Prediction of Learner's Course Completion Probability Based on Learning Analytics
AUTHORS
Jong-Yoen Lee,Konkuk University
Sung-Hyun Cha,Korea Tech
Jong-Teak Se,Yong InUnivesity
ABSTRACT
Based on learning analytics, this study investigated whether the learner’s time management data (TMD) accumulated in learning management system (LMS) could predict the probability for a student to complete a course in distance life-long education (DLE). It also attempted to determine the earliest learning progression point (LPP) that could predict the probability. The subjects of the study were 411 students who had taken the five courses offered by a typical DLE center located in Seoul, Korea in the spring semester of 2016. At the end of the semester, the regularity of connecting to the system (RCS), total learning time (TLT), and the number of accessing the system (NAS) were calculated and a stepwise multiple regression analysis was conducted to examine the relationship among the variables of RCS, TLT, and NAS and the total scores (TS). In order to decide LPP at which students’ TS can be predicted significantly, a multiple regression analysis was conducted each quarterly point of total 16 weeks for a semester. As a result, RCS and NAS were proved to predict the probability of completing a course significantly from the first quarterly progression point.
KEYWORDS
distance lifelong education, learning analytics, learner’s time management data, course completion probability
REFERENCES
[1] S. O. Park, S. S. Yoo, Y. S. Hyun, S. S. Lee and S. Y. Park, “Lifelong Education: HRD Research. Performance evaluation of lifelong education policy project: Analysis of the project to provide lifelong education programs for the marginalized”. Vol. 6, No. 3 (2010).
[2] G. H. S, “Governmental Research. The establishment of action plans to improve educational compatability of Korea Open University”. Vol. 15, No. 1 (2016).
[3] Y. Im, Journal of The Korean Association of information Education. “A substantial study on the relationship between students' variables and dropout in Cyber University”. Vol. 11, No. 2 (2007).
[4] J. Jun, Andragogy Today. “Identifying at-risk learners at a cyber university”. Vo. 13, No. 1 (2010).
[5] S. Carr, the Chronicle of Higher Education. “As distance education comes of age, the challenge is keeping the students”. Vol. 46, No. 23 (2000).
[6] P. A. Dupin-Bryant, the American Journal of Distance Education. “Pre-entry variables related to retention in online distance education”. Vol. 18, No. 4 (2004).
[7] G. Siemens and P. Long, EDUCAUSE review. “Penetrating the fog: Analytics in learning and education”. Vol. 46, No. 5 (2011).
[8] J. M. Kim, “Analysis of the primary factor of students' dropout in distance universities”, Master Thesis of The Graduate School of HRD, Chungang University, Korea (2008).
[9] M. J. Chang, “A study on dropouts of cyber university: Grounded theory approach”, Master Thesis of The Graduate School of Education, EwhaWomans University, Korea (2007).
[10] H. Lee, “Development of prediction models based on the clustered online learners’ behavioral patterns in university e-learning environment”, Master Thesis of The Graduate School, EwhaWomans University, Korea (2016).