Open AccessTracing Knowledge of Student based on Academic Knowledge with Machine Learning and Deep Learning
Author(s) -
Jiayu Hu,
Mingyi Li,
Huimin Mao,
Cheng Liu
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2010/1/012021
Subject(s) - pace , restructuring , tracing , equity (law) , shut down , artificial intelligence , computer science , mathematics education , political science , psychology , law , geography , geodesy , operating system
Because the number of students not attending school is expanding at an alarming pace, and because of the COVID-19 epidemic, 102 countries have implemented nationwide closures to conduct local shut-downs and temporarily close schools. This slowed down learning possibilities and intellectual growth even more. Every country’s equity disparities may widen. As a result, we must restructure our educational system so that students can gain correct knowledge and teachers can track how much each student has learned. As a result, Machine Learning and Deep Learning are the most effective solutions for this type of problem. As a result, we’re releasing a method for tackling this challenge using Tabnet, Transformers, LGBM, and a variety of other machine learning approaches for student knowledge tracing.