Personalized and Timely Feedback in Online Education: Enhancing Learning with Deep Learning and Large Language Models
Óscar Andrés Cuéllar Rojas, Manuel Contero, Mauricio Hincapié · Multimodal Technologies and Interaction · 2025
This study investigates an Adaptive Feedback System (AFS) that integrates deep learning (a recurrent neural network trained with historical student data) and GPT-4 to provide personalized feedback in a Digital Art course. In a quasi-experimental design, the intervention group (n = 42) received weekly feedback generated from model predictions, while the control group (n = 39) followed the same program without this intervention across four learning blocks or levels. The results revealed (1) a cumulative effect with a significant performance difference in the fourth learning block (+12.63 percentage points); (2) a reduction in performance disparities between students with varying levels of prior knowledge in the experimental group (−56.5%) versus an increase in the control group (+103.3%); (3) an “overcoming effect” where up to 42.9% of students surpassed negative performance predictions; and (4) a positive impact on active participation, especially in live class attendance (+30.21 points) and forum activity (+9.79 points). These findings demonstrate that integrating deep learning with LLMs can significantly improve learning outcomes in online educational environments, particularly for students with limited prior knowledge.