Welcome to the InfoSci Platform
Reference Hub9
“TwitterSpamDetector”: A Spam Detection Framework for Twitter

“TwitterSpamDetector”: A Spam Detection Framework for Twitter

Abdullah Talha Kabakus, Resul Kara
Copyright: © 2019 |Volume: 10 |Issue: 3 |Pages: 14
ISSN: 1947-8208|EISSN: 1947-8216|EISBN13: 9781522566960|DOI: 10.4018/IJKSS.2019070101
Cite Article Cite Article

MLA

Kabakus, Abdullah Talha, and Resul Kara. "“TwitterSpamDetector”: A Spam Detection Framework for Twitter." IJKSS vol.10, no.3 2019: pp.1-14. http://doi.org/10.4018/IJKSS.2019070101

APA

Kabakus, A. T. & Kara, R. (2019). “TwitterSpamDetector”: A Spam Detection Framework for Twitter. International Journal of Knowledge and Systems Science (IJKSS), 10(3), 1-14. http://doi.org/10.4018/IJKSS.2019070101

Chicago

Kabakus, Abdullah Talha, and Resul Kara. "“TwitterSpamDetector”: A Spam Detection Framework for Twitter," International Journal of Knowledge and Systems Science (IJKSS) 10, no.3: 1-14. http://doi.org/10.4018/IJKSS.2019070101

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Twitter is the most popular microblogging platform which lets users post status messages called tweets. This popularity and the advanced API provided by Twitter to read and write Twitter data programmatically attracts the attention of spammers as well as legitimate users. Since Twitter has some unique characteristics, the traditional spam detecting methods cannot be directly used to detect spam on Twitter. Therefore, a spam detection framework which is specially designed for Twitter namely TwitterSpamDetector is proposed in this paper. TwitterSpamDetector uses Twitter-specific features to detect spam on Twitter. 77,033 tweets which are posted by 50,490 users collected using the API provided by Twitter. Naive Bayes is used to train TwitterSpamDetector using the selected features of Twitter which clearly classify the spammers from legitimate users. According to the evaluation result, TwitterSpamDetector's accuracy and sensitivity are calculated as 0.943 and 0.913, respectively.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.