Learning Analytics of Student Participation and Achievement in Online Distance Education: A Structural Equation Modeling

doi:10.12738/estp.2017.6.0059

Cited by 7 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Accordingly, it was observed that monthly, weekly and daily interactions in the learning management system are more powerful factors in discriminating successful and unsuccessful students when compared to average time spent per semester and average numbers of logins to the system in total. Koc (2017) found that students' participation in discussion and live class in the learning management system was positively related to their project and final scores. Since these activities are planned daily, weekly or monthly, it can be said that regular follow-up of the learning management system increases the success of the students.…”

Section: Discussionmentioning

confidence: 96%

Classification of Students’ Achievement via Machine Learning by Using System Logs in Learning Management System

Koyuncu

Kılıç

Göksün

2022

Turkish Online Journal of Distance Education

View full text Add to dashboard Cite

During emergency remote teaching (ERT) process, factors affecting the achievement of students have changed. The purposes of this study are to determine the variables that affect the classification of students according to their course achievements in ERT during the pandemic process and to examine the classification performance of machine learning techniques. For these purposes, the logs from the learning management system were used. In the study, analyzes were carried out with various machine learning techniques and their performances were compared. As a result of the study, it was observed that Fisher’s Linear Discriminant Analysis was the best technique in classification according to F measure performance criteria. As another result, the most effective variable, in classifying students, is the average number of days logged into the system per month and week. It has been observed that total activity duration (min), total number of weeks and total number of page views during the semester are less influential factors. Accordingly, it could be suggested to check the monthly and weekly follow-up of the lectures instead of the total follow-ups per semester. In addition, students’ interaction patterns can be monitored with course tracking systems.

show abstract

Section: Discussionmentioning

confidence: 96%

Classification of Students’ Achievement via Machine Learning by Using System Logs in Learning Management System

Koyuncu

Kılıç

Göksün

2022

Turkish Online Journal of Distance Education

View full text Add to dashboard Cite

show abstract

“…Teachers can take the initiative to post discussion information or actively ask questions related to the course content after class to guide learners to actively share their learning experiences (Xiao et al , 2022). In addition, the text-based asynchronous communication mode provides learners with a more autonomous learning experience (Koç, 2017), while some of the more shy learners can also engage more in the asynchronous interaction mode, which also influences the learners’ learning to some extent. In addition to postback behavior, the frequency of learners submitting tests and assignments also showed extremely effective predictive power in all three models.…”

Section: Discussionmentioning

confidence: 99%

An evaluation model based on procedural behaviors for predicting MOOC learning performance: students’ online learning behavior analytics and algorithms construction

Tong

Zhan

2023

ITSE

View full text Add to dashboard Cite

Purpose The purpose of this study is to set up an evaluation model to predict massive open online courses (MOOC) learning performance by analyzing MOOC learners’ online learning behaviors, and comparing three algorithms – multiple linear regression (MLR), multilayer perceptron (MLP) and classification and regression tree (CART). Design/methodology/approach Through literature review and analysis of data correlation in the original database, a framework of online learning behavior indicators containing 26 behaviors was constructed. The degree of correlation with the final learning performance was analyzed based on learners’ system interaction behavior, resource interaction behavior, social interaction behavior and independent learning behavior. A total of 12 behaviors highly correlated to learning performance were extracted as major indicators, and the MLR method, MLP method and CART method were used as typical algorithms to evaluate learners’ MOOC learning performance. Findings The behavioral indicator framework constructed in this study can effectively analyze learners’ learning, and the evaluation model constructed using the MLP method (89.91%) and CART method (90.29%) can better achieve the prediction of MOOC learners’ learning performance than using MLR method (83.64%). Originality/value This study explores the patterns and characteristics among different learning behaviors and constructs an effective prediction model for MOOC learners’ learning performance, which can help teachers understand learners’ learning status, locate learners with learning difficulties promptly and provide targeted instructional interventions at the right time to improve teaching quality.

show abstract

“…The use of digital technology is a breakthrough in education because it offers a solution to limitations in time, place and funding in the implementation of the learning process (Koç, 2017;Strobl et al, 2019;Davey, Elliott & Bora, 2019;Boyle & Kennedy, 2019;Cheng & Lai, 2019;Shaikh, 2019). However, before its application, teachers require procedural assistance and preparation (Lall et al, 2019;Naraian & Surabian, 2014).…”

Section: ▪ Introductionmentioning

confidence: 99%

Developing Hidden Questions as a Learning Model to Enhance Student Communication Skills

Santoso,

Nadya,

Murdiono

2023

Bull. Soc. Stud. Community Dev

View full text Add to dashboard Cite

Developing Hidden Questions As A Learning Model To Enhance StudentCommunication Skills. This study was designed to develop learning models to improve student communication skills. In a learning model called hidden questions, students are required to learn actively through an exercise of arguing and answering questions. This R&D (research and development) study followed the instructional design proposed by the ADDIE (Analysis, Design, Development, Implementation and Evaluation) framework. The data were obtained from expert validation, interviews and model implementation in junior high schools in Pringsewu District, Indonesia, and analysed by a mixed method of quantitative (Test Statistics Kruskal Wallis) and descriptive qualitative. The results of the Test Statistics Kruskal Wallis showed that the asymptotic significance or p-value was 0.001 ˂ (0.05 or 0.01), indicating statistically significant differences between before and after the model implementation or signifying that the hypothesis is accepted. The quantitative and qualitative data analysis revealed that hidden question created an effective learning model in improving student communication skills. These findings provide a basis for further research in the development of learning models that can improve Communication, Collaborative ability, Critical Thinking and Creativity skills of students.

show abstract

Learning Analytics of Student Participation and Achievement in Online Distance Education: A Structural Equation Modeling

Cited by 7 publications

References 26 publications

Classification of Students’ Achievement via Machine Learning by Using System Logs in Learning Management System

Classification of Students’ Achievement via Machine Learning by Using System Logs in Learning Management System

An evaluation model based on procedural behaviors for predicting MOOC learning performance: students’ online learning behavior analytics and algorithms construction

Developing Hidden Questions as a Learning Model to Enhance Student Communication Skills

Contact Info

Product

Resources

About