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

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

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 languageEnglish
Title of host publicationIJCNLP 2013
Subtitle of host publicationProceedings of the Sixth International Joint Conference on Natural Language Processing
Place of PublicationNagoya, Japan
PublisherAsian Federation of Natural Language Processing
Pages712-718
Number of pages7
ISBN (Print)9784990734800
Publication statusPublished - 2013
EventInternational Joint Conference on Natural Language Processing (6th : 2013) - Nagoya, Japan
Duration: 14 Oct 201318 Oct 2013

Conference

ConferenceInternational Joint Conference on Natural Language Processing (6th : 2013)
CityNagoya, Japan
Period14/10/1318/10/13

Fingerprint Dive into the research topics of 'Automatic prediction of evidence-based recommendations via sentence-level polarity classification'. Together they form a unique fingerprint.

Cite this