Skip to main content Skip to navigation

Enhancing Higher Education with Generative AI: A Multimodal Approach for Personalised Learning

Project Overview

The document explores the integration of Generative AI (GenAI) in higher education, focusing on the development of a multimodal chatbot that leverages the ChatGPT API for text-based interactions and Google Bard for image analysis and converting diagrams to code. This innovative tool effectively addresses educational queries and includes a file-based analyzer designed to provide educators with insights derived from student feedback. The research underscores the importance of personalized learning experiences and outlines the significant advantages of GenAI in improving teaching and learning outcomes. By facilitating tailored educational support and enhancing the interaction between students and educators, GenAI demonstrates its potential to transform the educational landscape and foster a more engaging and efficient learning environment.

Key Applications

AI-driven feedback and interaction analysis

Context: Higher education, targeting undergraduate students and educators for personalized learning experiences and efficient feedback analysis.

Implementation: Developed using the ChatGPT API for text interactions, and Google Bard for image analysis, sentiment, and emotion analysis of course feedback and student interactions. This includes capabilities for analyzing course evaluation reports and converting diagrams to code.

Outcomes: ['Improved engagement and adaptability in teaching.', 'Enhanced understanding of student feedback.', 'Improved efficiency in analyzing large volumes of evaluations.']

Challenges: ['Technical difficulties in accurately converting diagrams to code.', 'Managing diverse document formats.', 'Ensuring accurate sentiment analysis.']

Implementation Barriers

Technical Barrier

Challenges in precise image recognition for converting diagrams to code.

Proposed Solutions: Advancements in image recognition technologies and standardizing diagram formats.

Functional Barrier

Lack of functionality in existing educational tools to support file input.

Proposed Solutions: Development of tools that allow students and teachers to upload various course-related documents.

Project Team

Johnny Chan

Researcher

Yuming Li

Researcher

Contact Information

For information about the paper, please contact the authors.

Authors: Johnny Chan, Yuming Li

Source Publication: View Original PaperLink opens in a new window

Project Contact: Dr. Jianhua Yang

LLM Model Version: gpt-4o-mini-2024-07-18

Analysis Provider: Openai

Let us know you agree to cookies