Emotionally Enriched Feedback via Generative AI
Project Overview
The document investigates the role of generative AI in education, particularly focusing on its application in providing emotionally enriched feedback to enhance student engagement and emotional responses in higher education. The findings reveal that feedback infused with motivational elements effectively mitigates negative emotions, such as anger, among students, although it does not significantly influence overall engagement levels or the quality of academic work produced. This suggests that while generative AI can play a crucial role in improving the feedback experience by considering emotional factors, its impact on engagement and performance may be limited. The research underscores the necessity of integrating emotional considerations into the design of educational technologies, highlighting the potential of generative AI to transform the feedback process and enrich the learning environment. Overall, the study illustrates that while generative AI offers promising avenues for enhancing educational feedback, further exploration is needed to maximize its effectiveness in promoting student engagement and academic success.
Key Applications
Emotionally enriched AI feedback
Context: Higher education, specifically in a first-year engineering course with 425 students
Implementation: Feedback generated by AI was enhanced with positive elements like praise and visual aids (emojis). The experimental group received this emotionally enriched feedback, while the control group received neutral feedback.
Outcomes: Students perceived the emotionally enriched feedback as more beneficial and reported lower levels of negative emotions, particularly anger. However, there was no significant improvement in engagement levels or the quality of student work.
Challenges: While students reported benefits from the emotionally enriched feedback, it did not significantly enhance engagement with the feedback or improve work quality.
Implementation Barriers
Technical Barrier
The lack of real-time emotional measurement tools limited the ability to provide personalized feedback based on students' immediate emotional states.
Proposed Solutions: Future research should focus on developing tools for measuring emotions in real-time and integrating them into feedback systems.
Perception Barrier
Some students felt that the AI feedback did not always accurately capture the tone they intended in their work, leading to confusion and frustration.
Proposed Solutions: Improving the AI's ability to understand context and tone in feedback could enhance its effectiveness.
Project Team
Omar Alsaiari
Researcher
Nilufar Baghaei
Researcher
Hatim Lahza
Researcher
Jason Lodge
Researcher
Marie Boden
Researcher
Hassan Khosravi
Researcher
Contact Information
For information about the paper, please contact the authors.
Authors: Omar Alsaiari, Nilufar Baghaei, Hatim Lahza, Jason Lodge, Marie Boden, Hassan Khosravi
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