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.

Experiences with Flipped Classroom Methodology in US High School Chemistry Courses: Lessons Learned from Action Research Projects

Especially since the Covid-19 pandemic when teachers might have found or created videos for students to watch, flipped classroom methodology has interested many secondary-level chemistry teachers. However, as the secondary coauthor teachers here found, most of the research on the effectiveness of flipped classroom methodology has been performed at the collegiate level. To help fill this gap, six high school teachers from different schools present their research and experience with flipped classroom methodologies in their classes. Taken as a collective, their research, aligning with previous research, suggests that there likely will not be gains on exam scores or course grades for high school students when a classroom is "flipped", but there are other positive reasons that flipped classroom methodology might be a useful tool in the secondary-level chemistry classroom.

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.

Grade Inflation in Schools During the COVID-19 Pandemic: Unexpected Effect or Anti-Crisis Strategy?

The closure of educational institutions and the transfer of the learning process to a distance format during the COVID-19 pandemic came as a shock to everyone involved in the educational process. There was, in fact, a rupture of the educational everyday - the normal and unproblematic order of things. A "new normal" as it came to be called, could not emerge immediately - it had to be re-constructed within the unaccustomed contexts of distance interaction for many. Collective practices of this construction were and are captured today in the narratives of their participants - teachers, students and sometimes their parents. This study attempts, through quantitative analysis, to describe the transforma-tion of assessment in schools during the pandemic and to formulate a hypothesis as to the possible reason for the change in marking practices as one of the most significant ways of managing the learning process as well as the social and psychological context of its implementation. The data source used was a database of students' grades from schools in one of the regions of the Russian Federation, accumulated from 2015 to 2021. Using big data methods and the Cohen effect coefficient, the main changes in assessment are described. Particular attention is paid to the few months of 2020, when all schools in the region were closed to face-to-face attendance. It is during this pe-riod that a significant inflationary spike in marking is recorded. It is suggested that teachers deliberately use the strategy of inflating marks in order to maintain a favorable social and psychological climate in school classes and to reduce the general tension in connection with the transition to the dis-tance learning format. An attempt has been made to theorize a strategy for the grade inflation behavior during a period of cataclysm.

Undergraduate student performance in an accounting sciences program: An analysis on the use of emergency remote teaching

This study aims to analyze the variation in academic performance of undergraduate students enrolled in the Accounting Sciences course of a public, federal university of Southern Brazil between the second academic semester of 2019 and the first semester of 2020. The research was documentary and descriptive, following a quantitative approach. The sample was composed of data from 281 students. Quantitative data analysis was carried out through the Statistical Package for the Social Sciences (SPSS) software. Results indicate that the implementation of emergency remote teaching due to social isolation caused by the COVID-19 pandemic did not impact student performance. However, analyzing the students' enrollment semester shows variation in the academic performance in 2017, which may be explored further by future research. Thus, this research contributes to understanding the new teaching model, supplying managers, students, teachers, and institutions new data regarding this issue.

Analysis of Student Study of Virtual Learning Using Machine Learning Techniques

Since COVID-19 was released, online education has taken center stage. Educational performance analysis is a central topic in virtual classrooms and across the spectrum of academic institutions. This research analyzed students' studies in virtual learning using many machine-learning classifiers, which include LogitBoost, Logistic Regression, J48, OneR, Multilayer Perceptron, and Naive Bayes, to find the ideal one that produces the best outcomes. This research evaluates algorithms based on recall, precision, and f-measure to determine their efficacy. Accordingly, the authors try to perform a comparative analysis of the algorithms in this research by employing two distinct test models: the use of training sets and the 10 cross-fold models. The research results demonstrate that the training set model outperforms the 10 cross-fold model. The findings demonstrate that the multilayer perceptron classifier utilizing the use training set model performs much better in terms of predicting student study in virtual learning.

