A model of web page classification using convolutional neural network (CNN): a tool to prevent internet addiction

Siti Hawa, Apandi and Jamaludin, Sallim and Rozlina, Mohamed (2022) A model of web page classification using convolutional neural network (CNN): a tool to prevent internet addiction. In: The 6th National Conference for Postgraduate Research (NCON-PGR 2022) , 15 November 2022 , Virtual Conference, Universiti Malaysia Pahang, Malaysia. p. 113..

[img]
Preview
Pdf
A model of web page classification using convolutional neural network (CNN) _ A tool to prevent internet addiction.pdf

Download (332kB) | Preview

Abstract

Game and Online Video Streaming are the most frequently visited web pages. Internet addiction may be negatively impacted by users who spend too much time on these types of web pages. Access to Game and Online Video Streaming web pages needs to be limited in order to combat the issue of internet addiction. Therefore, a tool that can categorize incoming web pages based on their content is required. This paper is proposing a web page classification model using a Convolutional Neural Network (CNN) to classify the web page whether it is a Game or Online Video Streaming based on the pattern of words in the word cloud image generated from the web page text content. The proposed web page classification model has achieved 85.6% accuracy.

Item Type: Conference or Workshop Item (Lecture)
Uncontrolled Keywords: Web page classification; Deep learning; Convolutional neural network; Word cloud image; Internet addiction.
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76 Computer software
T Technology > T Technology (General)
T Technology > TA Engineering (General). Civil engineering (General)
Faculty/Division: Institute of Postgraduate Studies
Faculty of Computing
Depositing User: Mr Muhamad Firdaus Janih@Jaini
Date Deposited: 07 Feb 2023 04:23
Last Modified: 07 Feb 2023 04:23
URI: http://umpir.ump.edu.my/id/eprint/36925
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item