Personalized and Timely Feedback in Online Education: Enhancing Learning with Deep Learning and Large Language Models

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 (<i>n</i> =...

Full description

Saved in:
Bibliographic Details
Main Authors: Óscar Cuéllar, Manuel Contero, Mauricio Hincapié
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Multimodal Technologies and Interaction
Subjects:
Online Access:https://www.mdpi.com/2414-4088/9/5/45
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850126703407398912
author Óscar Cuéllar
Manuel Contero
Mauricio Hincapié
author_facet Óscar Cuéllar
Manuel Contero
Mauricio Hincapié
author_sort Óscar Cuéllar
collection DOAJ
description 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 (<i>n</i> = 42) received weekly feedback generated from model predictions, while the control group (<i>n</i> = 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.
format Article
id doaj-art-b897262084464bb18ce147ae85cfcbac
institution OA Journals
issn 2414-4088
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Multimodal Technologies and Interaction
spelling doaj-art-b897262084464bb18ce147ae85cfcbac2025-08-20T02:33:51ZengMDPI AGMultimodal Technologies and Interaction2414-40882025-05-01954510.3390/mti9050045Personalized and Timely Feedback in Online Education: Enhancing Learning with Deep Learning and Large Language ModelsÓscar Cuéllar0Manuel Contero1Mauricio Hincapié2Instituto Universitario de Investigación en Tecnología Centrada en el Ser Humano (Human-Tech), Universitat Politècnica de València, 46022 Valencia, SpainInstituto Universitario de Investigación en Tecnología Centrada en el Ser Humano (Human-Tech), Universitat Politècnica de València, 46022 Valencia, SpainEscuela de Artes y Humanidades, Área Creación, Universidad EAFIT, Medellín 050022, ColombiaThis 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 (<i>n</i> = 42) received weekly feedback generated from model predictions, while the control group (<i>n</i> = 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.https://www.mdpi.com/2414-4088/9/5/45deep learninglarge language modelspersonalized feedbackassistive technologyeducational technologyperformance prediction
spellingShingle Óscar Cuéllar
Manuel Contero
Mauricio Hincapié
Personalized and Timely Feedback in Online Education: Enhancing Learning with Deep Learning and Large Language Models
Multimodal Technologies and Interaction
deep learning
large language models
personalized feedback
assistive technology
educational technology
performance prediction
title Personalized and Timely Feedback in Online Education: Enhancing Learning with Deep Learning and Large Language Models
title_full Personalized and Timely Feedback in Online Education: Enhancing Learning with Deep Learning and Large Language Models
title_fullStr Personalized and Timely Feedback in Online Education: Enhancing Learning with Deep Learning and Large Language Models
title_full_unstemmed Personalized and Timely Feedback in Online Education: Enhancing Learning with Deep Learning and Large Language Models
title_short Personalized and Timely Feedback in Online Education: Enhancing Learning with Deep Learning and Large Language Models
title_sort personalized and timely feedback in online education enhancing learning with deep learning and large language models
topic deep learning
large language models
personalized feedback
assistive technology
educational technology
performance prediction
url https://www.mdpi.com/2414-4088/9/5/45
work_keys_str_mv AT oscarcuellar personalizedandtimelyfeedbackinonlineeducationenhancinglearningwithdeeplearningandlargelanguagemodels
AT manuelcontero personalizedandtimelyfeedbackinonlineeducationenhancinglearningwithdeeplearningandlargelanguagemodels
AT mauriciohincapie personalizedandtimelyfeedbackinonlineeducationenhancinglearningwithdeeplearningandlargelanguagemodels