Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Science in Information Technology Letters
Mokhtar, Nur Azizah Mohammad
Unknown Affiliation
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Web log augmented analytics and extraction for e-learning environment Mokhtar, Nur Azizah Mohammad; Sulaiman, Sarina; Pranolo, Andri
Science in Information Technology Letters Vol 4, No 2 (2023): November 2023
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/sitech.v4i2.1224

Abstract

E-Learning is a commonly used platform by most institutions, especially during the pandemic Covid-19. E-learning services include viewing, submitting, and uploading files, attempting quizzes, viewing forums, and downloading files. The data store in the servers grow on par with the increment of users in e-Learning@UTM every semester. As a result, the data have become extremely huge. These web log data can be used in augmented analytics to find meaningful insights. The web log data extracted are the log files of the history engagement of users and students’ grades. Data obtained are used in augmented analytics to study the pattern of the data and insights into meaningful information. This research focuses on classification of data through predictive analytics. Hence, predictive models are required. To prove a better outcome, building the model consists of three types of algorithms; Decision Tree, Artificial Neural Networks and Support Vector Machine which are used and compared. After extracting data from e-learning, the first step in building a predictive model is to do data collection, data pre-processing, and data transformation. These three classifiers use the pre-processed data and split the data into training and test sets afterwards. Each classifiers techniques are built and a confusion matrix is applied as a performance measurement to summarise the performance of a classification algorithm, respectively.
Co-Authors Andri Pranolo Sarina Sulaiman