Journal of Embedded Systems, Security and Intelligent Systems
Vol 6, No 3 (2025): September 2025

Digital Distraction Analysis Using Machine Learning Models to Understand the Impact of Social Media and Risky Use on College Students as Gen Z

Mudarris, Mudarris (Unknown)
Anshari, Ahmad (Unknown)
Basirung, Muhammad Romario (Unknown)



Article Info

Publish Date
31 Aug 2025

Abstract

Research on digital distraction among Generation Z students shows that excessive social media use has significant impacts on academic, psychological, and social aspects. Gen Z, who on average own a smartphone before the age of 18 and spend 6–8 hours per day on digital platforms, are susceptible to impaired concentration and decreased academic achievement due to multitasking while studying. Analysis using the Extreme Gradient Boosting (XGBoost) machine learning model identified that the dominant factors influencing digital distraction are negative perceptions of mental health due to social media, feelings of guilt after excessive scrolling, and a tendency to lose time due to short content that offers instant gratification. The study also found that the 18–21 age group with a usage duration of more than six hours per day, especially before bed, is most at risk of experiencing sleep disorders, stress, and a decreased GPA. From a social aspect, the habit of spending time online reduces real interactions and weakens students' social skills. Thus, digital distraction is not only an individual problem, but also a collective one, necessitating interventions in the form of digital literacy education, strengthening study time management, limiting device use before bed, and providing alternative positive activities. This research confirms that the use of machine learning is able to provide an accurate predictive picture of risk patterns, so that the results are useful for academics, technology developers, policy makers, and educational institutions to design more targeted mitigation strategies for the most affected generations.

Copyrights © 2025






Journal Info

Abbrev

JESSI

Publisher

Subject

Computer Science & IT

Description

The Journal of Embedded System Security and Intelligent System (JESSI), ISSN/e-ISSN 2745-925X/2722-273X covers all topics of technology in the field of embedded system, computer and network security, and intelligence system as well as innovative and productive ideas related to emerging technology ...