Extracting and Understanding Contrastive Opinion through Topic Relevant Sentences

Emmanuel Ebuka Ibeke; Chenghua Lin; Adam Zachary Wyner; Mohamad Hardyman Bin Barawi

Extracting and Understanding Contrastive Opinion through Topic Relevant Sentences

Emmanuel Ebuka Ibeke, Chenghua Lin, Adam Zachary Wyner, Mohamad Hardyman Bin Barawi

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

Abstract

Contrastive opinion mining is essential in identifying, extracting and organising opinions from user generated texts. Most existing studies separate input data into respective collections. In addition, the relationships between the topics extracted and the sentences in the corpus which express the topics are opaque, hindering our understanding of the opinions expressed in the corpus. We propose a novel unified latent variable model (contraLDA) which addresses the above matters. Experimental results show the effectiveness of our model in mining contrasted opinions, outperforming our baselines.

Original language	English
Title of host publication	Proceedings of the The 8th International Joint Conference on Natural Language Processing
Place of Publication	Taiwan
Publisher	ACL Anthology
Pages	395-400
Number of pages	6
Volume	2
ISBN (Print)	978-1-948087-01-8
Publication status	Published - Nov 2017
Event	8th International Joint Conference on Natural Language Processing (IJCNLP 2017) - Taipei, Taiwan, Province of China Duration: 27 Nov 2017 → 1 Dec 2017

Conference

Conference	8th International Joint Conference on Natural Language Processing (IJCNLP 2017)
Country/Territory	Taiwan, Province of China
City	Taipei
Period	27/11/17 → 1/12/17

Access to Document

http://aclweb.org/anthology/I17-2067Licence: Unspecified

Cite this

Extracting and Understanding Contrastive Opinion through Topic Relevant Sentences. / Ibeke, Emmanuel Ebuka; Lin, Chenghua; Wyner, Adam Zachary et al.
Proceedings of the The 8th International Joint Conference on Natural Language Processing. Vol. 2 Taiwan: ACL Anthology, 2017. p. 395-400.

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

Ibeke, EE, Lin, C, Wyner, AZ & Barawi, MHB 2017, Extracting and Understanding Contrastive Opinion through Topic Relevant Sentences. in Proceedings of the The 8th International Joint Conference on Natural Language Processing. vol. 2, ACL Anthology, Taiwan, pp. 395-400, 8th International Joint Conference on Natural Language Processing (IJCNLP 2017), Taipei, Taiwan, Province of China, 27/11/17. <http://aclweb.org/anthology/I17-2067>

@inproceedings{bb3dd64689aa4370a6633978820f4317,

title = "Extracting and Understanding Contrastive Opinion through Topic Relevant Sentences",

abstract = "Contrastive opinion mining is essential in identifying, extracting and organising opinions from user generated texts. Most existing studies separate input data into respective collections. In addition, the relationships between the topics extracted and the sentences in the corpus which express the topics are opaque, hindering our understanding of the opinions expressed in the corpus. We propose a novel unified latent variable model (contraLDA) which addresses the above matters. Experimental results show the effectiveness of our model in mining contrasted opinions, outperforming our baselines.",

author = "Ibeke, {Emmanuel Ebuka} and Chenghua Lin and Wyner, {Adam Zachary} and Barawi, {Mohamad Hardyman Bin}",

year = "2017",

month = nov,

language = "English",

isbn = " 978-1-948087-01-8",

volume = "2",

pages = "395--400",

booktitle = "Proceedings of the The 8th International Joint Conference on Natural Language Processing",

publisher = "ACL Anthology",

note = "8th International Joint Conference on Natural Language Processing (IJCNLP 2017) ; Conference date: 27-11-2017 Through 01-12-2017",

}

TY - GEN

T1 - Extracting and Understanding Contrastive Opinion through Topic Relevant Sentences

AU - Ibeke, Emmanuel Ebuka

AU - Lin, Chenghua

AU - Wyner, Adam Zachary

AU - Barawi, Mohamad Hardyman Bin

PY - 2017/11

Y1 - 2017/11

N2 - Contrastive opinion mining is essential in identifying, extracting and organising opinions from user generated texts. Most existing studies separate input data into respective collections. In addition, the relationships between the topics extracted and the sentences in the corpus which express the topics are opaque, hindering our understanding of the opinions expressed in the corpus. We propose a novel unified latent variable model (contraLDA) which addresses the above matters. Experimental results show the effectiveness of our model in mining contrasted opinions, outperforming our baselines.

AB - Contrastive opinion mining is essential in identifying, extracting and organising opinions from user generated texts. Most existing studies separate input data into respective collections. In addition, the relationships between the topics extracted and the sentences in the corpus which express the topics are opaque, hindering our understanding of the opinions expressed in the corpus. We propose a novel unified latent variable model (contraLDA) which addresses the above matters. Experimental results show the effectiveness of our model in mining contrasted opinions, outperforming our baselines.

M3 - Published conference contribution

SN - 978-1-948087-01-8

VL - 2

SP - 395

EP - 400

BT - Proceedings of the The 8th International Joint Conference on Natural Language Processing

PB - ACL Anthology

CY - Taiwan

T2 - 8th International Joint Conference on Natural Language Processing (IJCNLP 2017)

Y2 - 27 November 2017 through 1 December 2017

ER -

Extracting and Understanding Contrastive Opinion through Topic Relevant Sentences

Abstract

Conference

Access to Document

Fingerprint

Cite this