Extracting Events from Web Documents for Social Media Monitoring Using Structured SVM

Yoonjae CHOI; Pum-Mo RYU; Hyunki KIM; Changki LEE

doi:10.1587/transinf.E96.D.1410

Extracting Events from Web Documents for Social Media Monitoring Using Structured SVM

Yoonjae CHOI, Pum-Mo RYU, Hyunki KIM, Changki LEE

Full Text Views

0

Share
Cite this

Summary :

Event extraction is vital to social media monitoring and social event prediction. In this paper, we propose a method for social event extraction from web documents by identifying binary relations between named entities. There have been many studies on relation extraction, but their aims were mostly academic. For practical application, we try to identify 130 relation types that comprise 31 predefined event types, which address business and public issues. We use structured Support Vector Machine, the state of the art classifier to capture relations. We apply our method on news, blogs and tweets collected from the Internet and discuss the results.

Publication: IEICE TRANSACTIONS on Information Vol.E96-D No.6 pp.1410-1414

Publication Date: 2013/06/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E96.D.1410

Type of Manuscript: LETTER

Category: Natural Language Processing

Authors

Yoonjae CHOI
  ETRI
Pum-Mo RYU
  ETRI
Hyunki KIM
  ETRI
Changki LEE
  Kangwon National University

Keyword

relation extraction, structured SVM, natural language processing, information extraction

Cite this

Copy

Yoonjae CHOI, Pum-Mo RYU, Hyunki KIM, Changki LEE, "Extracting Events from Web Documents for Social Media Monitoring Using Structured SVM" in IEICE TRANSACTIONS on Information, vol. E96-D, no. 6, pp. 1410-1414, June 2013, doi: 10.1587/transinf.E96.D.1410.
Abstract: Event extraction is vital to social media monitoring and social event prediction. In this paper, we propose a method for social event extraction from web documents by identifying binary relations between named entities. There have been many studies on relation extraction, but their aims were mostly academic. For practical application, we try to identify 130 relation types that comprise 31 predefined event types, which address business and public issues. We use structured Support Vector Machine, the state of the art classifier to capture relations. We apply our method on news, blogs and tweets collected from the Internet and discuss the results.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E96.D.1410/_p

Copy

@ARTICLE{e96-d_6_1410,
author={Yoonjae CHOI, Pum-Mo RYU, Hyunki KIM, Changki LEE, },
journal={IEICE TRANSACTIONS on Information},
title={Extracting Events from Web Documents for Social Media Monitoring Using Structured SVM},
year={2013},
volume={E96-D},
number={6},
pages={1410-1414},
abstract={Event extraction is vital to social media monitoring and social event prediction. In this paper, we propose a method for social event extraction from web documents by identifying binary relations between named entities. There have been many studies on relation extraction, but their aims were mostly academic. For practical application, we try to identify 130 relation types that comprise 31 predefined event types, which address business and public issues. We use structured Support Vector Machine, the state of the art classifier to capture relations. We apply our method on news, blogs and tweets collected from the Internet and discuss the results.},
keywords={},
doi={10.1587/transinf.E96.D.1410},
ISSN={1745-1361},
month={June},}

Copy

TY - JOUR
TI - Extracting Events from Web Documents for Social Media Monitoring Using Structured SVM
T2 - IEICE TRANSACTIONS on Information
SP - 1410
EP - 1414
AU - Yoonjae CHOI
AU - Pum-Mo RYU
AU - Hyunki KIM
AU - Changki LEE
PY - 2013
DO - 10.1587/transinf.E96.D.1410
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E96-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2013
AB - Event extraction is vital to social media monitoring and social event prediction. In this paper, we propose a method for social event extraction from web documents by identifying binary relations between named entities. There have been many studies on relation extraction, but their aims were mostly academic. For practical application, we try to identify 130 relation types that comprise 31 predefined event types, which address business and public issues. We use structured Support Vector Machine, the state of the art classifier to capture relations. We apply our method on news, blogs and tweets collected from the Internet and discuss the results.
ER -