A Systematic Review of Machine Learning Algorithms in Analyzing Student Performance: 2018–2022 (Poster 2)

• In Event: AERA Poster Session Five
  In Poster Session: Division D Section 2 Poster Session

Abstract

Employing Machine Learning Algorithms (MLAs) to improve students’ performance have increased rapidly in the last five years. In this paper, 46 empirical studies using MLAs to analyze students’ performance data were systematically reviewed in terms of the PRISMA 2020 framework. The review focused on various aspects of the research studies, including research purposes, characteristics of students being measured, learning outcomes, and the MLA methodology used in the research studies (i.e., feature selection techniques, MLAs validation, most frequently used MLAs, MLAs evaluation measures, and the most accurate MLAs). The study provided a roadmap for researchers who attempted to understand student academic performance through the implementation of MLAs.

Authors

• Ya Zhang, Western Michigan University
  Presenting Author

• Abdullah Alfarwan, Western Michigan University
  Non-Presenting Author