6 Citations (Scopus)

Abstract

With the humongous amount of news stories published daily and the range of ways (RSS feeds, blogs etc) to disseminate them, even an expert at tracking new developing stories can feel the information overload. At most times, when a user is reading a news story, she would like to know "what happened before this?" or "how things progressed after this incident?". In this paper, we present a novel real-time yet simple method to detect and track new events related to violence and terrorism in news streams through their life over a time line. We do this by first extracting signature of the event, at microscopic level rather than topic or macroscopic level, and then tracking and linking this event with mentions of same event signature in other incoming news articles. There by forming a thread that links all the news articles that describe this specific event, with no training data used or machine learning algorithms employed. We also present our experimental evaluations conducted with Document Understand Conference (DUC) datasets that validate our observations and methodology.

Original languageEnglish (US)
Title of host publication2009 IEEE International Conference on Intelligence and Security Informatics, ISI 2009
Pages182-184
Number of pages3
DOIs
StatePublished - 2009
Event2009 IEEE International Conference on Intelligence and Security Informatics, ISI 2009 - Dallas, TX, United States
Duration: Jun 8 2009Jun 11 2009

Other

Other2009 IEEE International Conference on Intelligence and Security Informatics, ISI 2009
CountryUnited States
CityDallas, TX
Period6/8/096/11/09

Fingerprint

RSS
Terrorism
Blogs
Learning algorithms
Learning systems
Violence

Keywords

  • Event detection
  • First story detection
  • Named entity recognition
  • News threads extraction

ASJC Scopus subject areas

  • Artificial Intelligence
  • Information Systems
  • Software

Cite this

Ahmed, S. T., Bhindwale, R., & Davulcu, H. (2009). Tracking terrorism news threads by extracting event signatures. In 2009 IEEE International Conference on Intelligence and Security Informatics, ISI 2009 (pp. 182-184). [5137296] https://doi.org/10.1109/ISI.2009.5137296

Tracking terrorism news threads by extracting event signatures. / Ahmed, Syed Toufeeq; Bhindwale, Ruchi; Davulcu, Hasan.

2009 IEEE International Conference on Intelligence and Security Informatics, ISI 2009. 2009. p. 182-184 5137296.

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

Ahmed, ST, Bhindwale, R & Davulcu, H 2009, Tracking terrorism news threads by extracting event signatures. in 2009 IEEE International Conference on Intelligence and Security Informatics, ISI 2009., 5137296, pp. 182-184, 2009 IEEE International Conference on Intelligence and Security Informatics, ISI 2009, Dallas, TX, United States, 6/8/09. https://doi.org/10.1109/ISI.2009.5137296
Ahmed ST, Bhindwale R, Davulcu H. Tracking terrorism news threads by extracting event signatures. In 2009 IEEE International Conference on Intelligence and Security Informatics, ISI 2009. 2009. p. 182-184. 5137296 https://doi.org/10.1109/ISI.2009.5137296
Ahmed, Syed Toufeeq ; Bhindwale, Ruchi ; Davulcu, Hasan. / Tracking terrorism news threads by extracting event signatures. 2009 IEEE International Conference on Intelligence and Security Informatics, ISI 2009. 2009. pp. 182-184
@inproceedings{06d42ce9b60e4caabb606cf588a49218,
title = "Tracking terrorism news threads by extracting event signatures",
abstract = "With the humongous amount of news stories published daily and the range of ways (RSS feeds, blogs etc) to disseminate them, even an expert at tracking new developing stories can feel the information overload. At most times, when a user is reading a news story, she would like to know {"}what happened before this?{"} or {"}how things progressed after this incident?{"}. In this paper, we present a novel real-time yet simple method to detect and track new events related to violence and terrorism in news streams through their life over a time line. We do this by first extracting signature of the event, at microscopic level rather than topic or macroscopic level, and then tracking and linking this event with mentions of same event signature in other incoming news articles. There by forming a thread that links all the news articles that describe this specific event, with no training data used or machine learning algorithms employed. We also present our experimental evaluations conducted with Document Understand Conference (DUC) datasets that validate our observations and methodology.",
keywords = "Event detection, First story detection, Named entity recognition, News threads extraction",
author = "Ahmed, {Syed Toufeeq} and Ruchi Bhindwale and Hasan Davulcu",
year = "2009",
doi = "10.1109/ISI.2009.5137296",
language = "English (US)",
isbn = "9781424441730",
pages = "182--184",
booktitle = "2009 IEEE International Conference on Intelligence and Security Informatics, ISI 2009",

}

TY - GEN

T1 - Tracking terrorism news threads by extracting event signatures

AU - Ahmed, Syed Toufeeq

AU - Bhindwale, Ruchi

AU - Davulcu, Hasan

PY - 2009

Y1 - 2009

N2 - With the humongous amount of news stories published daily and the range of ways (RSS feeds, blogs etc) to disseminate them, even an expert at tracking new developing stories can feel the information overload. At most times, when a user is reading a news story, she would like to know "what happened before this?" or "how things progressed after this incident?". In this paper, we present a novel real-time yet simple method to detect and track new events related to violence and terrorism in news streams through their life over a time line. We do this by first extracting signature of the event, at microscopic level rather than topic or macroscopic level, and then tracking and linking this event with mentions of same event signature in other incoming news articles. There by forming a thread that links all the news articles that describe this specific event, with no training data used or machine learning algorithms employed. We also present our experimental evaluations conducted with Document Understand Conference (DUC) datasets that validate our observations and methodology.

AB - With the humongous amount of news stories published daily and the range of ways (RSS feeds, blogs etc) to disseminate them, even an expert at tracking new developing stories can feel the information overload. At most times, when a user is reading a news story, she would like to know "what happened before this?" or "how things progressed after this incident?". In this paper, we present a novel real-time yet simple method to detect and track new events related to violence and terrorism in news streams through their life over a time line. We do this by first extracting signature of the event, at microscopic level rather than topic or macroscopic level, and then tracking and linking this event with mentions of same event signature in other incoming news articles. There by forming a thread that links all the news articles that describe this specific event, with no training data used or machine learning algorithms employed. We also present our experimental evaluations conducted with Document Understand Conference (DUC) datasets that validate our observations and methodology.

KW - Event detection

KW - First story detection

KW - Named entity recognition

KW - News threads extraction

UR - http://www.scopus.com/inward/record.url?scp=70350075654&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70350075654&partnerID=8YFLogxK

U2 - 10.1109/ISI.2009.5137296

DO - 10.1109/ISI.2009.5137296

M3 - Conference contribution

AN - SCOPUS:70350075654

SN - 9781424441730

SP - 182

EP - 184

BT - 2009 IEEE International Conference on Intelligence and Security Informatics, ISI 2009

ER -