Classifying Negative Findings in Biomedical Publications

Bei Yu, Daniele Fanelli

Research output: Chapter in Book/Entry/PoemConference contribution


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 languageEnglish (US)
Title of host publicationACL 2014 - BioNLP 2014, Workshop on Biomedical Natural Language Processing, Proceedings of the Workshop
PublisherAssociation for Computational Linguistics (ACL)
Number of pages5
ISBN (Electronic)9781941643181
StatePublished - 2014
Externally publishedYes
EventACL 2014 Workshop on Biomedical Natural Language Processing, BioNLP 2014 - Baltimore, United States
Duration: Jun 27 2014Jun 28 2014

Publication series

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


ConferenceACL 2014 Workshop on Biomedical Natural Language Processing, BioNLP 2014
Country/TerritoryUnited States

ASJC Scopus subject areas

  • Computer Science Applications
  • Linguistics and Language
  • Language and Linguistics


Dive into the research topics of 'Classifying Negative Findings in Biomedical Publications'. Together they form a unique fingerprint.

Cite this