Graph-Based Social Media Addiction Analysis and Its Impact on Academic Performance

View at publisher Summarise with VIRAT
Authors: Julius Irudayasamy, Aishwarya Kashyap
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Rapid growth of digital communication platforms has transformed the interaction patterns of students and significantly influenced behavioral dynamics within academic environments. Continuous engagement with social networking platforms has raised increasing concerns regarding social media addiction and its potential impact on learning behavior, attention span, and academic productivity. Effective understanding of this phenomenon requires analytical approaches capable of capturing the complex interaction structures present within digital communication systems. Graph theory and network science provide a powerful framework for modeling social media interactions as interconnected networks where users represent nodes and communication relationships represent edges. Structural properties of these interaction networks, including connectivity patterns, interaction density, and community clusters, reveal important behavioral signals associated with persistent online engagement. This book chapter presents a graph-based analytical perspective for investigating social media addiction and its relationship with academic performance among students. Integration of graph analytics with machine learning techniques enables extraction of network-based features that support predictive modeling of behavioral patterns within digital environments. Analysis of communication networks provides insights into engagement intensity, influence structures, and cluster formation that contribute to sustained digital participation. Behavioral patterns linked with continuous social media engagement influence study routines, concentration levels, and time allocation toward academic activities, ultimately affecting student academic outcomes. Network-based analytical frameworks offer deeper understanding of how interaction structures within digital communities reinforce engagement behaviors that influence educational performance. Insights derived from graph-based behavioral analysis contribute to the development of intelligent monitoring systems capable of identifying early indicators of excessive social media engagement and supporting intervention strategies for balanced technology usage in educational environments.

Fields of Study & Subjects

Impact of Technology on Adolescents Online Learning and Analytics Complex Network Analysis Techniques

Publication details

Pages
424–452
Publication date
19 March 2026
Language
EN
Document type
Book chapter