Published Paper Details:

Electronic gadget addiction has emerged as a pressing concern among students, with far-reaching consequences for their mental health, academic performance, and social relationships. The pervasive nature of gadget addiction, fueled by the widespread availability and accessibility of electronic devices, has led to a growing need for effective predictive models and targeted interventions. This study addresses this critical need by developing a machine learning model to predict gadget addiction among students aged 18-25, leveraging demographic, behavioral, and psychological characteristics. The predictive model, built using decision trees and random forest algorithms, identifies screen time, frequency of gadget use, anxiety, and depression as significant predictors of gadget addiction. The random forest algorithm emerges as the most accurate predictive model, underscoring its potential in identifying high-risk students. These findings have profound implications for educators, counselors, and parents, enabling them to pinpoint vulnerable students and provide personalized support. The predictive model developed in this study can serve as a valuable tool in promoting students' well-being and productivity. By identifying high-risk students, educators and counselors can design targeted interventions, such as counseling sessions, workshops, and awareness programs, to mitigate gadget addiction. Parents can also utilize the model to monitor their children's gadget use and provide guidance on responsible technology habits. Moreover, this study's findings can inform the development of evidence-based policies and programs aimed at reducing gadget addiction among students. Educational institutions can establish guidelines for responsible gadget use, incorporate digital literacy into their curricula, and provide resources for students struggling with gadget addiction.