short-paper

Enhancing First Story Detection using Word Embeddings

Authors:

Sean Moran,

Richard McCreadie,

Craig Macdonald, and

Iadh OunisAuthors Info & Claims

SIGIR '16: Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval

July 2016

Pages 821 - 824

https://doi.org/10.1145/2911451.2914719

Published: 07 July 2016 Publication History

Get Access

Abstract

In this paper we show how word embeddings can be used to increase the effectiveness of a state-of-the art Locality Sensitive Hashing (LSH) based first story detection (FSD) system over a standard tweet corpus. Vocabulary mismatch, in which related tweets use different words, is a serious hindrance to the effectiveness of a modern FSD system. In this case, a tweet could be flagged as a first story even if a related tweet, which uses different but synonymous words, was already returned as a first story. In this work, we propose a novel approach to mitigate this problem of lexical variation, based on tweet expansion. In particular, we propose to expand tweets with semantically related paraphrases identified via automatically mined word embeddings over a background tweet corpus. Through experimentation on a large data stream comprised of 50 million tweets, we show that FSD effectiveness can be improved by 9.5% over a state-of-the-art FSD system.

References

[1]

J. Fiscus Overview of of the TDT 2001 evaluation and results. In Proc. TDT, 2001.

Google Scholar

[2]

J. Allan. Introduction to topic detection and tracking. In Proc. TDT, 2002.

Digital Library

Google Scholar

[3]

C. Callison-Burch Syntactic constraints onparaphrases extracted from parallel corpora. In Proc. EMNLP, 2008.

Digital Library

Google Scholar

[4]

P. Indyk and R. Motwani. Approximate nearest neighbors: Towards removing the curse of dimensionality. In Proc. STOC, 1998.

Digital Library

Google Scholar

[5]

D. Wurzer, V. Lavrenko, M. Osborne Twitter-scale New Event Detection via K-term Hashing. In Proc. EMNLP, 2015.

Google Scholar

[6]

G. Miller. WordNet: a lexical database for English. Communications of the ACM, 38 (11), 1995.

Digital Library

Google Scholar

[7]

R. Lebret, and R. Collobert. N-gram-Based Low-Dimensional Representation for Document Classification. In Proc. ICLP, 2015.

Google Scholar

[8]

M. Charikar. Similarity Estimation Techniques from Rounding Algorithms. In Proc. STOC, 2002.

Digital Library

Google Scholar

[9]

T. Mikolov, K. Chen, G. Corrado and J. Dean. Efficient estimation of word representations in vector space. In Proc. ICLR, 2013.

Google Scholar

[10]

S. Petrović, M. Osborne, and V. Lavrenko. Streaming first story detection with application to Twitter. In Proc. NAACL, 2010.

Digital Library

Google Scholar

[11]

S. Petrović, M. Osborne and V. Lavrenko. Using paraphrases for improving first story detection in news and Twitter. In Proc. NAACL, 2012.

Digital Library

Google Scholar

[12]

C. Quirk, C. Brockett, and W. Dola. Monolingual machine translation for paraphrase generation. In Proc. EMNLP, 2004.

Google Scholar

Cited By

View all

Elbedwehy SThron CAlrahmawy MHamza T(2022)Real-Time Detection of First Stories in Twitter Using a FastText ModelArtificial Intelligence for Data Science in Theory and Practice10.1007/978-3-030-92245-0_9(179-218)Online publication date: 2022
https://doi.org/10.1007/978-3-030-92245-0_9
Panagiotou NSaravanou AGunopulos D(2021)News Monitor: A Framework for Exploring News in Real-TimeData10.3390/data70100037:1(3)Online publication date: 27-Dec-2021
https://doi.org/10.3390/data7010003
Lu J(2021)Event identification by deep transfer learning with dual transformations2021 30th Wireless and Optical Communications Conference (WOCC)10.1109/WOCC53213.2021.9602921(178-182)Online publication date: 7-Oct-2021
https://doi.org/10.1109/WOCC53213.2021.9602921
Show More Cited By

Index Terms

Enhancing First Story Detection using Word Embeddings
1. Information systems
  1. Information retrieval
    1. Retrieval tasks and goals
      1. Document filtering
    2. Specialized information retrieval
      1. Environment-specific retrieval
        Web and social media search
  2. Information systems applications
    1. Data mining
      1. Data stream mining
      2. Nearest-neighbor search
2. Theory of computation
  1. Design and analysis of algorithms
    1. Streaming, sublinear and near linear time algorithms
      1. Bloom filters and hashing
      2. Nearest neighbor algorithms
  2. Randomness, geometry and discrete structures
    1. Random projections and metric embeddings

Recommendations

Composing Word Embeddings for Compound Words Using Linguistic Knowledge
In recent years, the use of distributed representations has been a fundamental technology for natural language processing. However, Japanese has multiple compound words, and often we must compare the meanings of a word and a compound word. Moreover, word ...
Read More
Using word embeddings in Twitter election classification
Abstract
Word embeddings and convolutional neural networks (CNN) have attracted extensive attention in various classification tasks for Twitter, e.g. sentiment classification. However, the effect of the configuration used to generate the word embeddings on ...
Read More
Linguistic Pattern Mining for Data Analysis in Microblog Texts using Word Embeddings
SBSI '19: Proceedings of the XV Brazilian Symposium on Information Systems

