StuLAC: An Adaptive LLM-Driven Framework for Scalable Student Feedback Analysis in Software-Driven Educational Systems.
Abstract
With the growing scalability challenges in higher education, automated student feedback analysis has become crucial for course evaluation and pedagogical improvements. However, traditional methods struggle to handle mixed sentiments, adapt to evolving feedback trends, and maintain computational efficiency. To address these challenges, we propose StuLAC, a Software Engineering-driven framework that integrates Large Language Models (LLMs) with Adaptive Template-Based Caching (ATC). StuLAC employs hierarchical matching for fine-grained classification and dynamically updates feedback templates through context-aware cache refinement. Empirical results on 80,000 student feedback entries demonstrate that StuLAC-generated summaries improve overall quality by 10.5% compared to manually generated reports, while also achieving faster processing times. Additionally, StuLAC attains an 86.4% accuracy and an 86.24% F1-score in sentiment detection. StuLAC's Feedback Summary Generation provides actionable insights that enhance data-driven decision-making in educational settings. These findings establish StuLAC as a scalable and adaptive solution for improving AIdriven educational feedback systems. Index Terms-LLM-Driven Feedback Analysis, Adaptive Caching in NLP, Educational Data Engineering, Scalable AI for Academic Evaluation, Software-Optimized Sentiment Classification I. I NTRODUCTION The rapid expansion of higher education has led to an exponential increase in student feedback data, necessitating scalable, automated analysis techniques [1]. Traditional feedback evaluation methods, often relying on manual review or rudimentary keyword-based sentiment analysis, struggle with handling large-scale, complex, and mixed-sentiment responses [2], [3]. Additionally, static classification models fail to adapt to evolving feedback patterns, leading to poor generalization and inefficiencies in educational decision-making [4]. The increasing volume and diversity of student feedback data pose significant challenges for conventional feedback analysis methods. Traditional approaches [1], [2], [5], [6], often based on keyword matching or basic sentiment analysis, struggle to effectively ca