STUDYMATE: A Centralised Study Note Web Application Enhanced by LLM for Technical Majors

Abstract

Cognitive overload presents a considerable obstacle for self-directed learners, who are required to manage and assimilate extensive amounts of study materials from many sources. StudyMate, a centralised web-based program, aims to lessen this difficulty by optimising the self-study process. The system incorporates Large Language Models (LLMs) to analyse submitted documents and offer intelligent study support, including summarisation, key point extraction, and flashcard generation, thereby alleviating the cognitive burden of digesting extensive information. StudyMate offers features including organised note management, an intuitive user interface, annotation capabilities, and a comprehensive text editor to enhance organisation, usability, and user engagement. This study concentrates on students in technical disciplines (IT, Computer Science, and Electrical and Electronics Engineering), as StudyMate is designed for self-directed learners, and the creator is well-acquainted with their specific academic requirements and obstacles. The system, developed under the Waterfall model, underwent evaluation via usability testing. LLM-based elements attained an average rating of 4.40 out of 5 for clarity and relevance in study assistance, whereas organisational and note-taking capabilities garnered a satisfaction score of 4.11 out of 5. The findings underscore StudyMate's capacity to alleviate cognitive stress and enhance the learning experience for autonomous learners, especially in technical fields.