Classification of radical web text using a composite-based method

Research output: Contribution to conferencePaper

Abstract

The spread of terrorism and extremism activities on the Internet has created the need for intelligence gathering via Web and real-time monitoring of potential websites for extremist activities. However, the manual classification for such contents is practically difficult and time-consuming. In response to this challenge, an automated classification system called Composite technique was developed. This is a computational framework that explores the combination of both semantics and syntactic features of textual contents of a Web page. We implemented the framework on a set of extremist Web pages - a dataset that has been subjected to a manual classification process. Thereby, we developed a classification model on the data using the J48 decision algorithm, to generate a measure of how well each page can be classified into their appropriate classes. The classification result obtained from our method when compared with other states of the art, indicated a 96% success rate overall in classifying Web pages when matched against the manual classification.

Conference

ConferenceIEEE International Conference on Computational Science and Computational Intelligence
CountryUnited States
CityLas Vegas
Period13/12/1815/12/18
Internet address

Fingerprint

radicalism
website
terrorism
semantics
monitoring
Internet
time

Keywords

  • extremist
  • posit
  • classification
  • sentiment
  • web pages
  • composite

Cite this

Owoeye, K. O., & Weir, G. R. S. (2018). Classification of radical web text using a composite-based method. Paper presented at IEEE International Conference on Computational Science and Computational Intelligence, Las Vegas, United States.
Owoeye, Kolade Olawande ; Weir, George R. S. / Classification of radical web text using a composite-based method. Paper presented at IEEE International Conference on Computational Science and Computational Intelligence, Las Vegas, United States.7 p.
@conference{462b3aa7160547649843495ceb2c0386,
title = "Classification of radical web text using a composite-based method",
abstract = "The spread of terrorism and extremism activities on the Internet has created the need for intelligence gathering via Web and real-time monitoring of potential websites for extremist activities. However, the manual classification for such contents is practically difficult and time-consuming. In response to this challenge, an automated classification system called Composite technique was developed. This is a computational framework that explores the combination of both semantics and syntactic features of textual contents of a Web page. We implemented the framework on a set of extremist Web pages - a dataset that has been subjected to a manual classification process. Thereby, we developed a classification model on the data using the J48 decision algorithm, to generate a measure of how well each page can be classified into their appropriate classes. The classification result obtained from our method when compared with other states of the art, indicated a 96{\%} success rate overall in classifying Web pages when matched against the manual classification.",
keywords = "extremist, posit, classification, sentiment, web pages, composite",
author = "Owoeye, {Kolade Olawande} and Weir, {George R. S.}",
year = "2018",
month = "12",
day = "13",
language = "English",
note = "IEEE International Conference on Computational Science and Computational Intelligence ; Conference date: 13-12-2018 Through 15-12-2018",
url = "https://americancse.org/events/csci2018/Symposiums",

}

Owoeye, KO & Weir, GRS 2018, 'Classification of radical web text using a composite-based method' Paper presented at IEEE International Conference on Computational Science and Computational Intelligence, Las Vegas, United States, 13/12/18 - 15/12/18, .

Classification of radical web text using a composite-based method. / Owoeye, Kolade Olawande; Weir, George R. S.

2018. Paper presented at IEEE International Conference on Computational Science and Computational Intelligence, Las Vegas, United States.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Classification of radical web text using a composite-based method

AU - Owoeye, Kolade Olawande

AU - Weir, George R. S.

PY - 2018/12/13

Y1 - 2018/12/13

N2 - The spread of terrorism and extremism activities on the Internet has created the need for intelligence gathering via Web and real-time monitoring of potential websites for extremist activities. However, the manual classification for such contents is practically difficult and time-consuming. In response to this challenge, an automated classification system called Composite technique was developed. This is a computational framework that explores the combination of both semantics and syntactic features of textual contents of a Web page. We implemented the framework on a set of extremist Web pages - a dataset that has been subjected to a manual classification process. Thereby, we developed a classification model on the data using the J48 decision algorithm, to generate a measure of how well each page can be classified into their appropriate classes. The classification result obtained from our method when compared with other states of the art, indicated a 96% success rate overall in classifying Web pages when matched against the manual classification.

AB - The spread of terrorism and extremism activities on the Internet has created the need for intelligence gathering via Web and real-time monitoring of potential websites for extremist activities. However, the manual classification for such contents is practically difficult and time-consuming. In response to this challenge, an automated classification system called Composite technique was developed. This is a computational framework that explores the combination of both semantics and syntactic features of textual contents of a Web page. We implemented the framework on a set of extremist Web pages - a dataset that has been subjected to a manual classification process. Thereby, we developed a classification model on the data using the J48 decision algorithm, to generate a measure of how well each page can be classified into their appropriate classes. The classification result obtained from our method when compared with other states of the art, indicated a 96% success rate overall in classifying Web pages when matched against the manual classification.

KW - extremist

KW - posit

KW - classification

KW - sentiment

KW - web pages

KW - composite

M3 - Paper

ER -

Owoeye KO, Weir GRS. Classification of radical web text using a composite-based method. 2018. Paper presented at IEEE International Conference on Computational Science and Computational Intelligence, Las Vegas, United States.