Analysis of Factors Influencing LMS Extracted Data using Learning Analysis on the Total Score of Learners

Abstract

The development of information and communication technology has led to change in today's modern society with various names, such as knowledge, information society, internationalization society, and especially, the development of distance education without time and space restrictions. With the development of distance education, problems of dropouts and incompleteness of learners who are constantly in trouble are emerging as and they must be solved. Therefore, in this study, log data (regularity of learning start interval, total number of learnings and total learning time) and personal background data (courses experience, education experience, gender and age) accumulated in the web through learning management system (LMS) in a distant education environment. The purpose of this study is to analyze the effect of age and educational experience on the total scores that determine completion (more than 60 points) and incompleteness (less than 60 points). The study was carried out with data from 1,130 learners of distance learning centers, which were conducted for a total of 16 weeks. Data was extracted and analyzed based on learning analysis, and the results were as follows: First, among the log data, it was found that the total learning time and number of learning had significant effects on the total score. As the number of access to the LMS increased, the learning time and total score increased. Second, among personal background data, age was found to have a significant effect on the total score. It was concluded that the probability of completing the study, i.e, the probability of completing the study, increases as age increases, so the purpose of learning becomes more apparent. The data used in this study was used when a learner started signing up for LMS for learning and collected the consent in advance with the consent of the personal information agreement.

Qualifications Framework of Essential Learning Outcomes for Computer Innovation and Digital Industry Professionals

“…The efficiency and factor loading of this factor"s qualifications was at 0.93, and the covariance of the factor Interpersonal Skills and responsibility was at 95%, respectively. [19]. Thus, these five factors can be considered appropriate to use as the qualifications framework of essential learning outcomes for undergraduates in Computer Innovation and Digital Industry Major based on the context of NSTRU because of its validity in keeping with the hypothesis previously mentioned.…”

“…Step: The research instruments were sent to the group of experts in advance to ask for their opinion, consideration, and confirmation of the details of competency indicators followed in the qualifications framework of essential learning outcomes for [19]. They stated that determining the sample size depends on the number of factors the researcher wants to analyze.…”

“…CFA is still very popular because of its high level of construct validity. Moreover, it can correctly create new research knowledge [19,20].…”

“…The sample group was a group of experts who are all teachers and have expertise in Computer Science, Computer Engineering, Software Engineering, Information Technology, Business Computers, and Computer Education from public educational institutions across Thailand. For sample size determination to analyze the factors of a list of indicators of essential competencies followed in the qualifications framework, the researchers used the concept presented bySuwanroj et al (2019) [7],Seo et al (2021) …”