• Version
• Download 11
• File Size 488.09 KB
• File Count 1
• Create Date 12 June 2025
• Last Updated 12 June 2025

AI-Driven Understanding and Predicting Gadget Addiction Among Students

Keerthana K M1, Kruthi Shravya M2, Radhika R3, Dr Krishna Kumar P R4

*1,2 Student, Dept of CSE, SEA College of Engineering and Technology,Bangalore-49

3,4  Faculty, Dept of CSE, SEA College of Engineering and Technology,Bangalore-49

.

ABSTRACT:

In recent years, the overuse of electronic gadgets among students has emerged as a significant concern, affecting their academic performance, mental health, and social interactions. This study aims to understand and predict gadget addiction among students using Artificial Intelligence (AI) techniques, particularly machine learning models. By collecting behavioral, academic, and psychological data through structured surveys and usage logs, the study applies supervised learning algorithms such as Decision Trees, Random Forest, and Support Vector Machines to identify patterns and risk factors associated with gadget overuse. Feature selection techniques are used to determine the most influential variables contributing to addiction, such as screen time, sleep duration, academic stress, and social media usage. The models are evaluated using standard performance metrics like accuracy, precision, recall, and F1-score to ensure reliability and generalizability. The results demonstrate that AI-based predictive models can effectively identify at-risk students, providing a data-driven foundation for early intervention strategies. This research contributes to both educational and healthcare domains by offering insights into the behavioral aspects of gadget addiction and proposing intelligent systems for preventive care

Keywords: Electronic Gadget Addiction, Machine Learning, Random Forest Algorithm, Behavioral Factors, Psychological Factors, Screen Time, Social Media Usage, Sleep Disturbances, Addiction Prediction, Risk Classification, Early Intervention, Digital Well-Being.