Microblog posts (e.g. tweets) often contain users opinions and thoughts about events, products, people, organizations, among other possibilities. However, the usage of social media to promote online disinformation and manipulation is not an uncommon ...
Read More

Comments

Information & Contributors

Information

Published In

SIGIR '16: Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval

July 2016

1296 pages

ISBN:9781450340694

DOI:10.1145/2911451

General Chairs:
Raffaele Perego
ISTI-CNR, Italy
,
Fabrizio Sebastiani
Qatar Computing Research Institute, HBKU, Qatar
,
Program Chairs:
Javed Aslam
Northeastern University, US
,
Ian Ruthven
University of Strathclyde, UK
,
Justin Zobel
University of Melbourne, Australia

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 07 July 2016

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Short-paper

Funding Sources

Conference

SIGIR '16

Sponsor:

SIGIR

SIGIR '16: The 39th International ACM SIGIR conference on research and development in Information Retrieval

July 17 - 21, 2016

Pisa, Italy

Acceptance Rates

SIGIR '16 Paper Acceptance Rate 62 of 341 submissions, 18%;

Overall Acceptance Rate 792 of 3,983 submissions, 20%

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

17
Total Citations
View Citations
338
Total Downloads

Downloads (Last 12 months)12
Downloads (Last 6 weeks)0

Other Metrics

View Author Metrics

Citations

Cited By

View all

Elbedwehy SThron CAlrahmawy MHamza T(2022)Real-Time Detection of First Stories in Twitter Using a FastText ModelArtificial Intelligence for Data Science in Theory and Practice10.1007/978-3-030-92245-0_9(179-218)Online publication date: 2022
https://doi.org/10.1007/978-3-030-92245-0_9
Panagiotou NSaravanou AGunopulos D(2021)News Monitor: A Framework for Exploring News in Real-TimeData10.3390/data70100037:1(3)Online publication date: 27-Dec-2021
https://doi.org/10.3390/data7010003
Lu J(2021)Event identification by deep transfer learning with dual transformations2021 30th Wireless and Optical Communications Conference (WOCC)10.1109/WOCC53213.2021.9602921(178-182)Online publication date: 7-Oct-2021
https://doi.org/10.1109/WOCC53213.2021.9602921
Panagiotou NAkkaya CTsioutsiouliklis KKalogeraki VGunopulos D(2021)A General Framework for First Story Detection Utilizing Entities and Their RelationsIEEE Transactions on Knowledge and Data Engineering10.1109/TKDE.2020.297005133:11(3482-3493)Online publication date: 1-Nov-2021
https://dl.acm.org/doi/10.1109/TKDE.2020.2970051
Saravanou APanagiotou NGunopulos D(2021)News Monitor: A Framework for Querying News in Real TimeAdvances in Information Retrieval10.1007/978-3-030-72240-1_62(543-548)Online publication date: 28-Mar-2021
https://dl.acm.org/doi/10.1007/978-3-030-72240-1_62
Wang FRoss RKelleher J(2020)Update Frequency and Background Corpus Selection in Dynamic TF-IDF Models for First Story DetectionComputational Linguistics10.1007/978-981-15-6168-9_18(206-217)Online publication date: 2-Jul-2020
https://doi.org/10.1007/978-981-15-6168-9_18
Palaiokrassas GVoulodimos ALitke APapaoikonomou AVarvarigou T(2018)A Distance-Dependent Chinese Restaurant Process Based Method for Event Detection on Social MediaInventions10.3390/inventions30400803:4(80)Online publication date: 7-Dec-2018
https://doi.org/10.3390/inventions3040080
Wurzer DQin YCollins-Thompson KMei QDavison BLiu YYilmaz E(2018)Parameterizing Kterm HashingThe 41st International ACM SIGIR Conference on Research & Development in Information Retrieval10.1145/3209978.3210101(945-948)Online publication date: 27-Jun-2018
https://dl.acm.org/doi/10.1145/3209978.3210101
Spitz AGertz MChampin PGandon FMédini LLalmas MIpeirotis P(2018)Exploring Entity-centric Networks in Entangled News StreamsCompanion Proceedings of the The Web Conference 201810.1145/3184558.3188726(555-563)Online publication date: 23-Apr-2018
https://dl.acm.org/doi/10.1145/3184558.3188726
Yang XOunis IMcCreadie RMacdonald CFang A(2018)On the Reproducibility and Generalisation of the Linear Transformation of Word EmbeddingsAdvances in Information Retrieval10.1007/978-3-319-76941-7_20(263-275)Online publication date: 1-Mar-2018
https://doi.org/10.1007/978-3-319-76941-7_20
Show More Cited By

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Composing Word Embeddings for Compound Words Using Linguistic Knowledge

Using word embeddings in Twitter election classification

Linguistic Pattern Mining for Data Analysis in Microblog Texts using Word Embeddings