Title

Twitter Bot Detection using Social Network Analysis

Publication Date

1-1-2022

Document Type

Conference Proceeding

Publication Title

Proceedings - 2022 4th International Conference on Transdisciplinary AI, TransAI 2022

DOI

10.1109/TransAI54797.2022.00022

First Page

87

Last Page

88

Abstract

Twitter is an online platform that provides social networking services for hundreds of millions of active accounts. However, an estimation of 48 million accounts on Twitter are not human. These accounts are bots, which are automated software that control accounts. Identifying Twitter bots is desirable as human can view Twitter bots as a credible source of information. Existing methods to detect Twitter bots are mainly feature-based and text-based. In this paper, we propose a graph-based approach to detect Twitter bots as an alternative to the traditional bot detection methods. The paper outlines the data collection process, behaviors to observe in an account, and a proposal for a machine learning classifier utilizing these behaviors.

Keywords

graph classification, machine learning, social network analysis, Twitter bots

Department

Computer Science

COinS