Classifying Negative Findings in Biomedical Publications

Bei Yu; Daniele Fanelli

doi:10.3115/v1/W14-3403

Classifying Negative Findings in Biomedical Publications

Bei Yu, Daniele Fanelli

School of Social Sciences

Research output: Chapter in Book/Report/Conference proceeding › 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
Title of host publication	ACL 2014: BioNLP 2014, Workshop on Biomedical Natural Language Processing, Proceedings of the Workshop
Editors	Kevin Cohen, Dina Demner-Fushman, Sophia Ananiadou, Jun-ichi Tsujii
Place of Publication	Baltimore, Maryland
Publisher	Association for Computational Linguistics
Pages	19-23
Number of pages	5
ISBN (Print)	9781941643181
DOIs	https://doi.org/10.3115/v1/W14-3403
Publication status	Published - Jun 2014
Event	ACL 2014 Workshop on Biomedical Natural Language Processing - Baltimore, United States Duration: 27 Jun 2014 → 28 Jun 2014 https://aclanthology.org/volumes/W14-34/

Publication series

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

Conference

Conference	ACL 2014 Workshop on Biomedical Natural Language Processing
Abbreviated title	BioNLP 2014
Country/Territory	United States
City	Baltimore
Period	27/06/14 → 28/06/14
Internet address	https://aclanthology.org/volumes/W14-34/

ASJC Scopus subject areas

Computer Science Applications
Linguistics and Language
Language and Linguistics

Access to Document

10.3115/v1/W14-3403Licence: CC BY

Cite this

Yu, B., & Fanelli, D. (2014). Classifying Negative Findings in Biomedical Publications. In K. Cohen, D. Demner-Fushman, S. Ananiadou, & J. Tsujii (Eds.), ACL 2014: BioNLP 2014, Workshop on Biomedical Natural Language Processing, Proceedings of the Workshop (pp. 19-23). (Proceedings of the Annual Meeting of the Association for Computational Linguistics). Association for Computational Linguistics. https://doi.org/10.3115/v1/W14-3403

Yu, Bei ; Fanelli, Daniele. / Classifying Negative Findings in Biomedical Publications. ACL 2014: BioNLP 2014, Workshop on Biomedical Natural Language Processing, Proceedings of the Workshop. editor / Kevin Cohen ; Dina Demner-Fushman ; Sophia Ananiadou ; Jun-ichi Tsujii. Baltimore, Maryland : Association for Computational Linguistics, 2014. pp. 19-23 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

@inproceedings{9b2f2ace953a46efbb3abd17c25c4771,

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",

month = jun,

doi = "10.3115/v1/W14-3403",

language = "English",

isbn = "9781941643181",

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

publisher = "Association for Computational Linguistics",

pages = "19--23",

editor = "Kevin Cohen and Demner-Fushman, \{Dina \} and Sophia Ananiadou and Jun-ichi Tsujii",

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

url = "https://aclanthology.org/volumes/W14-34/",

}

Yu, B & Fanelli, D 2014, Classifying Negative Findings in Biomedical Publications. in K Cohen, D Demner-Fushman, S Ananiadou & J Tsujii (eds), 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, Baltimore, Maryland, pp. 19-23, ACL 2014 Workshop on Biomedical Natural Language Processing, Baltimore, Maryland, United States, 27/06/14. https://doi.org/10.3115/v1/W14-3403

Classifying Negative Findings in Biomedical Publications. / Yu, Bei; Fanelli, Daniele.
ACL 2014: BioNLP 2014, Workshop on Biomedical Natural Language Processing, Proceedings of the Workshop. ed. / Kevin Cohen; Dina Demner-Fushman; Sophia Ananiadou; Jun-ichi Tsujii. Baltimore, Maryland: Association for Computational Linguistics, 2014. p. 19-23 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

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

TY - GEN

T1 - Classifying Negative Findings in Biomedical Publications

AU - Yu, Bei

AU - Fanelli, Daniele

PY - 2014/6

Y1 - 2014/6

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 - https://www.scopus.com/pages/publications/85122514171

U2 - 10.3115/v1/W14-3403

DO - 10.3115/v1/W14-3403

M3 - Conference contribution

AN - SCOPUS:85122514171

SN - 9781941643181

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

A2 - Cohen, Kevin

A2 - Demner-Fushman, Dina

A2 - Ananiadou, Sophia

A2 - Tsujii, Jun-ichi

PB - Association for Computational Linguistics

CY - Baltimore, Maryland

T2 - ACL 2014 Workshop on Biomedical Natural Language Processing

Y2 - 27 June 2014 through 28 June 2014

ER -

Yu B, Fanelli D. Classifying Negative Findings in Biomedical Publications. In Cohen K, Demner-Fushman D, Ananiadou S, Tsujii J, editors, ACL 2014: BioNLP 2014, Workshop on Biomedical Natural Language Processing, Proceedings of the Workshop. Baltimore, Maryland: Association for Computational Linguistics. 2014. p. 19-23. (Proceedings of the Annual Meeting of the Association for Computational Linguistics). doi: 10.3115/v1/W14-3403

Classifying Negative Findings in Biomedical Publications

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this