Skip to main content

Research Repository

Advanced Search

Emotional bots: Content-based spammer detection on social media

Andriotis, Panagiotis; Takasu, Atsuhiro

Emotional bots: Content-based spammer detection on social media Thumbnail


Authors

Profile Image

Dr Panos Andriotis Panagiotis.Andriotis@uwe.ac.uk
Senior Lecturer in Computer Forensics and Security

Atsuhiro Takasu



Abstract

Recent research indicates that a considerable amount
of content on social media is generated by automated accounts. The automata present sophisticated behavior –
mimicking humans– aiming at evading traditional detection
methods. In this paper, we present a supervised approach to detect automated accounts on Twitter using mainly content-based features. We performed our experiments using four datasets that contain tweets from almost 20K malicious and benign accounts. Our methodology is lightweight and employs users’ metadata, content and sentiment features. It performs well on unseen data (0.95 F1-score) reaching 95% precision and recall. This work also demonstrates that sentiment characteristics can add value to social spambot detection algorithms when combined with known features.

Citation

Andriotis, P., & Takasu, A. (2019). Emotional bots: Content-based spammer detection on social media. https://doi.org/10.1109/WIFS.2018.8630760

Conference Name 10th IEEE International Workshop on Information Forensics and Security, WIFS 2018
Start Date Dec 11, 2018
End Date Dec 13, 2018
Acceptance Date Aug 31, 2018
Online Publication Date Jan 31, 2019
Publication Date Jan 31, 2019
Deposit Date Sep 6, 2018
Publicly Available Date Mar 1, 2019
Publisher Institute of Electrical and Electronics Engineers (IEEE)
Peer Reviewed Peer Reviewed
Pages 1-8
Series Title 2018 IEEE International Workshop on Information Forensics and Security (WIFS)
Series ISSN 2157-4774
ISBN 9781538665367
DOI https://doi.org/10.1109/WIFS.2018.8630760
Keywords Twitter , Feature extraction , Metadata , Sentiment analysis , Uniform resource locators , Mathematical model
Public URL https://uwe-repository.worktribe.com/output/873044
Additional Information Title of Conference or Conference Proceedings : IEEE International Workshop on Information Forensics and Security (WIFS)

Files







You might also like



Downloadable Citations