[Paper Review] Transformative Influence of LLM and AI Tools in Student Social Media Engagement: Analyzing Personalization, Communication Efficiency, and Collaborative Learning

Masoud Bashiri, Kamran Kowsari|arXiv (Cornell University)|Jun 15, 2024

Artificial Intelligence in Healthcare and EducationMedicine3 citations

TL;DR

This paper investigates how Large Language Models (LLMs) and AI tools transform student engagement on educational social media platforms like UniversityCube, enhancing personalization, communication efficiency, and collaborative learning. Using statistical analysis and case studies on real user data, it finds that AI integration boosts academic performance, critical thinking, and retention, with educational networks showing rising usage trends (R² = 0.82) and higher seasonal variability (CV = 0.51) compared to entertainment networks.

ABSTRACT

The advent of Large Language Models (LLMs) and Artificial Intelligence (AI) tools has revolutionized various facets of our lives, particularly in the realm of social media. For students, these advancements have unlocked unprecedented opportunities for learning, collaboration, and personal growth. AI-driven applications are transforming how students interact with social media, offering personalized content and recommendations, and enabling smarter, more efficient communication. Recent studies utilizing data from UniversityCube underscore the profound impact of AI tools on students' academic and social experiences. These studies reveal that students engaging with AI-enhanced social media platforms report higher academic performance, enhanced critical thinking skills, and increased engagement in collaborative projects. Moreover, AI tools assist in filtering out distracting content, allowing students to concentrate more on educational materials and pertinent discussions. The integration of LLMs in social media has further facilitated improved peer-to-peer communication and mentorship opportunities. AI algorithms effectively match students based on shared academic interests and career goals, fostering a supportive and intellectually stimulating online community, thereby contributing to increased student satisfaction and retention rates. In this article, we delve into the data provided by UniversityCube to explore how LLMs and AI tools are specifically transforming social media for students. Through case studies and statistical analyses, we offer a comprehensive understanding of the educational and social benefits these technologies offer. Our exploration highlights the potential of AI-driven tools to create a more enriched, efficient, and supportive educational environment for students in the digital age.

Motivation & Objective

• To analyze the impact of LLMs and AI tools on student social media engagement in educational contexts.
• To examine how personalization, communication efficiency, and collaborative learning are enhanced through AI integration on platforms like UniversityCube.
• To identify usage patterns and long-term trends in educational versus entertainment social networks among students.
• To evaluate the role of AI in improving academic performance, critical thinking, and student retention through data-driven analysis.
• To provide actionable insights for educators and platform developers on optimizing AI-driven educational tools.

Proposed method

• Utilized real-world usage data from the UniversityCube educational social network platform.
• Applied statistical techniques including time series analysis to detect seasonal and long-term usage trends.
• Calculated coefficient of variation (CV = σ/μ) to quantify seasonal variability in network usage.
• Conducted linear trend analysis to assess changes in usage over time, reporting R² values for entertainment (0.75) and educational (0.82) networks.
• Used principal component analysis (PCA) to identify key factors driving user engagement and feature relationships.
• Integrated case studies and empirical data to link AI tool usage with academic and social outcomes.

Figure 1 : Student Usage of Social network in monthly bases

Experimental results

Research questions

• RQ1 How do LLMs and AI tools influence personalization in student social media engagement?
• RQ2 To what extent do AI tools improve communication efficiency and collaborative learning in educational social networks?
• RQ3 What are the long-term and seasonal usage trends in educational versus entertainment social networks among students?
• RQ4 How does AI-driven content filtering affect student focus on academic materials?
• RQ5 What is the relationship between AI-enhanced platform features and student academic performance and retention?

Key findings

• Educational social networks exhibit higher seasonal variability (CV = 0.51) compared to entertainment networks (CV = 0.34), indicating more pronounced shifts in student engagement.
• Educational networks show a strong positive linear trend in usage (R² = 0.82), while entertainment networks display a declining trend (R² = 0.75).
• Students using AI-enhanced platforms report higher academic performance, improved critical thinking skills, and increased engagement in collaborative projects.
• AI tools effectively filter distracting content, allowing students to focus more on educational materials and relevant discussions.
• AI-driven matching algorithms based on academic interests and career goals foster a more supportive and intellectually stimulating online community, contributing to higher student satisfaction and retention.
• The integration of LLMs and AI tools in social media platforms enables personalized content recommendations, real-time feedback, and AI-powered visualizations that enhance comprehension and learning efficiency.

Figure 2 : Student Usage of Social network in Yearly bases