Detection of Digital Device Dependency in Adolescents using Decision Tree

The rapid proliferation of smartphones has revolutionized modern communication, but an over dependence on these devices has resulted in a growing psychological disorder known as NOMOPHOBIA (NO MObile PHone PhoBIA), which is linked to issues with social anxiety and self-esteem. In this article, nomophobia prediction using Decision Tree C4.5 is proposed. In the comparative study, other Machine Learning (ML) models such as Naïve Bayes (NB) Classifier, K-Nearest Neighbors (KNN), Multi-Layer Perceptron (MLP), and Support Vector Machine (SVM) are used to compare the performance with C4.5. All ML models are cross-validated using the K-fold cross-validation technique, and their hyperparameters are adjusted using the Random Search technique. Well-known classification performance evaluation criteria, including accuracy, recall, precision, F1, and Geometric Mean (GM), are used to assess the performance. It is found that the C4.5 outperforms other models for all the evaluation criteria.