Ratas framework: A comprehensive genai-based approach to rubric-based marking of real-world textual exams

Automated answer grading is a critical challenge in educational technology, with the potential to streamline assessment processes, ensure grading consistency, and provide timely feedback to students. However, existing approaches are often constrained to specific exam formats, lack interpretability in score assignment, and struggle with real-world applicability across diverse subjects and assessment types. To address these limitations, we introduce RATAS (Rubric Automated Tree-based Answer Scoring), a novel framework that leverages state-of-the-art generative AI models for rubric-based grading of textual responses. RATAS is designed to support a wide range of grading rubrics, enable subject-agnostic evaluation, and generate structured, explainable rationales for assigned scores. We formalize the automatic grading task through a mathematical framework tailored to rubric-based assessment and present an architecture capable of handling complex, real-world exam structures. To rigorously evaluate our approach, we construct a unique, contextualized dataset derived from real-world project-based courses, encompassing diverse response formats and varying levels of complexity. Empirical results demonstrate that RATAS achieves high reliability and accuracy in automated grading while providing interpretable feedback that enhances transparency for both students and nstructors.

The Impact of Generative AI on Student Churn and the Future of Formal Education

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.