The challenge of predicting students’ final score with online activity in blended learning environment: A comparison between discussion-based learning and lecture-based learning

• In Event: KSET - Innovative Learning Environment

Short Description

A variety of studies to predict students’ performance have been conducted since the educational data tracked from LMS are increasingly utilized to analyze their learning behaviors. However, such a prediction is still challenging in blended learning environments due to the large proportion of residuals occurred by off-line behaviors that are not explained by student’s online activity. In this study, we analyzed two different blended classes (discussion-based vs. lecture-based) by using a mix of regression and random forest approach.

Authors

• Jeong Hyun Kim, Ewha Womans University

• Yeonjeong Park, Ewha Womans University

• Jongwoo Song, Ewha Womans University

• Il-Hyun Jo, Ewha Womans University