Analysis and Prediction of Student Performance Based on Moodle Log Data using Machine Learning Techniques

During the COVID-19 Pandemic, many universities in Thailand were mostly locked down and classrooms were also transformed into a fully online format. It was challenging for teachers to manage online learning and especially to track student behavior since the teacher could not observe and notify students. To alleviate this problem, one solution that has become increasingly important is the prediction of student performance based on their log data. This study, therefore, aims to analyze student behavior data by applying Predictive Analytics through Moodle Log for approximately 54,803 events. Six Machine Learning Classifiers (Neural Network, Random Forest, Decision Tree, Logistic Regression, Linear Regression, and Support Vector Machine) were applied to predict student performance. Further, we attained a comparison of the effectiveness of early prediction for four stages at 25%, 50%, 75%, and 100% of the course. The prediction models could guide future studies, motivate self-preparation and reduce dropout rates. In the experiment, the model with 5-fold cross-validation was evaluated. Results indicated that the Decision Tree performed best at 81.10% upon course completion. Meanwhile, the SVM had the best result at 86.90% at the first stage, at 25% of the course, and Linear Regression performed with the best efficiency at the middle stages at 70.80%, and 80.20% respectively. The results could be applied to other courses and on a larger e-learning systems log that has similar student activity conditions and this could contribute to more accurate student performance prediction © 2023, International Journal of Emerging Technologies in Learning.All Rights Reserved.

E-learning enhancement through educational data mining with Covid-19 outbreak period in backdrop: A review.

E-learning is fast becoming an integral part of the teaching- learning process, particularly after the outbreak of Covid-19 pandemic. Educational institutions across the globe are striving to enhance their e-learning instructional mechanism in accordance with the aspirations of present-day students who are widely using numerous technological tools - computers, tablets, mobiles, and Internet for educational purposes. In the wake of the evident incorporation of e-learning into the educational process, research related to the application of Educational Data Mining (EDM) techniques for enhancing e-learning systems has gained significance in recent times. The various data mining techniques applied by researchers to study hidden trends or patterns in educational data can provide valuable insights for educational institutions in terms of making the learning process adaptive to student needs. The insights can help the institutions achieve their ultimate goal of improving student academic performance in technology-assisted learning systems of the modern world. This review paper aims to comprehend EDM's role in enhancing e-learning environments with reference to commonly-used techniques, along with student performance prediction, the impact of Covid-19 pandemic on e-learning and priority e-learning focus areas in the future.

Augmenting Convolution Neural Networks by Utilizing Attention Mechanism for Knowledge Tracing

The devastating, ongoing Covid-19 epidemic has led to many students resorting to online education. In order to better guarantee the quality, online education faces severe challenges. There is an important part of online education referred to as Knowledge Tracing (KT). The objective of KT is to estimate students’ learning performance using a series of questions. It has garnered widespread attention ever since it was proposed. Recently, an increasing number of research efforts have concentrated on deep learning (DL)-based KT attributing to the huge success over traditional Bayesian-based KT methods. Most existing DL-based KT methods utilize Recurrent Neural Network and its variants, i.e. Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU) etc. Recurrent neural networks are good at modeling local features, but underperforms at long sequence modeling, so the attention mechanism is introduced to make up for this shortcoming. In this paper, we introduce a DL-based KT model referred to as Convolutional Attention Knowledge Tracing (CAKT) utilizing attention mechanism to augment Convolutional Neural Network (CNN) in order to enhance the ability of modeling longer range dependencies. © 2022, IFIP International Federation for Information Processing.

Evaluating the Performance of ID3 Method to Analyze and Predict Students' Performance in Online Platforms

The primary goal of this work was to establish the influence of the epidemic on education, especially the impact of online platforms on students' overall performance. To improve education quality in this new normal, it is vital to ascertain the elements influencing students' performance. During the Covid-19 epidemic, online-based learning (e-learning) activities increased significantly as every educational institution shifted its operations to digital means. To improve education quality in this circumstance, it is vital to ascertain the elements that influence students' performance. Data mining techniques are becoming more used in educational field research. Educational data mining is a new area that tries to study the unique, ever more extensive data sets generated by educational settings to better understand the students who use them. In this study, Iterative Dichotomiser 3 was implemented to explore precisely 280 students' data to evaluate its performance on an online learning platform. 10-fold cross-validation and the percentage split method were used to assess the classifier. In this analysis, the 10-fold cross-validation method outperformed the percentage split by almost 3 percent, where this validation method achieved almost 77.86 percent accuracy. The effectiveness of the ID3 classifier in predicting students' performance on an online platform will be investigated in this research. © 2022 IEEE.

Student Performance Prediction Using Classification Models

The education industry has gone through major changes amidst the recent COVID-19 pandemic. Facing unforeseen circumstances, educational institutions were forced to shift to an online learning model rather than an offline, classroom-based learning model. The sudden change in the learning model impacted not only students but also the teaching faculty. Even though many resources are available online, simulating a classroom-like study environment is not an easy task. Hence mapping student performance in the new learning model is an essential task. The main goal of our work is to predict the student performance in the online learning model implemented by many colleges and universities amidst the COVID-19 pandemic. Unlike the previous work in this domain, we are purely focusing on an online study system. An online survey was conducted to collect the data from the students who had undergone the aforementioned learning model for at least one semester. The data set for the research includes features that would have an impact on a student’s performance having various attributes. The model strives to predict a student’s performance with good accuracy and help infer where the online learning model can be improved. Several classifiers such as KNN, Gradient boost, Adaboost, Decision tree, SVM, Gaussian NB were used to classify the student data. To validate the performance of these classifiers we have compared them with the latest state-of-the-art works. The Gradient Boost, Xgboost Classifier, and SVM classifiers returned the highest accuracies, in essence, 97.46, 97.45, and 97.45%, respectively. This indicates that the performance of the students is predictable with the given features. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Predicting Student Performance from Online Engagement Activities Using Novel Statistical Features.

Predicting students' performance during their years of academic study has been investigated tremendously. It offers important insights that can help and guide institutions to make timely decisions and changes leading to better student outcome achievements. In the post-COVID-19 pandemic era, the adoption of e-learning has gained momentum and has increased the availability of online related learning data. This has encouraged researchers to develop machine learning (ML)-based models to predict students' performance during online classes. The study presented in this paper, focuses on predicting student performance during a series of online interactive sessions by considering a dataset collected using digital electronics education and design suite. The dataset tracks the interaction of students during online lab work in terms of text editing, a number of keystrokes, time spent in each activity, etc., along with the exam score achieved per session. Our proposed prediction model consists of extracting a total of 86 novel statistical features, which were semantically categorized in three broad categories based on different criteria: (1) activity type, (2) timing statistics, and (3) peripheral activity count. This set of features were further reduced during the feature selection phase and only influential features were retained for training purposes. Our proposed ML model aims to predict whether a student's performance will be low or high. Five popular classifiers were used in our study, namely: random forest (RF), support vector machine, Naïve Bayes, logistic regression, and multilayer perceptron. We evaluated our model under three different scenarios: (1) 80:20 random data split for training and testing, (2) fivefold cross-validation, and (3) train the model on all sessions but one which will be used for testing. Results showed that our model achieved the best classification accuracy performance of 97.4% with the RF classifier. We demonstrated that, under similar experimental setup, our model outperformed other existing studies.