JISE


  [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13]


Journal of Information Science and Engineering, Vol. 34 No. 5, pp. 1175-1186


Applying Learning Analytics to Deconstruct User Engagement by Using Log Data of MOOCs


MING-CHI LIU1, CHEN-HSIANG YU1, JUNGPIN WU2,
AN-CHI LIU1 AND HSI-MIN CHEN1
1Department of Information Engineering and Computer Science
2Department of Statistics
Feng Chia University
Taichung, 407 Taiwan
E-mail: {mingcliu; chyu; cwu; acliu; hsiminc*}@fcu.edu.tw


  Previous research noted that software requirement analysis should move beyond usability to understand and design for more engaging user experiences. This study analyzes system logs collected from the Massive Open Online Courses (MOOCs) to capture user engagement over time. We measured engagement through mapping event logs with three components of engagement. We further analyzed the helpfulness of engagement measurement in predicting grades. The results showed that there was a significant and moderate positive correlation between the behavioral, cognitive, and emotional engagement and quiz scores. A multiple linear regression analysis also showed that higher behavioral and cognitive engagement were related to higher quiz scores. Thus, this study performed three classification methods and found that the ANN method got the highest accuracy. This study applied sequential analysis to discover the difference between video watching behavior of the high and low quiz scores students. The results indicate that it is important to take into account all of the behavioral, cognitive, and emotional engagement in understanding user engagement during the system development process.


Keywords: system log analysis, user engagement, MOOCs

  Retrieve PDF document (JISE_201805_04.pdf)