Abstract
If a piece of disinformation released from a terrorist organization propagates on Twitter and this adversarial campaign is detected after a while, how emergence responders can wisely choose a set of source users to start the counter campaign to minimize the disruptive influence of disinformation in a short time This practical problem is challenging and critical for authorities to make online social networks a more trustworthy source of information. In this work, we propose to study the time critical disinformation influence minimization problem in online social networks based on a continuous-time multiple campaign diffusion model. We show that the complexity of this optimization problem is NP-hard and provide a provable guaranteed approximation algorithm for this problem by proving several critical properties of the objective function. Experimental results on a sample of real online social network show that the proposed approximation algorithm outperforms various heuristics and the transmission temporal dynamics knowledge is vital for selecting the counter campaign source users, especially when the time window is small.
| Original language | English (US) |
|---|---|
| Title of host publication | Proceedings - 2014 IEEE Joint Intelligence and Security Informatics Conference, JISIC 2014 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 68-74 |
| Number of pages | 7 |
| ISBN (Print) | 9781479963645 |
| DOIs | |
| State | Published - Dec 4 2014 |
| Event | 2014 IEEE Joint Intelligence and Security Informatics Conference, JISIC 2014 - The Hague, Netherlands Duration: Sep 24 2014 → Sep 26 2014 |
Other
| Other | 2014 IEEE Joint Intelligence and Security Informatics Conference, JISIC 2014 |
|---|---|
| Country | Netherlands |
| City | The Hague |
| Period | 9/24/14 → 9/26/14 |
Fingerprint
Keywords
- competing campaigns
- disinformation
- information cascades
- social networks
- submodular functions
ASJC Scopus subject areas
- Artificial Intelligence
- Information Systems
- Software
Cite this
Time critical disinformation influence minimization in online social networks. / Luo, Chuan; Cui, Kainan; Zheng, Xiaolong; Zeng, Dajun.
Proceedings - 2014 IEEE Joint Intelligence and Security Informatics Conference, JISIC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 68-74 6975556.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Time critical disinformation influence minimization in online social networks
AU - Luo, Chuan
AU - Cui, Kainan
AU - Zheng, Xiaolong
AU - Zeng, Dajun
PY - 2014/12/4
Y1 - 2014/12/4
N2 - If a piece of disinformation released from a terrorist organization propagates on Twitter and this adversarial campaign is detected after a while, how emergence responders can wisely choose a set of source users to start the counter campaign to minimize the disruptive influence of disinformation in a short time This practical problem is challenging and critical for authorities to make online social networks a more trustworthy source of information. In this work, we propose to study the time critical disinformation influence minimization problem in online social networks based on a continuous-time multiple campaign diffusion model. We show that the complexity of this optimization problem is NP-hard and provide a provable guaranteed approximation algorithm for this problem by proving several critical properties of the objective function. Experimental results on a sample of real online social network show that the proposed approximation algorithm outperforms various heuristics and the transmission temporal dynamics knowledge is vital for selecting the counter campaign source users, especially when the time window is small.
AB - If a piece of disinformation released from a terrorist organization propagates on Twitter and this adversarial campaign is detected after a while, how emergence responders can wisely choose a set of source users to start the counter campaign to minimize the disruptive influence of disinformation in a short time This practical problem is challenging and critical for authorities to make online social networks a more trustworthy source of information. In this work, we propose to study the time critical disinformation influence minimization problem in online social networks based on a continuous-time multiple campaign diffusion model. We show that the complexity of this optimization problem is NP-hard and provide a provable guaranteed approximation algorithm for this problem by proving several critical properties of the objective function. Experimental results on a sample of real online social network show that the proposed approximation algorithm outperforms various heuristics and the transmission temporal dynamics knowledge is vital for selecting the counter campaign source users, especially when the time window is small.
KW - competing campaigns
KW - disinformation
KW - information cascades
KW - social networks
KW - submodular functions
UR - http://www.scopus.com/inward/record.url?scp=84920264370&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84920264370&partnerID=8YFLogxK
U2 - 10.1109/JISIC.2014.20
DO - 10.1109/JISIC.2014.20
M3 - Conference contribution
AN - SCOPUS:84920264370
SN - 9781479963645
SP - 68
EP - 74
BT - Proceedings - 2014 IEEE Joint Intelligence and Security Informatics Conference, JISIC 2014
PB - Institute of Electrical and Electronics Engineers Inc.
ER -