Classifying Negative Findings in Biomedical Publications

Bei Yu; Daniele Fanelli

Classifying Negative Findings in Biomedical Publications

Bei Yu, Daniele Fanelli

School of Information Studies

Research output: Chapter in Book/Entry/Poem › Conference contribution

Abstract

Publication bias refers to the phenomenon that statistically significant, “positive” results are more likely to be published than non-significant, “negative” results. Currently, researchers have to manually identify negative results in a large number of publications in order to examine publication biases. This paper proposes an NLP approach for automatically classifying negated sentences in biomedical abstracts as either reporting negative findings or not. Using multinomial naïve Bayes algorithm and bag-of-words features enriched by parts-of-speeches and constituents, we built a classifier that reached 84% accuracy based on 5-fold cross validation on a balanced data set.

Original language	English (US)
Title of host publication	ACL 2014 - BioNLP 2014, Workshop on Biomedical Natural Language Processing, Proceedings of the Workshop
Publisher	Association for Computational Linguistics (ACL)
Pages	19-23
Number of pages	5
ISBN (Electronic)	9781941643181
State	Published - 2014
Event	ACL 2014 Workshop on Biomedical Natural Language Processing, BioNLP 2014 - Baltimore, United States Duration: Jun 27 2014 → Jun 28 2014

Publication series

Name	Proceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)	0736-587X

Conference

Conference	ACL 2014 Workshop on Biomedical Natural Language Processing, BioNLP 2014
Country/Territory	United States
City	Baltimore
Period	6/27/14 → 6/28/14

ASJC Scopus subject areas

Computer Science Applications
Linguistics and Language
Language and Linguistics

Cite this

Classifying Negative Findings in Biomedical Publications. / Yu, Bei; Fanelli, Daniele.
ACL 2014 - BioNLP 2014, Workshop on Biomedical Natural Language Processing, Proceedings of the Workshop. Association for Computational Linguistics (ACL), 2014. p. 19-23 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

Research output: Chapter in Book/Entry/Poem › Conference contribution

Yu, B & Fanelli, D 2014, Classifying Negative Findings in Biomedical Publications. in ACL 2014 - BioNLP 2014, Workshop on Biomedical Natural Language Processing, Proceedings of the Workshop. Proceedings of the Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics (ACL), pp. 19-23, ACL 2014 Workshop on Biomedical Natural Language Processing, BioNLP 2014, Baltimore, United States, 6/27/14.

@inproceedings{8af01794cba849f69a10bed9004f7448,

title = "Classifying Negative Findings in Biomedical Publications",

abstract = "Publication bias refers to the phenomenon that statistically significant, “positive” results are more likely to be published than non-significant, “negative” results. Currently, researchers have to manually identify negative results in a large number of publications in order to examine publication biases. This paper proposes an NLP approach for automatically classifying negated sentences in biomedical abstracts as either reporting negative findings or not. Using multinomial na{\"i}ve Bayes algorithm and bag-of-words features enriched by parts-of-speeches and constituents, we built a classifier that reached 84% accuracy based on 5-fold cross validation on a balanced data set.",

author = "Bei Yu and Daniele Fanelli",

note = "Publisher Copyright: {\textcopyright}2014 Association for Computational Linguistics; ACL 2014 Workshop on Biomedical Natural Language Processing, BioNLP 2014 ; Conference date: 27-06-2014 Through 28-06-2014",

year = "2014",

language = "English (US)",

series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics (ACL)",

pages = "19--23",

booktitle = "ACL 2014 - BioNLP 2014, Workshop on Biomedical Natural Language Processing, Proceedings of the Workshop",

address = "United States",

}

TY - GEN

T1 - Classifying Negative Findings in Biomedical Publications

AU - Yu, Bei

AU - Fanelli, Daniele

PY - 2014

Y1 - 2014

N2 - Publication bias refers to the phenomenon that statistically significant, “positive” results are more likely to be published than non-significant, “negative” results. Currently, researchers have to manually identify negative results in a large number of publications in order to examine publication biases. This paper proposes an NLP approach for automatically classifying negated sentences in biomedical abstracts as either reporting negative findings or not. Using multinomial naïve Bayes algorithm and bag-of-words features enriched by parts-of-speeches and constituents, we built a classifier that reached 84% accuracy based on 5-fold cross validation on a balanced data set.

AB - Publication bias refers to the phenomenon that statistically significant, “positive” results are more likely to be published than non-significant, “negative” results. Currently, researchers have to manually identify negative results in a large number of publications in order to examine publication biases. This paper proposes an NLP approach for automatically classifying negated sentences in biomedical abstracts as either reporting negative findings or not. Using multinomial naïve Bayes algorithm and bag-of-words features enriched by parts-of-speeches and constituents, we built a classifier that reached 84% accuracy based on 5-fold cross validation on a balanced data set.

UR - http://www.scopus.com/inward/record.url?scp=85122514171&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85122514171&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85122514171

T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics

SP - 19

EP - 23

BT - ACL 2014 - BioNLP 2014, Workshop on Biomedical Natural Language Processing, Proceedings of the Workshop

PB - Association for Computational Linguistics (ACL)

T2 - ACL 2014 Workshop on Biomedical Natural Language Processing, BioNLP 2014

Y2 - 27 June 2014 through 28 June 2014

ER -

Classifying Negative Findings in Biomedical Publications

Abstract

Publication series

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this