TY - GEN
T1 - An End-to-End Framework to Identify Pathogenic Social Media Accounts on Twitter
AU - Shaabani, Elham
AU - Sadeghi Mobarakeh, Ashkan
AU - Alvari, Hamidreza
AU - Shakarian, Paulo
N1 - Funding Information:
Acknowledgments. Some of the authors are supported through the ARO (grant W911NF-15-1-0282).
Publisher Copyright:
© 2019 IEEE.
PY - 2019/6
Y1 - 2019/6
N2 - Pathogenic Social Media (PSM) accounts such as terrorist supporter accounts and fake news writers have the capability of spreading disinformation to viral proportions. Early detection of PSM accounts is crucial as they are likely to be key users to make malicious information 'viral'. In this paper, we adopt the causal inference framework along with graph-based metrics in order to distinguish PSMs from normal users within a short time of their activities. We propose both supervised and semi-supervised approaches without taking the network information and content into account. Results on a real-world the dataset from Twitter accentuates the advantage of our proposed frameworks. We show our approach achieves 0.28 improvement in F1 score over existing approaches with the precision of 0.90 and F1 score of 0.63.
AB - Pathogenic Social Media (PSM) accounts such as terrorist supporter accounts and fake news writers have the capability of spreading disinformation to viral proportions. Early detection of PSM accounts is crucial as they are likely to be key users to make malicious information 'viral'. In this paper, we adopt the causal inference framework along with graph-based metrics in order to distinguish PSMs from normal users within a short time of their activities. We propose both supervised and semi-supervised approaches without taking the network information and content into account. Results on a real-world the dataset from Twitter accentuates the advantage of our proposed frameworks. We show our approach achieves 0.28 improvement in F1 score over existing approaches with the precision of 0.90 and F1 score of 0.63.
KW - Fake account detection
KW - Pathogenic account
KW - bipartite graph analysis
KW - causal reasoning
KW - deep learning approach
UR - http://www.scopus.com/inward/record.url?scp=85066905216&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85066905216&partnerID=8YFLogxK
U2 - 10.1109/ICDIS.2019.00027
DO - 10.1109/ICDIS.2019.00027
M3 - Conference contribution
AN - SCOPUS:85066905216
T3 - Proceedings - 2019 2nd International Conference on Data Intelligence and Security, ICDIS 2019
SP - 128
EP - 135
BT - Proceedings - 2019 2nd International Conference on Data Intelligence and Security, ICDIS 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2nd International Conference on Data Intelligence and Security, ICDIS 2019
Y2 - 28 June 2019 through 30 June 2019
ER -