Detect rumors using time series of social context information on microblogging

Jing Ma, Wei Gao, Zhongyu Wei, Yueming Lu, Kam Fai Wong

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Automatically identifying rumors from online social media especially microblogging websites is an important research issue. Most of existing work for rumor detection focuses on modeling features related to microblog contents, users and propagation patterns, but ignore the importance of the variation of these social context features during the message propagation over time. In this study, we propose a novel approach to capture the temporal characteristics of these features based on the time series of rumor’s lifecycle, for which time series modeling technique is applied to incorporate various social context information. Our experiments using the events in two microblog datasets confirm that the method outperforms state-of-the-art rumor detection approaches by large margins. Moreover, our model demonstrates strong performance on detecting rumors at early stage after their initial broadcast.

Original languageEnglish
Title of host publicationSocial Media Content Analysis
Subtitle of host publicationNatural Language Processing and Beyond
PublisherWorld Scientific Publishing Co. Pte Ltd
Pages67-77
Number of pages11
ISBN (Electronic)9789813223615
ISBN (Print)9789813223608
DOIs
Publication statusPublished - 1 Jan 2017

Fingerprint

Time series
Websites
Experiments

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Ma, J., Gao, W., Wei, Z., Lu, Y., & Wong, K. F. (2017). Detect rumors using time series of social context information on microblogging. In Social Media Content Analysis: Natural Language Processing and Beyond (pp. 67-77). World Scientific Publishing Co. Pte Ltd. https://doi.org/10.1142/9789813223615_0006

Detect rumors using time series of social context information on microblogging. / Ma, Jing; Gao, Wei; Wei, Zhongyu; Lu, Yueming; Wong, Kam Fai.

Social Media Content Analysis: Natural Language Processing and Beyond. World Scientific Publishing Co. Pte Ltd, 2017. p. 67-77.

Research output: Chapter in Book/Report/Conference proceedingChapter

Ma, J, Gao, W, Wei, Z, Lu, Y & Wong, KF 2017, Detect rumors using time series of social context information on microblogging. in Social Media Content Analysis: Natural Language Processing and Beyond. World Scientific Publishing Co. Pte Ltd, pp. 67-77. https://doi.org/10.1142/9789813223615_0006
Ma J, Gao W, Wei Z, Lu Y, Wong KF. Detect rumors using time series of social context information on microblogging. In Social Media Content Analysis: Natural Language Processing and Beyond. World Scientific Publishing Co. Pte Ltd. 2017. p. 67-77 https://doi.org/10.1142/9789813223615_0006
Ma, Jing ; Gao, Wei ; Wei, Zhongyu ; Lu, Yueming ; Wong, Kam Fai. / Detect rumors using time series of social context information on microblogging. Social Media Content Analysis: Natural Language Processing and Beyond. World Scientific Publishing Co. Pte Ltd, 2017. pp. 67-77
@inbook{d0ba9690e1654e3784f979e89115a24b,
title = "Detect rumors using time series of social context information on microblogging",
abstract = "Automatically identifying rumors from online social media especially microblogging websites is an important research issue. Most of existing work for rumor detection focuses on modeling features related to microblog contents, users and propagation patterns, but ignore the importance of the variation of these social context features during the message propagation over time. In this study, we propose a novel approach to capture the temporal characteristics of these features based on the time series of rumor’s lifecycle, for which time series modeling technique is applied to incorporate various social context information. Our experiments using the events in two microblog datasets confirm that the method outperforms state-of-the-art rumor detection approaches by large margins. Moreover, our model demonstrates strong performance on detecting rumors at early stage after their initial broadcast.",
author = "Jing Ma and Wei Gao and Zhongyu Wei and Yueming Lu and Wong, {Kam Fai}",
year = "2017",
month = "1",
day = "1",
doi = "10.1142/9789813223615_0006",
language = "English",
isbn = "9789813223608",
pages = "67--77",
booktitle = "Social Media Content Analysis",
publisher = "World Scientific Publishing Co. Pte Ltd",
address = "Singapore",

}

TY - CHAP

T1 - Detect rumors using time series of social context information on microblogging

AU - Ma, Jing

AU - Gao, Wei

AU - Wei, Zhongyu

AU - Lu, Yueming

AU - Wong, Kam Fai

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Automatically identifying rumors from online social media especially microblogging websites is an important research issue. Most of existing work for rumor detection focuses on modeling features related to microblog contents, users and propagation patterns, but ignore the importance of the variation of these social context features during the message propagation over time. In this study, we propose a novel approach to capture the temporal characteristics of these features based on the time series of rumor’s lifecycle, for which time series modeling technique is applied to incorporate various social context information. Our experiments using the events in two microblog datasets confirm that the method outperforms state-of-the-art rumor detection approaches by large margins. Moreover, our model demonstrates strong performance on detecting rumors at early stage after their initial broadcast.

AB - Automatically identifying rumors from online social media especially microblogging websites is an important research issue. Most of existing work for rumor detection focuses on modeling features related to microblog contents, users and propagation patterns, but ignore the importance of the variation of these social context features during the message propagation over time. In this study, we propose a novel approach to capture the temporal characteristics of these features based on the time series of rumor’s lifecycle, for which time series modeling technique is applied to incorporate various social context information. Our experiments using the events in two microblog datasets confirm that the method outperforms state-of-the-art rumor detection approaches by large margins. Moreover, our model demonstrates strong performance on detecting rumors at early stage after their initial broadcast.

UR - http://www.scopus.com/inward/record.url?scp=85041560800&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041560800&partnerID=8YFLogxK

U2 - 10.1142/9789813223615_0006

DO - 10.1142/9789813223615_0006

M3 - Chapter

AN - SCOPUS:85041560800

SN - 9789813223608

SP - 67

EP - 77

BT - Social Media Content Analysis

PB - World Scientific Publishing Co. Pte Ltd

ER -