Personalized Adaptive Learning Technologies Using Machine Learning
Year: 2024
Type: article
Study design: Systematic Review
Abstract: Personalized adaptive education systemshave used AI methods to circumvent theshortcomings of statically defined learningstyles (LSs). By automatically anddynamically mapping students' behavioralvariables to a specific LS, these systemsmaximize the individual learning process byusing algorithms from machine learning(ML). This tackles the difficulty ofcustomizing e-learning. We performed athorough systematic literature evaluationfrom 2015 to 2022 in response to the manyseminal research in the area as well as recentadvances in ML and AI. To find out what'snew and what's missing in the literature onLS models and potential ML approachesused for adaptive learning platforms that aretailored to each individual, we looked at themost influential scholarly articles. Thispaper's findings include an examination ofthe state of the art in this developing area,with a focus on the latest innovations inusing ML techniques to create smarter, moreadaptable online learning spaces that canautomatically identify students' learningstyles (LSs) and improve their learningexperiences. Topics such as researchinspiring platforms, e-learning LS modelidentification, assessment methodologies,and learning support services were alsoexamined. The findings showed that therewas a growing desire to find LSs utilizingmethods including artificial neural networks.Nevertheless, there is a lack of researchcomparing deep learning approaches in thisparticular setting. The results highlight theneed of doing more empirical research torecord the use and comparison of deeplearning algorithms for LS classification,with the goal of achieving greater flexibility
Authors: MR.CH SURESH, KARRI NAGA HEMANTH KUMAR
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: diamond
OpenAlex ID: W7217104645
