Clustering multivariate data, per ESCI503 Multivariate Statistics (Dr. Rebecca Bunn, WWU)

Principle components analysis, per ESCI503 Multivariate Statistics (Dr. Rebecca Bunn, WWU)

Versión Final

Box's M and MANOVA analysis, per ESCI503 Multivariate Statistics (Dr. Rebecca Bunn, WWU)

Prueba

Graphing multivariate data, per ESCI503 Multivariate Statistics (Dr. Rebecca Bunn, WWU)

Recent advances in artificial intelligence (AI), particularly large language models (LLMs) and multimodal systems, present transformative opportunities for educational assessment. This PhD research proposes the development of an explainable, multimodal AI framework for automatically evaluating high-stakes student examinations, such as UK A-levels, which often contain complex textual responses, diagrams, and structured problem-solving steps. The project addresses key limitations of current automated assessment systems—including lack of transparency, inability to process visual content, and misalignment with pedagogical goals—by integrating state-of-the-art natural language processing, computer vision, and interpretability techniques. Developed in collaboration with AQA, the UK’s leading examination board, this research will produce an AI system capable of accurate scoring, personalized feedback generation, and human-understandable explanations of its decision-making process. The study employs a mixed-methods approach, combining technical development (e.g., fine-tuned LLMs, multimodal fusion architectures) with rigorous educational validation (e.g., expert reviews, fairness audits). Key innovations include novel methods for aligning AI assessments with curriculum standards, quantifying model explainability in educational contexts, and generating actionable feedback to support student learning. By bridging AI and education research, this work aims to establish best practices for trustworthy, pedagogically sound AI assessment systems while contributing open-source tools and datasets to the research community. The outcomes will provide critical insights for policymakers and educators seeking to leverage AI’s potential in high-stakes assessment environments—ensuring both technological advancement and educational equity.