Acknowledging Discourse Function for Sentiment Analysis

Phillip Smith; M. Lee

doi:10.1007/978-3-642-54903-8

Acknowledging Discourse Function for Sentiment Analysis

Phillip Smith, M. Lee

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

2 Citations (Scopus)

Abstract

In this paper, we observe the eects that discourse function attribute to the task of training learned classiers for sentiment analysis. Experimental results from our study show that training on a corpus of primarily persuasive documents can have a negative eect on the performance of supervised sentiment classication. In addition we demonstrate that through use of the Multinomial Nave Bayes classier we can minimise the detrimental eects of discourse function during sentiment analysis.

Original language	English
Title of host publication	Computational Linguistics and Intelligent Text Processing: 15th International Conference, CICLing 2014, Kathmandu, Nepal, April 6-12, 2014, Proceedings
Editors	Alexander Gelbukh
Place of Publication	Berlin
Publisher	Springer Verlag
Pages	45-52
Volume	II
ISBN (Print)	978-3-642-54903-8, 978-3-642-54902-1
DOIs	https://doi.org/10.1007/978-3-642-54903-8
Publication status	Published - 2014

Bibliographical note

The full text is not available on the repository.

Access to Document

10.1007/978-3-642-54903-8

Cite this

Acknowledging Discourse Function for Sentiment Analysis. / Smith, Phillip; Lee, M.
Computational Linguistics and Intelligent Text Processing: 15th International Conference, CICLing 2014, Kathmandu, Nepal, April 6-12, 2014, Proceedings. ed. / Alexander Gelbukh. Vol. II Berlin: Springer Verlag, 2014. p. 45-52.

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

@inbook{24f12b7bd3af4c3185879ed63d9c2791,

title = "Acknowledging Discourse Function for Sentiment Analysis",

abstract = "In this paper, we observe the eects that discourse function attribute to the task of training learned classiers for sentiment analysis. Experimental results from our study show that training on a corpus of primarily persuasive documents can have a negative eect on the performance of supervised sentiment classication. In addition we demonstrate that through use of the Multinomial Nave Bayes classier we can minimise the detrimental eects of discourse function during sentiment analysis.",

author = "Phillip Smith and M. Lee",

note = "The full text is not available on the repository.",

year = "2014",

doi = "10.1007/978-3-642-54903-8",

language = "English",

isbn = "978-3-642-54903-8",

volume = "II",

pages = "45--52",

editor = "Alexander Gelbukh",

booktitle = "Computational Linguistics and Intelligent Text Processing: 15th International Conference, CICLing 2014, Kathmandu, Nepal, April 6-12, 2014, Proceedings",

publisher = "Springer Verlag",

address = "Austria",

}

TY - CHAP

T1 - Acknowledging Discourse Function for Sentiment Analysis

AU - Smith, Phillip

AU - Lee, M.

N1 - The full text is not available on the repository.

PY - 2014

Y1 - 2014

N2 - In this paper, we observe the eects that discourse function attribute to the task of training learned classiers for sentiment analysis. Experimental results from our study show that training on a corpus of primarily persuasive documents can have a negative eect on the performance of supervised sentiment classication. In addition we demonstrate that through use of the Multinomial Nave Bayes classier we can minimise the detrimental eects of discourse function during sentiment analysis.

AB - In this paper, we observe the eects that discourse function attribute to the task of training learned classiers for sentiment analysis. Experimental results from our study show that training on a corpus of primarily persuasive documents can have a negative eect on the performance of supervised sentiment classication. In addition we demonstrate that through use of the Multinomial Nave Bayes classier we can minimise the detrimental eects of discourse function during sentiment analysis.

U2 - 10.1007/978-3-642-54903-8

DO - 10.1007/978-3-642-54903-8

M3 - Chapter

SN - 978-3-642-54903-8

SN - 978-3-642-54902-1

VL - II

SP - 45

EP - 52

BT - Computational Linguistics and Intelligent Text Processing: 15th International Conference, CICLing 2014, Kathmandu, Nepal, April 6-12, 2014, Proceedings

A2 - Gelbukh, Alexander

PB - Springer Verlag

CY - Berlin

ER -

Acknowledging Discourse Function for Sentiment Analysis

Abstract

Bibliographical note

Access to Document

Fingerprint

Cite this