Year: 2018
Type: article
Abstract: Educational institutions have many expectations for the use of E-book. The top expectation is to evaluate and to improve the education system based on the accumulated learning activity log data. This paper applied machine learning to predict the learner's final score from e-Book browsing logs. The present paper evaluated the prediction performance of the good students with the final grade of 80 or more from their learning access logs. An experimental evaluation revealed that the prediction performance (accuracy) was only 64% if we use only the accessed page information. However, the accuracy was improved to 89% when consecutive browsing page transition information was used. Furthermore, it was confirmed that returning to the previous page is a feature of the highest grades students.
Author: Sachio Hirokawa
Language: English
Subfield: Computer Science Applications
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: green
OpenAlex ID: W2920633197
