Predicting and Comparing Students’ Online and Offline Academic Performance Using Machine Learning Algorithms

Abstract

Due to COVID-19, the researching of educational data and the improvement of related systems have become increasingly important in recent years. Educational institutions seek more information about their students to find ways to utilize their talents and address their weaknesses. With the emergence of e-learning, researchers and programmers aim to find ways to maintain students’ attention and improve their chances of achieving a higher grade point average (GPA) to gain admission to their desired colleges. In this paper, we predict, test, and provide reasons for declining student performance using various machine learning algorithms, including support vector machine with different kernels, decision tree, random forest, and k-nearest neighbors algorithms. Additionally, we compare two databases, one with data related to online learning and another with data on relevant offline learning properties, to compare predicted weaknesses with metrics such as F1 score and accuracy. However, before applying the algorithms, the databases need normalization to meet the prediction format. Ultimately, we find that success in school is related to habits such as sleep, study time, and screen time. More details regarding the results are provided in this paper.

Comprehensive analysis of factors influencing the real-world application of machine learning for student success rate calculation and their impacts on student achievement & educational institutions

“…They conclude that behaviors like sleep, study, and use of electronic media all have a role in academic achi evement. This publication elaborates on the findings in further depth [7]. S. Kaddoura et al (2022) presented machine learning methods for online education and testing.…”

“…In conclusion, machine learning not only protects personal information but also allows businesses to use data to make more informed decisions in compliance with legal mandates [5]. [6,7] When it comes to assessing and enhancing student success rates in education, machine learning plays a significant role while also addressing the critical topic of data privacy. Academic achievement records, attendance records, engagement data, and socioeconomic characteristics may all be analyzed with the use of machine learning algorithms in today's schools.…”

Design and Implementation of Machine Learning Algorithms in Automatic Grading of Students' Assignments

“…These findings have the potential to guide targeted interventions and enhance the effectiveness of anti-bullying measures in schools. In [11], the study focused on the use of ML algorithms to predict and understand declining student performance during the COVID-19 era, especially in the context of the rise of e-learning. It sheds light on the impact of habits such as sleep, study time, and screen time on academic success, drawing comparisons between online and offline learning data for valuable insights.…”

“…It offers a numerical evaluation of how accurately the model's predictions align with the true grades. The mathematical formula for computing MSE is shown as equation (11).…”

“…From equation (11), the terms 𝑛 implies the samples count, 𝑦 𝑖 implies the i th sample actual grade and 𝑦 𝑖 ̂ implies the i th sample predicted grade. Similar to MAE, a decreased MSE value represents improved performance, as it suggests the model's forecasts are more accurate.…”