Examining the performance of topic modeling techniques in Twitter trends extraction

Mutia N. Kurniati; Woo Jong Ryu; Md Hijbul Alam; Sang-Geun Lee

doi:10.1109/ICOIN.2014.6799706

Examining the performance of topic modeling techniques in Twitter trends extraction

Mutia N. Kurniati, Woo Jong Ryu, Md Hijbul Alam, Sang-Geun Lee

Center for Artificial Intelligence Research

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

It is very important to extract the Twitter trends since it reflects the personal view over 645 million of its users. We examine the effectiveness of two topic modeling techniques i.e., standard Latent Dirichlet Allocation (LDA) and semantic-based Joint Multi-grain Topic-Sentiment (JMTS) in Twitter trends extraction. In addition, we also examine the frequent phrase method. Our finding reveals that JMTS significantly outperforms frequent phrase method and LDA by 54% and 24%, respectively.

Original language	English
Title of host publication	International Conference on Information Networking 2014, ICOIN 2014
Publisher	IEEE Computer Society
Pages	364-369
Number of pages	6
ISBN (Print)	9781479936892
DOIs	https://doi.org/10.1109/ICOIN.2014.6799706
Publication status	Published - 2014
Event	2014 28th International Conference on Information Networking, ICOIN 2014 - Phuket, Thailand Duration: 2014 Feb 10 → 2014 Feb 12

Publication series

Name	International Conference on Information Networking
ISSN (Print)	1976-7684

Other

Other	2014 28th International Conference on Information Networking, ICOIN 2014
Country/Territory	Thailand
City	Phuket
Period	14/2/10 → 14/2/12

ASJC Scopus subject areas

Computer Networks and Communications
Information Systems

Access to Document

10.1109/ICOIN.2014.6799706

Cite this

Examining the performance of topic modeling techniques in Twitter trends extraction. / Kurniati, Mutia N.; Ryu, Woo Jong; Alam, Md Hijbul et al.
International Conference on Information Networking 2014, ICOIN 2014. IEEE Computer Society, 2014. p. 364-369 6799706 (International Conference on Information Networking).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Kurniati, MN, Ryu, WJ, Alam, MH & Lee, S-G 2014, Examining the performance of topic modeling techniques in Twitter trends extraction. in International Conference on Information Networking 2014, ICOIN 2014., 6799706, International Conference on Information Networking, IEEE Computer Society, pp. 364-369, 2014 28th International Conference on Information Networking, ICOIN 2014, Phuket, Thailand, 14/2/10. https://doi.org/10.1109/ICOIN.2014.6799706

@inproceedings{e0d2cb36f8a843e9b6249647758d98b7,

title = "Examining the performance of topic modeling techniques in Twitter trends extraction",

abstract = "It is very important to extract the Twitter trends since it reflects the personal view over 645 million of its users. We examine the effectiveness of two topic modeling techniques i.e., standard Latent Dirichlet Allocation (LDA) and semantic-based Joint Multi-grain Topic-Sentiment (JMTS) in Twitter trends extraction. In addition, we also examine the frequent phrase method. Our finding reveals that JMTS significantly outperforms frequent phrase method and LDA by 54% and 24%, respectively.",

author = "Kurniati, {Mutia N.} and Ryu, {Woo Jong} and Alam, {Md Hijbul} and Sang-Geun Lee",

year = "2014",

doi = "10.1109/ICOIN.2014.6799706",

language = "English",

isbn = "9781479936892",

series = "International Conference on Information Networking",

publisher = "IEEE Computer Society",

pages = "364--369",

booktitle = "International Conference on Information Networking 2014, ICOIN 2014",

note = "2014 28th International Conference on Information Networking, ICOIN 2014 ; Conference date: 10-02-2014 Through 12-02-2014",

}

TY - GEN

T1 - Examining the performance of topic modeling techniques in Twitter trends extraction

AU - Kurniati, Mutia N.

AU - Ryu, Woo Jong

AU - Alam, Md Hijbul

AU - Lee, Sang-Geun

PY - 2014

Y1 - 2014

N2 - It is very important to extract the Twitter trends since it reflects the personal view over 645 million of its users. We examine the effectiveness of two topic modeling techniques i.e., standard Latent Dirichlet Allocation (LDA) and semantic-based Joint Multi-grain Topic-Sentiment (JMTS) in Twitter trends extraction. In addition, we also examine the frequent phrase method. Our finding reveals that JMTS significantly outperforms frequent phrase method and LDA by 54% and 24%, respectively.

AB - It is very important to extract the Twitter trends since it reflects the personal view over 645 million of its users. We examine the effectiveness of two topic modeling techniques i.e., standard Latent Dirichlet Allocation (LDA) and semantic-based Joint Multi-grain Topic-Sentiment (JMTS) in Twitter trends extraction. In addition, we also examine the frequent phrase method. Our finding reveals that JMTS significantly outperforms frequent phrase method and LDA by 54% and 24%, respectively.

UR - http://www.scopus.com/inward/record.url?scp=84899969712&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899969712&partnerID=8YFLogxK

U2 - 10.1109/ICOIN.2014.6799706

DO - 10.1109/ICOIN.2014.6799706

M3 - Conference contribution

AN - SCOPUS:84899969712

SN - 9781479936892

T3 - International Conference on Information Networking

SP - 364

EP - 369

BT - International Conference on Information Networking 2014, ICOIN 2014

PB - IEEE Computer Society

T2 - 2014 28th International Conference on Information Networking, ICOIN 2014

Y2 - 10 February 2014 through 12 February 2014

ER -

Examining the performance of topic modeling techniques in Twitter trends extraction

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this