A Review of Learning Types Research Trends on the Use of Machine Learning in Education

EasyChair Preprint 10401

Abstract

This review paper presents an overview of the use of machine learning (ML) in education, particularly in analyzing student performance data through techniques such as eye tracking, voice tracking, and window switching during online exams. With the goal of providing personalized learning experiences that address the individual needs of students, the utilization of ML in education has gained significant attention in recent years. Eye tracking enables the collection of valuable data on student behavior during online exams, which can then be analyzed by ML algorithms to identify patterns and relationships between behavior and exam performance. This can lead to the development of interventions that improve student learning outcomes. Voice tracking is another technique that provides insight into student behavior during online exams. By analyzing the data collected through voice tracking, ML algorithms can identify keywords or phrases associated with incorrect answers, leading to the development of interventions that improve student performance. Finally, window switching can provide valuable information on student engagement with exam content, which can be analyzed by ML algorithms to identify patterns and relationships between window switching behavior and exam performance, leading to interventions that improve learning outcomes.

Keyphrases: Data Mining, Education, Window Switch, eye tracking, machine learning, online exam, student performance

@booklet{EasyChair:10401,
  author    = {Md Ferdous Hossain Parvaj and Amandeep Kaur Kaur and Aditya Pratap and Md Abdullah Al Mamun and Md Tanjim Alam Abir},
  title     = {A Review of Learning Types Research Trends on the Use of Machine Learning in Education},
  howpublished = {EasyChair Preprint 10401},
  year      = {EasyChair, 2023}}