QuickStop

A Markov optimal stopping approach for quickest misinformation detection

Honghao Wei, Xiaohan Kang, Weina Wang, Lei Ying

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper combines data-driven and model-driven methods for real-time misinformation detection. Our algorithm, named Quick- Stop, is an optimal stopping algorithm based on a probabilistic information spreading model obtained from labeled data. The algorithm consists of an offline machine learning algorithm for learning the probabilistic information spreading model and an online optimal stopping algorithm to detect misinformation. The online detection algorithm has both low computational and memory complexities. Our numerical evaluations with a real-world dataset show that QuickStop outperforms existing misinformation detection algorithms in terms of both accuracy and detection time (number of observations needed for detection). Our evaluations with synthetic data further show that QuickStop is robust to (offline) learning errors.

Original languageEnglish (US)
Title of host publicationSIGMETRICS Performance 2019 - Abstracts of the 2019 SIGMETRICS/Performance Joint International Conference on Measurement and Modeling of Computer Systems
PublisherAssociation for Computing Machinery, Inc
Pages79-80
Number of pages2
ISBN (Electronic)9781450366786
DOIs
StatePublished - Jun 20 2019
Event14th Joint Conference of International Conference on Measurement and Modeling of Computer Systems, SIGMETRICS 2019 and IFIP Performance Conference 2019, SIGMETRICS/Performance 2019 - Phoenix, United States
Duration: Jun 24 2019Jun 28 2019

Publication series

NameSIGMETRICS Performance 2019 - Abstracts of the 2019 SIGMETRICS/Performance Joint International Conference on Measurement and Modeling of Computer Systems

Conference

Conference14th Joint Conference of International Conference on Measurement and Modeling of Computer Systems, SIGMETRICS 2019 and IFIP Performance Conference 2019, SIGMETRICS/Performance 2019
CountryUnited States
CityPhoenix
Period6/24/196/28/19

Fingerprint

Learning algorithms
Learning systems
Data storage equipment

Keywords

  • Fake news
  • Misinformation detection
  • Quickest detection
  • Social networks

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Networks and Communications
  • Hardware and Architecture

Cite this

Wei, H., Kang, X., Wang, W., & Ying, L. (2019). QuickStop: A Markov optimal stopping approach for quickest misinformation detection. In SIGMETRICS Performance 2019 - Abstracts of the 2019 SIGMETRICS/Performance Joint International Conference on Measurement and Modeling of Computer Systems (pp. 79-80). (SIGMETRICS Performance 2019 - Abstracts of the 2019 SIGMETRICS/Performance Joint International Conference on Measurement and Modeling of Computer Systems). Association for Computing Machinery, Inc. https://doi.org/10.1145/3309697.3331513

QuickStop : A Markov optimal stopping approach for quickest misinformation detection. / Wei, Honghao; Kang, Xiaohan; Wang, Weina; Ying, Lei.