The use of Deep Learning techniques in E-Learning systems and MOOCs

E-Learning and Massive Open Online Courses are old techniques, but since the Coronavirus, they have become more popular again. Students already suffer from a lack of concentration and motivation in traditional courses;thus, this lack affects online courses. Furthermore, another important Online Learning systems problem is the difference between learners in terms of Learning Styles, abilities, social characteristics as well as preferences, background, and other psychological and mental features. Generally, these features are not taken into account by scientists. Therefore, Deep Learning techniques and Datasets have been used to improve E-Learning systems and MOOCs in several aspects such as: predicting dropout, Learning Styles and performance of online learners, and even their attention after taking an online course. In this work, we have studied and analyzed many recent works in the area of using Deep Learning techniques to improve Online Learning systems and MOOCs. This analysis shows what researchers rely on to improve E-Learning and MOOCs and demonstrates that research does not use the definition of the appropriate Learning Style frequently. However, the most used ones are dropout and performance of learners. In another hand, learners' attention is still gap. © 2022 IEEE.

Enhancement of E-Learning Student's Performance Based on Ensemble Techniques

Educational institutions have dramatically increased in recent years, producing many graduates and postgraduates each year. One of the critical concerns of decision-makers is student performance. Educational data mining techniques are beneficial to explore uncovered data in data itself, creating a pattern to analyze student performance. In this study, we investigate the student E-learning data that has increased significantly in the era of COVID-19. Thus, this study aims to analyze and predict student performance using information gathered from online systems. Evaluating the student E-learning data through the data mining model proposed in this study will help the decision-makers make informed and suitable decisions for their institution. The proposed model includes three traditional data mining methods, decision tree, Naive Bays, and random forest, which are further enhanced by the use of three ensemble techniques: bagging, boosting, and voting. The results demonstrated that the proposed model improved the accuracy from 0.75 to 0.77 when we used the DT method with boosting. Furthermore, the precision and recall results both improved from 0.76 to 0.78. © 2023 by the authors.

A Comprehensive Study to Investigate Student Performance in Online Education during Covid-19

During the recent Covid-19 pandemic, there has been a tremendous increase in online-based learning (e-learning) activities as nearly every educational institution has transferred its programs to digital platforms. This makes it crucial to investigate student performance under this new mode of delivery. This research conducts a comparison among the traditional educational data mining techniques to detect the best performing classifier for analyzing as well as predicting students' performance in online learning platforms during the pandemic. It is achieved through extracting four datasets from X-University student information system and learning platform, followed by the application of 6 classifiers to the extracted datasets. Random Forest Classifier has demonstrated the highest accuracy in the first two out of the four datasets, while Simple Cart and Naïve Bayes Classifiers presented the same for the remainder two. All the classifiers have demonstrated medium to high TP rates, class precision and recall, ranging from 60% to 100% for almost all of the classes. This study emphasized the attributes that have a direct impact on students' performance. The outcomes of this study will assist the instructors and educational institutions to identify important factors in the analysis and prediction of student performance for online program delivery.

Situating teacher well-being in English language teaching

The global events of the 21st century, especially during its second decade, contributed to rising rates of mental and emotional health issues around the world, including depression, anxiety, and social isolation. These concerns, which were compounded by the COVID-19 pandemic, are reminding policymakers, scholars, and stakeholders in the field of education about the importance of well-being in schools and in learning. English language teachers' well-being directly affects their effectiveness, teaching practices, classroom atmosphere, teacher-student relationships, and students' well-being and performance, to name a few. In the same way that teacher preparation and knowledge affect teachers' performance, so does teacher well-being. With the purpose of situating teacher well-being in English language teaching (ELT), this chapter provides a brief overview of existing published works highlighting the effects of well-being on teachers' personal and professional lives. It introduces the topic of well-being and teacher well-being in ELT. The chapter divides the manuscript into three main sections, each addressing a salient topic affecting language teacher well-being-namely, emotions in ELT, work-life balance in ELT, and services and supports in ELT. It introduces the topic with a vignette, followed by a brief overview of the literature. (PsycInfo Database Record (c) 2023 APA, all rights reserved)

