A simple Bayesian modelling approach to event extraction from Twitter

Deyu Zhou; Liangyu Chen; Yulan He

A simple Bayesian modelling approach to event extraction from Twitter

Deyu Zhou, Liangyu Chen, Yulan He

Computer Science Research Group

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

With the proliferation of social media sites, social streams have proven to contain the most up-to-date information on current events. Therefore, it is crucial to extract events from the social streams such as tweets. However, it is not straightforward to adapt the existing event extraction systems since texts in social media are fragmented and noisy. In this paper we propose a simple and yet effective Bayesian model, called Latent Event Model (LEM), to extract structured representation of events from social media. LEM is fully unsupervised and does not require annotated data for training. We evaluate LEM on a Twitter corpus. Experimental results show that the proposed model achieves 83% in F-measure, and outperforms the state-of-the-art baseline by over 7%.

Original language	English
Title of host publication	The 52nd Annual Meeting of the Association for Computational Linguistics (ACL)
Publisher	Association for Computational Linguistics
Pages	700-705
Number of pages	6
Volume	2
ISBN (Print)	978-1-937284-73-2
Publication status	Published - 2014
Event	52nd annual meeting of the Association for Computational Linguistics - Baltimore, MD, United States Duration: 22 Jun 2014 → 27 Jun 2014

Meeting

Meeting	52nd annual meeting of the Association for Computational Linguistics
Abbreviated title	ACL 2014
Country/Territory	United States
City	Baltimore, MD
Period	22/06/14 → 27/06/14

Cite this

@inproceedings{a12f722e80794a00b7896e765af7491f,

title = "A simple Bayesian modelling approach to event extraction from Twitter",

abstract = "With the proliferation of social media sites, social streams have proven to contain the most up-to-date information on current events. Therefore, it is crucial to extract events from the social streams such as tweets. However, it is not straightforward to adapt the existing event extraction systems since texts in social media are fragmented and noisy. In this paper we propose a simple and yet effective Bayesian model, called Latent Event Model (LEM), to extract structured representation of events from social media. LEM is fully unsupervised and does not require annotated data for training. We evaluate LEM on a Twitter corpus. Experimental results show that the proposed model achieves 83% in F-measure, and outperforms the state-of-the-art baseline by over 7%.",

author = "Deyu Zhou and Liangyu Chen and Yulan He",

year = "2014",

language = "English",

isbn = "978-1-937284-73-2",

volume = "2",

pages = "700--705",

booktitle = "The 52nd Annual Meeting of the Association for Computational Linguistics (ACL)",

publisher = "Association for Computational Linguistics",

note = "52nd annual meeting of the Association for Computational Linguistics, ACL 2014 ; Conference date: 22-06-2014 Through 27-06-2014",

}

TY - GEN

T1 - A simple Bayesian modelling approach to event extraction from Twitter

AU - Zhou, Deyu

AU - Chen, Liangyu

AU - He, Yulan

PY - 2014

Y1 - 2014

N2 - With the proliferation of social media sites, social streams have proven to contain the most up-to-date information on current events. Therefore, it is crucial to extract events from the social streams such as tweets. However, it is not straightforward to adapt the existing event extraction systems since texts in social media are fragmented and noisy. In this paper we propose a simple and yet effective Bayesian model, called Latent Event Model (LEM), to extract structured representation of events from social media. LEM is fully unsupervised and does not require annotated data for training. We evaluate LEM on a Twitter corpus. Experimental results show that the proposed model achieves 83% in F-measure, and outperforms the state-of-the-art baseline by over 7%.

AB - With the proliferation of social media sites, social streams have proven to contain the most up-to-date information on current events. Therefore, it is crucial to extract events from the social streams such as tweets. However, it is not straightforward to adapt the existing event extraction systems since texts in social media are fragmented and noisy. In this paper we propose a simple and yet effective Bayesian model, called Latent Event Model (LEM), to extract structured representation of events from social media. LEM is fully unsupervised and does not require annotated data for training. We evaluate LEM on a Twitter corpus. Experimental results show that the proposed model achieves 83% in F-measure, and outperforms the state-of-the-art baseline by over 7%.

UR - http://www.scopus.com/inward/record.url?scp=84906922000&partnerID=8YFLogxK

M3 - Conference publication

AN - SCOPUS:84906922000

SN - 978-1-937284-73-2

VL - 2

SP - 700

EP - 705

BT - The 52nd Annual Meeting of the Association for Computational Linguistics (ACL)

PB - Association for Computational Linguistics

T2 - 52nd annual meeting of the Association for Computational Linguistics

Y2 - 22 June 2014 through 27 June 2014

ER -

A simple Bayesian modelling approach to event extraction from Twitter

Abstract

Meeting

Other files and links

Fingerprint

Automatic labelling of topic models learned from Twitter by summarisation

Real-time detection, tracking, and monitoring of automatically discovered events in social media

Cite this