Prediction of Students’ Performances Using Course Analytics Data: A Case of Water Engineering Course at the University of South Australia (original) (raw)
Related papers
Students' engagement characteristics predict success and completion of online courses
Journal of Computer Assisted Learning
This study examined students' engagement characteristics in online courses and their impact on academic achievements, trying to distinguish between course completers and noncompleters. Moreover, this research is intended to differentiate between those who pass the final exam and those who do not. Four online courses were examined with a similar pedagogical model (N students = 646) using learning analytics methods. The results revealed significant differences between students who completed the courses and students who did not, in all 13 variables. Completers' learning activities were more than twice as high, except for writing in the forums. Course subject and ongoing task and assignment submissions predicted course completion, whereas, in addition to these variables, engagement with course materials and reading the forums predicted final exam success, as well. Thus, the prediction of success in final exam emphasized the significant importance of engagement in various activities in the online course.
2019
Over the last four decades, the study of academic performance in higher education has increased its number of information sources to understand phenomena such as student achievement or dropout. The first econometric models in the field commonly used student characteristics, pre-college achievement, and college performance. Then, a large range of psychosocial theories, with its respective instruments (typically questionnaires), added a new layer of analyses that complemented previous models. Recently, colleges and universities have dramatically expanded their capacity to capture student data through different systems. Such is the case of the learning management systems (LMS), which provide dynamic and a large amount of data about student online behavior. We are just beginning to explore how these layers of data come together to explain academic performance. In this study, we seek to understand and model these layers of data from a first year cohort at a large engineering school in Ch...
Can Student Engagement in Online Courses Predict Performance on Online Knowledge Surveys
International Journal of Learning, Teaching and Educational Research, 2017
The link between student engagement and academic performance has been widely examined. However, most of these studies have focused on ascertaining the existence of such a relationship on the summative assessment level. By comparing students’ experience points in an online course and students’ scores on online knowledge surveys (KS), this study examined the relationship between student engagement and performance on online KS on the formative assessment level. Knowledge surveys were developed and formatively administered in four sections of an online Integration of ICT in Education course. Using Moodle Feedback Module, knowledge surveys were designed based on three key elements: learning objectives, the course content, and the revised Bloom’s Taxonomy of learning objectives. Using rated multiple choice KS questions, the correlation between students’ scores on KSs and students’ experience points was calculated using SPSS. The results show that students’ confidence levels in ability to ...
Is Learning Analytics the Future of Online Education?
International Journal of Emerging Technologies in Learning (iJET)
Educational structures have been evolving, that even so rapidly with the revolution of information technology and internet. Recent pandemic and its after effects are still looming over the globe, posing as challenge and an opportunity for educators. Online education was one such innovation, which has changed the dynamics of education around the world. The purpose of the paper is three-fold, first, to assess the levels of student engagement in the online learning environment, second, to examine how student engagement is related to their academic performance using learning analytic tools and third, to propose an integrated learning analytics framework. The study used, an exploratory research method and the data was collected from multiple sources; LMS Logs, self-administered questionnaires from students, and interviews with the instructor. The study was conducted at a course level in a private university. The finding suggests a positive relationship between student engagement and thei...
Factors that Predict Student Engagement in Online Learning: HarvardX Case Study
With the increased availability of learning analytics data in the online learning space, there is room for research that examines and develops quantifiable measures of online teaching and learning practices. This paper examines the 2012-2013 HarvardX learning analytics data to look at factors predicting student engagement. The effects of student demographic and online learning behavior on student engagement levels has been examined through logistic regression analysis. According to the results, there are three significant predictors for student engagement: (1) student age; (2) the number of unique days students interacted within the course; and (3) the number of chapters with which the student interacted. Implications for future studies using learning analytics data for measuring online teaching and learning practices are discussed.
The Relationship Between Student Engagement and Academic Performance in Online Education
2021
In recent years, online education has become a mature, recognised, and heavily used alternative for delivering higher education programmes. Beyond its benefits, online education faces a number of challenges, some of which relate to its engagement and impact on student performance. To support the ongoing research into the complex relationships developed, this research investigated the relationship between engagement and academic performance for students that undertake standalone online programmes. The study uses as input the module content engagement data, as collected from an e-learning platform, including the number of content views, forum posts, completed assignments, and watching of videos. The study used Pearson correlation to evaluate the relationship between learner engagement and academic performance. The analysis revealed that the student engagement was positively correlated to the student performance both for individual modules as well as across the cohort. In addition, correlation between initial engagement with individual subjects and the overall engagement was also strong, indicating both variables lead to improved academic results.
Measuring Student Engagement in the Online Course: The Online Student Engagement Scale (OSE)
Online Learning, 2015
Student engagement is critical to student learning, especially in the online environment, where students can often feel isolated and disconnected. Therefore, teachers and researchers need to be able to measure student engagement. This study provides validation of the Online Student Engagement scale (OSE) by correlating student self-reports of engagement (via the OSE) with tracking data of student behaviors from an online course management system. It hypothesized that reported student engagement on the OSE would be significantly correlated with two types of student behaviors: observational learning behaviors (i.e., reading e-mails, reading discussion posts, viewing content lectures and documents) and application learning behaviors (posting to forums, writing e-mails, taking quizzes). The OSE was significantly and positively correlated with application learning behaviors. Results are discussed along with potential uses of the OSE by researchers and online instructors.
International Journal on Recent and Innovation Trends in Computing and Communication
This study aims to bring out the engagement level of university students during this pandemic. The research is to study the levels of engagement such as affective, behavioural, and cognitive engagement on the dependent variable of students' performances. As in this pandemic, most classes are online, and students need different classes and web-based tools to interact in the classroom. The biggest challenge to the educational sector is the transformation, and by 2030 there could be a change in the educational sector. For this purpose, the primary data are collected from 979 students of the Kingdom of Bahrain. PLS-SEM was utilised to analyse the measurement and structural models through SmartPLS 3.3.2 software to prove the construct's hypothesis. Therefore, the study utilised the combinative PLS method that fulfils the characteristics of the model. The study results show that affective engagement, behavioural engagement, and cognitive engagement positively affect the students&#...