Fuzzy Memory Networks and Contextual Schemas: Enhancing ChatGPT Responses in a Personalized Educational System

Educational AI systems often do not employ proper sophistication techniques to enhance learner interactions, organize their contextual knowledge or even deliver personalized feedback. To address this gap, this paper seeks to reform the way ChatGPT supports learners by employing fuzzy memory retention and thematic clustering. To achieve this, three modules have been developed: (a) the Fuzzy Memory Module which models human memory retention using time decay fuzzy weights to assign relevance to user interactions, (b) the Schema Manager which then organizes these prioritized interactions into thematic clusters for structured contextual representation, and (c) the Response Generator which uses the output of the other two modules to provide feedback to ChatGPT by synthesizing personalized responses. The synergy of these three modules is a novel approach to intelligent and AI tutoring that enhances the output of ChatGPT to learners for a more personalized learning experience. The system was evaluated by 120 undergraduate students in the course of Java programming, and the results are very promising, showing memory retrieval accuracy, schema relevance and personalized response quality. The results also show the system outperforms traditional methods in delivering adaptive and contextually enriched educational feedback.