Naive Bayes Method for Classification of Student Interest Based on Website Accessed

Interest is a feeling of liking a thing or activity without any coercion. Students' interest in a certain subject will maintain students' learning abilities, thus they could master it and get good learning outcomes. Interest can be known from the website accessed. The aim of this study is...

Full description

Saved in:
Bibliographic Details
Published inJournal of physics. Conference series Vol. 1655; no. 1; pp. 12104 - 12116
Main Authors Nazir, Alwis, Akhyar, Amany, Ramadhani, Muhammad, Herlina
Format Journal Article
LanguageEnglish
Published Bristol IOP Publishing 01.10.2020
Subjects
Learning
Physics
Search engines
Students
Websites
Online AccessGet full text

Cover

More Information
Summary:Interest is a feeling of liking a thing or activity without any coercion. Students' interest in a certain subject will maintain students' learning abilities, thus they could master it and get good learning outcomes. Interest can be known from the website accessed. The aim of this study is to build a web-based application that could classify student interest using Naïve Bayes based on the website accessed. In this study, the data used are 17.265 student internet history data. The application was tested using Black Box and the method was tested using Confusion Matrix. The result from the application testing met the expectation, and the method (Naïve Bayes) reached 99,81% accuracy using 70:30 data percentage. The top five classes obtained are Social Networking, Educational Institution, Streaming Video, Search Engines, and Web-Based Mail. The "Develop" class was also found, thus the study group related to application development is recommended to be formed.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1655/1/012104