Abstract

The automatic and early detection of rumors is of paramount importance as the spread of information with questionable veracity can have devastating consequences. This became starkly apparent when, in early 2013, a compromised Associated Press account issued a tweet claiming that there had been an explosion at the White House. This tweet resulted in a significant drop for the Dow Jones Industrial Average. Most existing work in rumor detection leverages conversation statistics and propagation patterns, however, such patterns tend to emerge slowly requiring a conversation to have a significant number of interactions in order to become eligible for classification. In this work, we propose a method for classifying conversations within their formative stages as well as improving accuracy within mature conversations through the discovery of implicit linkages between conversation fragments. In our experiments, we show that current state-of-the-art rumor classification methods can leverage implicit links to significantly improve the ability to properly classify emergent conversations when very little conversation data is available. Adopting this technique allows rumor detection methods to continue to provide a high degree of classification accuracy on emergent conversations with as few as a single tweet. This improvement virtually eliminates the delay of conversation growth inherent in current rumor classification methods while significantly increasing the number of conversations considered viable for classification.

Original languageEnglish (US)
Title of host publicationCIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management
PublisherAssociation for Computing Machinery
Pages2377-2382
Number of pages6
Volume24-28-October-2016
ISBN (Electronic)9781450340731
DOIs
StatePublished - Oct 24 2016
Event25th ACM International Conference on Information and Knowledge Management, CIKM 2016 - Indianapolis, United States
Duration: Oct 24 2016Oct 28 2016

Other

Other25th ACM International Conference on Information and Knowledge Management, CIKM 2016
CountryUnited States
CityIndianapolis
Period10/24/1610/28/16

Fingerprint

Social media
Rumor
Leverage
Propagation
Interaction
Linkage
Experiment
Statistics
Explosion

ASJC Scopus subject areas

  • Business, Management and Accounting(all)
  • Decision Sciences(all)

Cite this

Sampson, J., Morstatter, F., Wu, L., & Liu, H. (2016). Leveraging the implicit structure within social media for emergent rumor detection. In CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management (Vol. 24-28-October-2016, pp. 2377-2382). Association for Computing Machinery. https://doi.org/10.1145/2983323.2983697

Leveraging the implicit structure within social media for emergent rumor detection. / Sampson, Justin; Morstatter, Fred; Wu, Liang; Liu, Huan.

CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management. Vol. 24-28-October-2016 Association for Computing Machinery, 2016. p. 2377-2382.

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

Sampson, J, Morstatter, F, Wu, L & Liu, H 2016, Leveraging the implicit structure within social media for emergent rumor detection. in CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management. vol. 24-28-October-2016, Association for Computing Machinery, pp. 2377-2382, 25th ACM International Conference on Information and Knowledge Management, CIKM 2016, Indianapolis, United States, 10/24/16. https://doi.org/10.1145/2983323.2983697
Sampson J, Morstatter F, Wu L, Liu H. Leveraging the implicit structure within social media for emergent rumor detection. In CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management. Vol. 24-28-October-2016. Association for Computing Machinery. 2016. p. 2377-2382 https://doi.org/10.1145/2983323.2983697
Sampson, Justin ; Morstatter, Fred ; Wu, Liang ; Liu, Huan. / Leveraging the implicit structure within social media for emergent rumor detection. CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management. Vol. 24-28-October-2016 Association for Computing Machinery, 2016. pp. 2377-2382
@inproceedings{b8288e1d61c24fc6b7a2771dbfab759b,
title = "Leveraging the implicit structure within social media for emergent rumor detection",
abstract = "The automatic and early detection of rumors is of paramount importance as the spread of information with questionable veracity can have devastating consequences. This became starkly apparent when, in early 2013, a compromised Associated Press account issued a tweet claiming that there had been an explosion at the White House. This tweet resulted in a significant drop for the Dow Jones Industrial Average. Most existing work in rumor detection leverages conversation statistics and propagation patterns, however, such patterns tend to emerge slowly requiring a conversation to have a significant number of interactions in order to become eligible for classification. In this work, we propose a method for classifying conversations within their formative stages as well as improving accuracy within mature conversations through the discovery of implicit linkages between conversation fragments. In our experiments, we show that current state-of-the-art rumor classification methods can leverage implicit links to significantly improve the ability to properly classify emergent conversations when very little conversation data is available. Adopting this technique allows rumor detection methods to continue to provide a high degree of classification accuracy on emergent conversations with as few as a single tweet. This improvement virtually eliminates the delay of conversation growth inherent in current rumor classification methods while significantly increasing the number of conversations considered viable for classification.",
author = "Justin Sampson and Fred Morstatter and Liang Wu and Huan Liu",
year = "2016",
month = "10",
day = "24",
doi = "10.1145/2983323.2983697",
language = "English (US)",
volume = "24-28-October-2016",
pages = "2377--2382",
booktitle = "CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - Leveraging the implicit structure within social media for emergent rumor detection

AU - Sampson, Justin

AU - Morstatter, Fred

AU - Wu, Liang

AU - Liu, Huan

PY - 2016/10/24

Y1 - 2016/10/24

N2 - The automatic and early detection of rumors is of paramount importance as the spread of information with questionable veracity can have devastating consequences. This became starkly apparent when, in early 2013, a compromised Associated Press account issued a tweet claiming that there had been an explosion at the White House. This tweet resulted in a significant drop for the Dow Jones Industrial Average. Most existing work in rumor detection leverages conversation statistics and propagation patterns, however, such patterns tend to emerge slowly requiring a conversation to have a significant number of interactions in order to become eligible for classification. In this work, we propose a method for classifying conversations within their formative stages as well as improving accuracy within mature conversations through the discovery of implicit linkages between conversation fragments. In our experiments, we show that current state-of-the-art rumor classification methods can leverage implicit links to significantly improve the ability to properly classify emergent conversations when very little conversation data is available. Adopting this technique allows rumor detection methods to continue to provide a high degree of classification accuracy on emergent conversations with as few as a single tweet. This improvement virtually eliminates the delay of conversation growth inherent in current rumor classification methods while significantly increasing the number of conversations considered viable for classification.

AB - The automatic and early detection of rumors is of paramount importance as the spread of information with questionable veracity can have devastating consequences. This became starkly apparent when, in early 2013, a compromised Associated Press account issued a tweet claiming that there had been an explosion at the White House. This tweet resulted in a significant drop for the Dow Jones Industrial Average. Most existing work in rumor detection leverages conversation statistics and propagation patterns, however, such patterns tend to emerge slowly requiring a conversation to have a significant number of interactions in order to become eligible for classification. In this work, we propose a method for classifying conversations within their formative stages as well as improving accuracy within mature conversations through the discovery of implicit linkages between conversation fragments. In our experiments, we show that current state-of-the-art rumor classification methods can leverage implicit links to significantly improve the ability to properly classify emergent conversations when very little conversation data is available. Adopting this technique allows rumor detection methods to continue to provide a high degree of classification accuracy on emergent conversations with as few as a single tweet. This improvement virtually eliminates the delay of conversation growth inherent in current rumor classification methods while significantly increasing the number of conversations considered viable for classification.

UR - http://www.scopus.com/inward/record.url?scp=84996503647&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84996503647&partnerID=8YFLogxK

U2 - 10.1145/2983323.2983697

DO - 10.1145/2983323.2983697

M3 - Conference contribution

AN - SCOPUS:84996503647

VL - 24-28-October-2016

SP - 2377

EP - 2382

BT - CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management

PB - Association for Computing Machinery

ER -