Personalised Feedback Framework for Online Education Programmes Using Generative AI
Project Overview
The document explores the application of generative AI, specifically large language models like ChatGPT, in improving personalized feedback mechanisms within online education. It emphasizes the critical role of timely and tailored feedback in enhancing student learning experiences, particularly in online settings where conventional interactions are sparse. By integrating ChatGPT with educational content, the proposed framework offers nuanced and context-aware feedback, significantly increasing efficacy rates in assessments. This innovative approach not only aims to boost student engagement and understanding but also seeks to enhance academic performance by overcoming the common issue of delayed feedback linked to traditional manual grading processes. Overall, the findings showcase the transformative potential of generative AI in fostering a more responsive and effective educational environment.
Key Applications
Personalised Feedback Framework using ChatGPT
Context: Online education program for MSc in Cybersecurity students
Implementation: Integration of ChatGPT with Moodle LMS via API to provide automated feedback based on quiz performance.
Outcomes: Achieved an efficacy rate of 90% for open-ended questions and 100% for multiple-choice questions, highlighting the potential for AI to enhance educational feedback mechanisms.
Challenges: Challenges include ensuring the quality of feedback, maintaining accuracy in scoring, and the need for continuous improvement of the AI model to provide reliable feedback.
Implementation Barriers
Technical Barrier
The implementation of generative AI requires robust technical infrastructure and integration with existing Learning Management Systems (LMS), such as Moodle.
Proposed Solutions: Utilize cloud-based solutions like AWS to host AI systems and ensure compatibility with LMS platforms.
Educational Barrier
Variability in student understanding and capabilities can impact the effectiveness of AI-generated feedback. Continuous refinement of AI models based on student performance data is necessary to tailor feedback more effectively.
Proposed Solutions: Refine AI models continuously based on student performance data to enhance the effectiveness of feedback.
Ethical Barrier
Concerns regarding data privacy and the ethical implications of using AI in educational contexts necessitate the implementation of measures to protect student data.
Proposed Solutions: Implement anonymization techniques to protect student data and ensure compliance with data protection regulations.
Project Team
Ievgeniia Kuzminykh
Researcher
Tareita Nawaz
Researcher
Shihao Shenzhang
Researcher
Bogdan Ghita
Researcher
Jeffery Raphael
Researcher
Hannan Xiao
Researcher
Contact Information
For information about the paper, please contact the authors.
Authors: Ievgeniia Kuzminykh, Tareita Nawaz, Shihao Shenzhang, Bogdan Ghita, Jeffery Raphael, Hannan Xiao
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