Analysis of Online Behavior and Prediction of Learning Performance in Blended Learning Environments

서지정보

ㆍ발행기관 : 한국교육공학회 ㆍ수록지정보 : Educational Technology International / 15권 / 2호
ㆍ저자명 : Il-Hyun JO, Yeonjeong PARK, Jeonghyun KIM, Jongwoo SONG

목차

Introduction
Theoretical Backgrounds
Method
Results
Conclusion
References

한국어 초록

A variety of studies to predict students’ performance have been conducted since educational data suchas web-log files traced from Learning Management System (LMS) are increasingly used to analyzestudents’ learning behaviors. However, it is still challenging to predict students’ learning achievementin blended learning environment where online and offline learning are combined. In higher education,diverse cases of blended learning can be formed from simple use of LMS for administrative purposesto full usages of functions in LMS for online distance learning class. As a result, a generalized modelto predict students’ academic success does not fulfill diverse cases of blended learning. This studycompares two blended learning classes with each prediction model. The first blended class whichinvolves online discussion-based learning revealed a linear regression model, which explained 70% ofthe variance in total score through six variables including total log-in time, log-in frequencies, log-inregularities, visits on boards, visits on repositories, and the number of postings. However, the secondcase, a lecture-based class providing regular basis online lecture notes in Moodle show weaker resultsfrom the same linear regression model mainly due to non-linearity of variables. To investigate thenon-linear relations between online activities and total score, RF (Random Forest) was utilized. Theresults indicate that there are different set of important variables for the two distinctive types ofblended learning cases. Results suggest that the prediction models and data-mining technique shouldbe based on the considerations of diverse pedagogical characteristics of blended learning classes.

참고 자료

없음