Relating Student Performance and Procrastination Behavior in Online Discussion Forums

Procrastination is a behavioral feature in which a person chooses to delay a task or a decision. Academic procrastination is the tendency to postpone school-related obligations despite known negative consequences. In this paper, we examine how procrastination manifests in online discussion forum participation in a university in the Philippines during the COVID-19 pandemic. We visualize how high- and low-performing students differ in the rate at which they respond to discussion forum prompts. We also make use of association rule mining in order to determine which student behaviors are antecedents of procrastination. We find that most high-performing students tend to respond to discussion forum prompts much earlier than most low-performing students. This implies that they procrastinate less. We also found that making initial accesses or posts later or no graded posts at all makes the student at risk for poor performance. © ICCE 2022.All rights reserved.

A Prediction System Using AI Techniques to Predict Students' Learning Difficulties Using LMS for Sustainable Development at KFU

With the emergence of the covid 19 pandemic, E-learning usage was the only way to solve the problem of study interruption in educational institutions and universities. Therefore, this field reserved significant attention in current times. In this paper, we used ten Machine Learning (ML) algorithms: Decision Tree(DT), Random Forest(RF), Logistic Regression(LR), SGD Classifier, Multinomial NB, K- Nearest Neighbors Classifier(KNN), Ridge Classifier, Nearest Centroid, Complement NB and Bernoulli NB) to build a prediction system based on artificial intelligence techniques to predict the difficulties students face in using the e-learning management system, to support related decision-making. Which, in turn, contributes supporting the sustainable development of technology at the university. From the results obtained, we detect the important factors that affect the use of E-learning to solve students' learning difficulties using LMS by building a prediction system based on AI techniques. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Experience Report on Using WeBWorK in Teaching Discrete Mathematics

Due to the Covid-19 pandemic, most university classes were moved to online instruction. This greatly stimulated the need for online learning tools. WeBWorK is an open source online homework system, which has been used extensively in a variety of subjects. However, it has not been widely adopted by the Computer Science education community. In this paper, we discuss our experience using WeBWorK in teaching two large online sections of discrete mathematics. Emphasis is given to how we created randomized and auto-graded problems for many topics. In addition, we summarize student performance and feedback. We conclude with our reflections on using WeBWorK and propose future work for exploring its adaptive learning features. © 2023 ACM.

A System Design with Deep Learning and IoT to Ensure Education Continuity for Post-COVID

In this paper, an IoT and deep learning-based comprehensive study to reduce the effects of COVID-19 on the education system is presented. The proposed system consists of an edge device, IoT nodes, and a neural network that runs on a server. The purpose of the proposed system is to protect students and staff against infectious diseases and increase the students performance during classes by monitoring the environmental conditions via an IoT-based sensor network, during the current pandemic to ensure the use of masks in closed areas by training a customized deep learning model, and to monitor the student attendance data by deep learning and IoT-based solution. Furthermore, effective heating and cooling can be done to save energy by transmitting the environmental conditions of the indoor environment to the relevant destinations. The experiment is conducted with five different networks to classify the faces in the images as masked or unmasked, and their performances were examined. The networks were trained on the Face Mask Detection Dataset which contains a total of 7553 masked and unmasked images. The best results were obtained as 99.5% for the F1 Score and 99% for MCC by the model trained on the InceptionV3 network. IEEE

Prediction Student Performance in E-Learning Environment: Challenge and Opportunity

With advancements in e-learning technology, students may power them by interacting with the eLearning environment, such that the teacher is no longer the gatekeeper of instruction. This research attempts to examine students' prediction performance based on their interaction with educational activities in MOODLE and MOOCs;this was accomplished via the use of student log files and some extra data about the specific student. In order to discover the best approach for the student's prediction, the performance prediction was explored using Decision Tree (C4.5 algorithm), Artificial Neural Network, Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) algorithm techniques. Furthermore, log file analysis shows that the rate of interaction with the e-learning context has a substantial influence on their performance, with students with the highest interaction on the MOODLE performing better than someone with low interactivity rates. According to the data, students are more interested on e-learning MOODLE than MOOCs, and as a result, they are missing out on the benefits of the available resources on MOOCs, such as viewing lecture videos and participating in quizzes, which may help them with their studies. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Effects of the COVID-19 pandemic on reading performance of second grade children in Germany.

