Unsupervised Fact-finding with Multi-modal Data in Social Sensing

Huajie Shao, Shuochao Yao, Yiran Zhao, Lu Su, Zhibo Wang, Dongxin Liu, Shengzhong Liu, Lance Kaplan, Tarek Abdelzaher

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

Abstract

This paper develops unsupervised fact-finding algorithms that combine consideration of multi-modal microblog content features with analysis of propagation patterns to determine veracity of microblog observations. In contrast to prior solutions that use labeled examples to learn content features that are correlated with veracity, our approach is entirely unsupervised. Hence, given no prior training data, we jointly learn the importance of different content features together with the veracity of observations using propagation patterns as an indicator of perceived content reliability. To offer robustness, we describe fact-finding extensions that handle the existence of malicious colluding sources. We evaluate the performance of the proposed algorithms on real-world data sets collected from Twitter. The evaluation results demonstrate that the proposed algorithms outperform the existing fact-finding approaches, and offer tunable knobs for controlling robustness/performance trade-offs in the presence of malicious sources.

Original languageEnglish (US)
Title of host publicationFUSION 2019 - 22nd International Conference on Information Fusion
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9780996452786
StatePublished - Jul 2019
Event22nd International Conference on Information Fusion, FUSION 2019 - Ottawa, Canada
Duration: Jul 2 2019Jul 5 2019

Publication series

NameFUSION 2019 - 22nd International Conference on Information Fusion

Conference

Conference22nd International Conference on Information Fusion, FUSION 2019
CountryCanada
CityOttawa
Period7/2/197/5/19

Keywords

  • estimation accuracy
  • multi-modal data
  • penalized expectation maximization (PEM)
  • social networks
  • truth discovery

ASJC Scopus subject areas

  • Information Systems
  • Instrumentation

Fingerprint Dive into the research topics of 'Unsupervised Fact-finding with Multi-modal Data in Social Sensing'. Together they form a unique fingerprint.

  • Cite this

    Shao, H., Yao, S., Zhao, Y., Su, L., Wang, Z., Liu, D., Liu, S., Kaplan, L., & Abdelzaher, T. (2019). Unsupervised Fact-finding with Multi-modal Data in Social Sensing. In FUSION 2019 - 22nd International Conference on Information Fusion [9011270] (FUSION 2019 - 22nd International Conference on Information Fusion). Institute of Electrical and Electronics Engineers Inc..