Automatic prediction of evidence-based recommendations via sentence-level polarity classification

Abeed Sarker; Diego Mollá-Aliod; Cécile Paris

Automatic prediction of evidence-based recommendations via sentence-level polarity classification

Abeed Sarker, Diego Mollá-Aliod, Cécile Paris

School of Computing

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

4 Citations (Scopus)

Abstract

We propose a supervised classification approach for automatically determining the polarities of medical sentences. Our polarity classification approach is context sensitive, meaning that the same sentence may have differing polarities depending on the context. Using a set of carefully selected features, we achieve 84.7% accuracy, which is significantly better than current state-of-the-art for the polarity classification task. Our analyses and experiments on a specialised corpus indicate that automatic polarity classification of key sentences can be utilised to generate evidence-based recommendations.

Original language	English
Title of host publication	IJCNLP 2013
Subtitle of host publication	Proceedings of the Sixth International Joint Conference on Natural Language Processing
Place of Publication	Nagoya, Japan
Publisher	Asian Federation of Natural Language Processing
Pages	712-718
Number of pages	7
ISBN (Print)	9784990734800
Publication status	Published - 2013
Event	International Joint Conference on Natural Language Processing (6th : 2013) - Nagoya, Japan Duration: 14 Oct 2013 → 18 Oct 2013

Conference

Conference	International Joint Conference on Natural Language Processing (6th : 2013)
City	Nagoya, Japan
Period	14/10/13 → 18/10/13

Access to Document

http://aclweb.org/anthology/I/I13/I13-1084.pdf

Cite this

@inproceedings{8d37197419b0459e935b937add59a488,

title = "Automatic prediction of evidence-based recommendations via sentence-level polarity classification",

abstract = "We propose a supervised classification approach for automatically determining the polarities of medical sentences. Our polarity classification approach is context sensitive, meaning that the same sentence may have differing polarities depending on the context. Using a set of carefully selected features, we achieve 84.7% accuracy, which is significantly better than current state-of-the-art for the polarity classification task. Our analyses and experiments on a specialised corpus indicate that automatic polarity classification of key sentences can be utilised to generate evidence-based recommendations.",

author = "Abeed Sarker and Diego Moll{\'a}-Aliod and C{\'e}cile Paris",

year = "2013",

language = "English",

isbn = "9784990734800",

pages = "712--718",

booktitle = "IJCNLP 2013",

publisher = "Asian Federation of Natural Language Processing",

note = "International Joint Conference on Natural Language Processing (6th : 2013) ; Conference date: 14-10-2013 Through 18-10-2013",

}

Sarker, A, Mollá-Aliod, D & Paris, C 2013, Automatic prediction of evidence-based recommendations via sentence-level polarity classification. in IJCNLP 2013: Proceedings of the Sixth International Joint Conference on Natural Language Processing. Asian Federation of Natural Language Processing, Nagoya, Japan, pp. 712-718, International Joint Conference on Natural Language Processing (6th : 2013), Nagoya, Japan, 14/10/13. <http://aclweb.org/anthology/I/I13/I13-1084.pdf>

Automatic prediction of evidence-based recommendations via sentence-level polarity classification. / Sarker, Abeed; Mollá-Aliod, Diego ; Paris, Cécile.

IJCNLP 2013: Proceedings of the Sixth International Joint Conference on Natural Language Processing. Nagoya, Japan : Asian Federation of Natural Language Processing, 2013. p. 712-718.

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

TY - GEN

T1 - Automatic prediction of evidence-based recommendations via sentence-level polarity classification

AU - Sarker, Abeed

AU - Mollá-Aliod, Diego

AU - Paris, Cécile

PY - 2013

Y1 - 2013

N2 - We propose a supervised classification approach for automatically determining the polarities of medical sentences. Our polarity classification approach is context sensitive, meaning that the same sentence may have differing polarities depending on the context. Using a set of carefully selected features, we achieve 84.7% accuracy, which is significantly better than current state-of-the-art for the polarity classification task. Our analyses and experiments on a specialised corpus indicate that automatic polarity classification of key sentences can be utilised to generate evidence-based recommendations.

AB - We propose a supervised classification approach for automatically determining the polarities of medical sentences. Our polarity classification approach is context sensitive, meaning that the same sentence may have differing polarities depending on the context. Using a set of carefully selected features, we achieve 84.7% accuracy, which is significantly better than current state-of-the-art for the polarity classification task. Our analyses and experiments on a specialised corpus indicate that automatic polarity classification of key sentences can be utilised to generate evidence-based recommendations.

M3 - Conference proceeding contribution

SN - 9784990734800

SP - 712

EP - 718

BT - IJCNLP 2013

PB - Asian Federation of Natural Language Processing

CY - Nagoya, Japan

T2 - International Joint Conference on Natural Language Processing (6th : 2013)

Y2 - 14 October 2013 through 18 October 2013

ER -

Automatic prediction of evidence-based recommendations via sentence-level polarity classification

Abstract

Conference

Access to Document

Fingerprint

Cite this