In education, among the most anticipated consequences of the COVID-19 pandemic are that student performance will stagnate or decline and that existing inequities will increase. Although some studies suggest a decline in student performance and widening learning gaps, the picture is less clear than expected. In this study, we add to the existing literature on the effects of the COVID-19 pandemic on student achievement. Specifically, we provide an analysis of the short- and mid-term effects of the pandemic on second grade reading performance in Germany using longitudinal assessments from over 19,500 students with eight measurement points in each school year. Interestingly, the effects of the pandemic established over time. Students in the first pandemic cohort even outperformed students from the pre-pandemic cohorts and showed a tendency towards decreased variances during the first lockdown. The second pandemic cohort showed no systematic mean differences, but generally had larger interindividual differences as compared to the pre-pandemic cohorts. While the gender achievement gap seemed unaffected by the pandemic, the gap between students with and without a migration background widened over time-though even before the pandemic. These results underline the importance of considering effects of the pandemic across cohorts, large samples, and fine-grained assessments. We discuss our findings considering the context-specific educational challenges and in terms of practical implications for teachers' professional development.

Engaging Online Learning at AAU and Its Impact on Students' Performance during COVID-19

The sudden and wide spread of the deadly severe acute respiratory syndrome coronavirus SARS-COV-2 (COVID-19) has disrupted the normal world we know. This pandemic has produced significant challenges on all world sectors including the global higher education community. In this paper, we present the effect of the COVID-19 pandemic on AL Ain University (AAU), analyse AAU response strategy to shift to an emergency remote, on-line, learning system and compare it with other universities' responses. The technological infrastructure readiness of AAU and how it shifted easily to online learning is discussed. A comparison between the results of some courses that were taught in-class previously (2019) against the ones that were taught remotely (2020) is presented. For the selected sample, results show that online teaching has a good impact on students' performance for many reasons such as saving traveling time, staying at home, and quarantine that imposes focusing on the study since other outdoor entertainments are closed. © 2022 IEEE.

The impact of the learning environment sudden shifts on students' performance in the context of the COVID-19 pandemic

