisting in the creation of focused interventions and preventive measures.