Event detection with spatial latent Dirichlet allocation

Chi Chun Pan, Prasenjit Mitra

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

34 Citations (Scopus)

Abstract

A large number of news articles are generated every day on the Web. Automatically identifying events from a large document collection is a challenging problem. In this paper, we propose two event detection approaches using generative models. We combine the popular LDA model with temporal segmentation and spatial clustering. In addition, we adapt an image segmentation model, SLDA, for spatial-temporal event detection on text. The results of our experiments show that both approaches outperform the traditional content-based clustering approaches on our datasets.

Original languageEnglish (US)
Title of host publicationJCDL'11 - Proceedings of the 2011 ACM/IEEE Joint Conference on Digital Libraries
Pages349-358
Number of pages10
DOIs
StatePublished - Jul 25 2011
Event11th Annual International ACM/IEEE Joint Conference on Digital Libraries, JCDL'11 - Ottawa, ON, Canada
Duration: Jun 13 2011Jun 17 2011

Publication series

NameProceedings of the ACM/IEEE Joint Conference on Digital Libraries
ISSN (Print)1552-5996

Other

Other11th Annual International ACM/IEEE Joint Conference on Digital Libraries, JCDL'11
CountryCanada
CityOttawa, ON
Period6/13/116/17/11

Fingerprint

Image segmentation
Experiments

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Pan, C. C., & Mitra, P. (2011). Event detection with spatial latent Dirichlet allocation. In JCDL'11 - Proceedings of the 2011 ACM/IEEE Joint Conference on Digital Libraries (pp. 349-358). (Proceedings of the ACM/IEEE Joint Conference on Digital Libraries). https://doi.org/10.1145/1998076.1998141
Pan, Chi Chun ; Mitra, Prasenjit. / Event detection with spatial latent Dirichlet allocation. JCDL'11 - Proceedings of the 2011 ACM/IEEE Joint Conference on Digital Libraries. 2011. pp. 349-358 (Proceedings of the ACM/IEEE Joint Conference on Digital Libraries).
@inproceedings{d9f86d3b301a49bc86cf1dffe1d5f1b6,
title = "Event detection with spatial latent Dirichlet allocation",
abstract = "A large number of news articles are generated every day on the Web. Automatically identifying events from a large document collection is a challenging problem. In this paper, we propose two event detection approaches using generative models. We combine the popular LDA model with temporal segmentation and spatial clustering. In addition, we adapt an image segmentation model, SLDA, for spatial-temporal event detection on text. The results of our experiments show that both approaches outperform the traditional content-based clustering approaches on our datasets.",
author = "Pan, {Chi Chun} and Prasenjit Mitra",
year = "2011",
month = "7",
day = "25",
doi = "10.1145/1998076.1998141",
language = "English (US)",
isbn = "9781450307444",
series = "Proceedings of the ACM/IEEE Joint Conference on Digital Libraries",
pages = "349--358",
booktitle = "JCDL'11 - Proceedings of the 2011 ACM/IEEE Joint Conference on Digital Libraries",

}

Pan, CC & Mitra, P 2011, Event detection with spatial latent Dirichlet allocation. in JCDL'11 - Proceedings of the 2011 ACM/IEEE Joint Conference on Digital Libraries. Proceedings of the ACM/IEEE Joint Conference on Digital Libraries, pp. 349-358, 11th Annual International ACM/IEEE Joint Conference on Digital Libraries, JCDL'11, Ottawa, ON, Canada, 6/13/11. https://doi.org/10.1145/1998076.1998141

Event detection with spatial latent Dirichlet allocation. / Pan, Chi Chun; Mitra, Prasenjit.

JCDL'11 - Proceedings of the 2011 ACM/IEEE Joint Conference on Digital Libraries. 2011. p. 349-358 (Proceedings of the ACM/IEEE Joint Conference on Digital Libraries).

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

TY - GEN

T1 - Event detection with spatial latent Dirichlet allocation

AU - Pan, Chi Chun

AU - Mitra, Prasenjit

PY - 2011/7/25

Y1 - 2011/7/25

N2 - A large number of news articles are generated every day on the Web. Automatically identifying events from a large document collection is a challenging problem. In this paper, we propose two event detection approaches using generative models. We combine the popular LDA model with temporal segmentation and spatial clustering. In addition, we adapt an image segmentation model, SLDA, for spatial-temporal event detection on text. The results of our experiments show that both approaches outperform the traditional content-based clustering approaches on our datasets.

AB - A large number of news articles are generated every day on the Web. Automatically identifying events from a large document collection is a challenging problem. In this paper, we propose two event detection approaches using generative models. We combine the popular LDA model with temporal segmentation and spatial clustering. In addition, we adapt an image segmentation model, SLDA, for spatial-temporal event detection on text. The results of our experiments show that both approaches outperform the traditional content-based clustering approaches on our datasets.

UR - http://www.scopus.com/inward/record.url?scp=79960534133&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79960534133&partnerID=8YFLogxK

U2 - 10.1145/1998076.1998141

DO - 10.1145/1998076.1998141

M3 - Conference contribution

AN - SCOPUS:79960534133

SN - 9781450307444

T3 - Proceedings of the ACM/IEEE Joint Conference on Digital Libraries

SP - 349

EP - 358

BT - JCDL'11 - Proceedings of the 2011 ACM/IEEE Joint Conference on Digital Libraries

ER -

Pan CC, Mitra P. Event detection with spatial latent Dirichlet allocation. In JCDL'11 - Proceedings of the 2011 ACM/IEEE Joint Conference on Digital Libraries. 2011. p. 349-358. (Proceedings of the ACM/IEEE Joint Conference on Digital Libraries). https://doi.org/10.1145/1998076.1998141