•Introduction: This study aims to determine the effect of sudden changes in learning environments on students' performance, in the context of the COVID-19 pandemic lockdown. We present an analysis of the kinesiology program, focusing on the learning modality changes through the years, and its impact on students' performance. Methods: We analyzed three periods over five years. During the Pre-pandemic period (2018-2019), classes had been taught in-person, during the pandemic (2020-2021) classes had been taught online, and during end of lockdown (2022) classes had return to in-person modality. In addition, we also examined the academic performance outcomes by gender during the three periods. Results: We found that the academic performance significantly increased in all cohort of career, increasing the average grade from 4.7±0.08 (2018 to 2019, in-person) to 5.15±0.07 during the pandemic period, from 2020 to 2021, when online modality was utilized. Furthermore, when returning to in-person classes in 2022, the academic performance reduced significantly to 4.6±0.17. We also found that gender did not have an influence on academic performance in any of the learning environments presented. However, during clinical internships, we found that gender had a significantly effect on academic performance. Conclusion: Based on these results, we conclude that the sudden shift from in-person learning to online learning modality helped improved the learning performance of student, reflecting those results on better students' performance scores that could be associated with the enhanced efficient use of time. Resumen Introducción: Este estudio tiene como objetivo determinar el efecto de los cambios repentinos en los entornos de aprendizaje sobre el rendimiento de los estudiantes, en el contexto del confinamiento por la pandemia del COVID-19. Presentamos un análisis del programa de la carrera de kinesiología, enfocándonos en los cambios de modalidad de aprendizaje a través de los años, y su impacto en el rendimiento de los estudiantes. Métodos: Se analizaron tres períodos a lo largo de cinco años. Durante el periodo Pre-pandemia (2018-2019) las clases se habían impartido de forma presencial, durante la pandemia (2020-2021) las clases se habían impartido online y durante el fin del confinamiento (2022) las clases habían vuelto a la modalidad presencial. Además, también examinamos los resultados del rendimiento académico por género durante los tres períodos. Resultados: Se encontró que el rendimiento académico aumentó significativamente en toda la cohorte de la carrera, aumentando la calificación promedio de 4.74±0.08 (2018 a 2019, presencial) a 5.15±0.07 durante el período de pandemia, de 2020 a 2021, cuando la modalidad en línea fue utilizada. Además, al regresar a las clases presenciales en 2022, el rendimiento académico se redujo significativamente a 4,6±0,17. También encontramos que el género no influyó en el rendimiento académico en ninguno de los entornos de aprendizaje presentados. Sin embargo, durante las pasantías clínicas, encontramos que el género tuvo un efecto significativo en el rendimiento académico. Conclusión: Con base en estos resultados, concluimos que el cambio repentino de la modalidad de aprendizaje en persona a la modalidad de aprendizaje en línea ayudó a mejorar el rendimiento de aprendizaje de los estudiantes, lo que refleja esos resultados en mejores puntajes de rendimiento de los estudiantes que podrían estar asociados con un mayor uso eficiente del tiempo.

A Hybridized Framework for Designing and Evaluating E-Learning Students' Performance in Medical Education

The COVID-19 pandemic resulted in the hurried adoption of e-learning with no proper need analysis to inform the design and subsequent evaluation of students' performance in e-learning in medical education. Consequently, several studies evaluating performance in e-learning in medical education do so by conducting pre-Test and post-Test with no defined framework or model to guide the evaluation. This makes the findings from these studies subjective and biased since factors that possibly impact students' performance were neither considered in the design of the course nor measured and reported in the evaluation studies. We, therefore, introduce an essential pedagogical e-learning concept by developing a framework to inform the design and evaluation of students' performance in e-learning in medical education via the thoughtful fusion of the Task-Technology Fit Model and the Kirkpatrick Evaluation Model. Our hybrid framework was piloted at the University of KwaZulu-Natal, Durban, South Africa and findings emphasize the need for alignment between learning tasks, technology infrastructures, individual traits, and contextual limitations of students as key factors in determining how well students perform in the classroom and their clinical practices at work. This study advances the body of knowledge by providing a well-brainstormed and intricately designed framework to guide the design of courses and evaluation of student's performance in an e-learning context in medical education. © 2022 IEEE.

The Influence of E-Iearning, M-learning, and D-learning on the Student Performance: Moderating Role of Institutional Support

Student performance was affected due to the covid-19 pandemic;therefore, electronic (E), mobile (M), and distance (D) learning are the significant solution for this issue and needs researchers' focus. This study examines the impact of E learning, M learning, and D-Iearning on student performance in educational institutions in the UAE. Besides, this study investigates the moderating impact of institutional support on E-Iearning, M-learning, D-Iearning, and student performance in educational institutions in the UAE. The data were collected from students using questionnaires utilizing smart-PLS to check the data reliability and relationships among variables. The results indicated that E-Iearning, M-Iearning, and D-Iearning have a positive impact on student performance in educational institutions in the UAE. The results also revealed that the institutional support significantly moderates E-Iearning, M-learning, D-Iearning, and student performance in educational institutions in the UAE. The findings of this study help policymakers in establishing the policies related to the improvement of student performance using E learning, M-learning, and D-Iearning. © 2022 IEEE.