Detecting Spammers on Twitter by Identifying User Behavior and Tweet-Based Features

Authors

  • Dewi W. Wardani Department of Informatics, Universitas Sebelas Maret (UNS), Surakarta, Indonesia
  • Yulia Wardhani Department of Informatics, Universitas Sebelas Maret (UNS), Surakarta, Indonesia

Keywords:

C5.0, Spammer, Detection, Tweet-Based Features, Twitter,

Abstract

Spam is a problem in the delivery of news and communication networks. It has various forms and definitions depend on the type of the network. With millions of users across worldwide, Twitter provides a variety of news and events. However, with the ease of dissemination of news, and allowing users to discuss the stories in their status, these services also open opportunities for another kind of spam. In this study, the proposed spammer detection classifies accounts into a spammer or non-spammer by studying/identifying user behavior and tweet-based features (number of followers, following, mentions and hashtag). The results showed that our proposed approach returns better scores comparing to the result of C5.0 algorithm.

Downloads

Download data is not yet available.

Downloads

Published

2018-07-03

How to Cite

Wardani, D. W., & Wardhani, Y. (2018). Detecting Spammers on Twitter by Identifying User Behavior and Tweet-Based Features. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 10(2-4), 81–84. Retrieved from https://jtec.utem.edu.my/jtec/article/view/4321