SIGMETRICS Performance 2019 - Abstracts of the 2019 SIGMETRICS/Performance Joint International Conference on Measurement and Modeling of Computer Systems. Association for Computing Machinery, Inc, 2019. p. 79-80 (SIGMETRICS Performance 2019 - Abstracts of the 2019 SIGMETRICS/Performance Joint International Conference on Measurement and Modeling of Computer Systems).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wei, H, Kang, X, Wang, W & Ying, L 2019, QuickStop: A Markov optimal stopping approach for quickest misinformation detection. in SIGMETRICS Performance 2019 - Abstracts of the 2019 SIGMETRICS/Performance Joint International Conference on Measurement and Modeling of Computer Systems. SIGMETRICS Performance 2019 - Abstracts of the 2019 SIGMETRICS/Performance Joint International Conference on Measurement and Modeling of Computer Systems, Association for Computing Machinery, Inc, pp. 79-80, 14th Joint Conference of International Conference on Measurement and Modeling of Computer Systems, SIGMETRICS 2019 and IFIP Performance Conference 2019, SIGMETRICS/Performance 2019, Phoenix, United States, 6/24/19. https://doi.org/10.1145/3309697.3331513
Wei H, Kang X, Wang W, Ying L. QuickStop: A Markov optimal stopping approach for quickest misinformation detection. In SIGMETRICS Performance 2019 - Abstracts of the 2019 SIGMETRICS/Performance Joint International Conference on Measurement and Modeling of Computer Systems. Association for Computing Machinery, Inc. 2019. p. 79-80. (SIGMETRICS Performance 2019 - Abstracts of the 2019 SIGMETRICS/Performance Joint International Conference on Measurement and Modeling of Computer Systems). https://doi.org/10.1145/3309697.3331513
Wei, Honghao ; Kang, Xiaohan ; Wang, Weina ; Ying, Lei. / QuickStop : A Markov optimal stopping approach for quickest misinformation detection. SIGMETRICS Performance 2019 - Abstracts of the 2019 SIGMETRICS/Performance Joint International Conference on Measurement and Modeling of Computer Systems. Association for Computing Machinery, Inc, 2019. pp. 79-80 (SIGMETRICS Performance 2019 - Abstracts of the 2019 SIGMETRICS/Performance Joint International Conference on Measurement and Modeling of Computer Systems).
@inproceedings{d8ebdb015f3d4df5a31c734e61147a71,
title = "QuickStop: A Markov optimal stopping approach for quickest misinformation detection",
abstract = "This paper combines data-driven and model-driven methods for real-time misinformation detection. Our algorithm, named Quick- Stop, is an optimal stopping algorithm based on a probabilistic information spreading model obtained from labeled data. The algorithm consists of an offline machine learning algorithm for learning the probabilistic information spreading model and an online optimal stopping algorithm to detect misinformation. The online detection algorithm has both low computational and memory complexities. Our numerical evaluations with a real-world dataset show that QuickStop outperforms existing misinformation detection algorithms in terms of both accuracy and detection time (number of observations needed for detection). Our evaluations with synthetic data further show that QuickStop is robust to (offline) learning errors.",
keywords = "Fake news, Misinformation detection, Quickest detection, Social networks",
author = "Honghao Wei and Xiaohan Kang and Weina Wang and Lei Ying",
year = "2019",
month = "6",
day = "20",
doi = "10.1145/3309697.3331513",
language = "English (US)",
series = "SIGMETRICS Performance 2019 - Abstracts of the 2019 SIGMETRICS/Performance Joint International Conference on Measurement and Modeling of Computer Systems",
publisher = "Association for Computing Machinery, Inc",
pages = "79--80",
booktitle = "SIGMETRICS Performance 2019 - Abstracts of the 2019 SIGMETRICS/Performance Joint International Conference on Measurement and Modeling of Computer Systems",

}

TY - GEN

T1 - QuickStop

T2 - A Markov optimal stopping approach for quickest misinformation detection

AU - Wei, Honghao

AU - Kang, Xiaohan

AU - Wang, Weina

AU - Ying, Lei

PY - 2019/6/20

Y1 - 2019/6/20

N2 - This paper combines data-driven and model-driven methods for real-time misinformation detection. Our algorithm, named Quick- Stop, is an optimal stopping algorithm based on a probabilistic information spreading model obtained from labeled data. The algorithm consists of an offline machine learning algorithm for learning the probabilistic information spreading model and an online optimal stopping algorithm to detect misinformation. The online detection algorithm has both low computational and memory complexities. Our numerical evaluations with a real-world dataset show that QuickStop outperforms existing misinformation detection algorithms in terms of both accuracy and detection time (number of observations needed for detection). Our evaluations with synthetic data further show that QuickStop is robust to (offline) learning errors.

AB - This paper combines data-driven and model-driven methods for real-time misinformation detection. Our algorithm, named Quick- Stop, is an optimal stopping algorithm based on a probabilistic information spreading model obtained from labeled data. The algorithm consists of an offline machine learning algorithm for learning the probabilistic information spreading model and an online optimal stopping algorithm to detect misinformation. The online detection algorithm has both low computational and memory complexities. Our numerical evaluations with a real-world dataset show that QuickStop outperforms existing misinformation detection algorithms in terms of both accuracy and detection time (number of observations needed for detection). Our evaluations with synthetic data further show that QuickStop is robust to (offline) learning errors.

KW - Fake news

KW - Misinformation detection

KW - Quickest detection

KW - Social networks

UR - http://www.scopus.com/inward/record.url?scp=85069187623&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069187623&partnerID=8YFLogxK

U2 - 10.1145/3309697.3331513

DO - 10.1145/3309697.3331513

M3 - Conference contribution

T3 - SIGMETRICS Performance 2019 - Abstracts of the 2019 SIGMETRICS/Performance Joint International Conference on Measurement and Modeling of Computer Systems

SP - 79

EP - 80

BT - SIGMETRICS Performance 2019 - Abstracts of the 2019 SIGMETRICS/Performance Joint International Conference on Measurement and Modeling of Computer Systems

PB - Association for Computing Machinery, Inc

ER -