The Impact of Generative AI on Student Churn and the Future of Formal Education
Stephen Elbourn
TL;DR
The study addresses how Generative AI reshapes education and student churn by mining social-media signals rather than controlled experiments. It introduces a framework that combines ProcessGPT-based contextualisation with Deep Embedded Clustering of text representations, aided by contrastive learning and a KL-divergence objective, to identify emerging educational trends and churn drivers, denoted by metrics such as $ACC$ and $NMI$. Findings from a Twitter dataset (e.g., $50{,}000$ tweets) show AI-enabled personalised learning correlates with heightened engagement and entrepreneurial aspirations, informing policy and curriculum design. The work provides actionable insights for educators and policymakers and discusses future directions including data privacy, bias mitigation, platform diversity, and integration with educational systems.
Abstract
In the contemporary educational landscape, the advent of Generative Artificial Intelligence (AI) presents unprecedented opportunities for personalised learning, fundamentally challenging the traditional paradigms of education. This research explores the emerging trend where high school students, empowered by tailored educational experiences provided by Generative AI, opt to forgo traditional university degrees to pursue entrepreneurial ventures at a younger age. To understand and predict the future of education in the age of Generative AI, we employ a comprehensive methodology to analyse social media data. Our approach includes sentiment analysis to gauge public opinion, topic modelling to identify key themes and emerging trends, and user demographic analysis to understand the engagement of different age groups and regions. We also perform influencer analysis to identify key figures shaping the discourse and engagement metrics to measure the level of interest and interaction with AI-related educational content. Content analysis helps us to determine the types of content being shared and the prevalent narratives, while hashtag analysis reveals the connectivity of discussions. The temporal analysis tracks changes over time and identifies event-based spikes in discussions. The insights derived from this analysis include the acceptance and adoption of Generative AI in education, its impact on traditional education models, the influence on students' entrepreneurial ambitions, and the educational outcomes associated with AI-driven personalised learning. Additionally, we explore public sentiment towards policies and regulations and use predictive modelling to forecast future trends. This comprehensive social media analysis provides a nuanced understanding of the evolving educational landscape, offering valuable perspectives on the role of Generative AI in shaping the future of education.