@inproceedings{yu-etal-2019-detecting,
title = "Detecting Causal Language Use in Science Findings",
author = "Yu, Bei and
Li, Yingya and
Wang, Jun",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1473",
doi = "10.18653/v1/D19-1473",
pages = "4664--4674",
abstract = "Causal interpretation of correlational findings from observational studies has been a major type of misinformation in science communication. Prior studies on identifying inappropriate use of causal language relied on manual content analysis, which is not scalable for examining a large volume of science publications. In this study, we first annotated a corpus of over 3,000 PubMed research conclusion sentences, then developed a BERT-based prediction model that classifies conclusion sentences into {``}no relationship{''}, {``}correlational{''}, {``}conditional causal{''}, and {``}direct causal{''} categories, achieving an accuracy of 0.90 and a macro-F1 of 0.88. We then applied the prediction model to measure the causal language use in the research conclusions of about 38,000 observational studies in PubMed. The prediction result shows that 21.7{\%} studies used direct causal language exclusively in their conclusions, and 32.4{\%} used some direct causal language. We also found that the ratio of causal language use differs among authors from different countries, challenging the notion of a shared consensus on causal language use in the global science community. Our prediction model could also be used to help identify the inappropriate use of causal language in science publications.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2019-detecting">
<titleInfo>
<title>Detecting Causal Language Use in Science Findings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bei</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingya</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Causal interpretation of correlational findings from observational studies has been a major type of misinformation in science communication. Prior studies on identifying inappropriate use of causal language relied on manual content analysis, which is not scalable for examining a large volume of science publications. In this study, we first annotated a corpus of over 3,000 PubMed research conclusion sentences, then developed a BERT-based prediction model that classifies conclusion sentences into “no relationship”, “correlational”, “conditional causal”, and “direct causal” categories, achieving an accuracy of 0.90 and a macro-F1 of 0.88. We then applied the prediction model to measure the causal language use in the research conclusions of about 38,000 observational studies in PubMed. The prediction result shows that 21.7% studies used direct causal language exclusively in their conclusions, and 32.4% used some direct causal language. We also found that the ratio of causal language use differs among authors from different countries, challenging the notion of a shared consensus on causal language use in the global science community. Our prediction model could also be used to help identify the inappropriate use of causal language in science publications.</abstract>
<identifier type="citekey">yu-etal-2019-detecting</identifier>
<identifier type="doi">10.18653/v1/D19-1473</identifier>
<location>
<url>https://aclanthology.org/D19-1473</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>4664</start>
<end>4674</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Detecting Causal Language Use in Science Findings
%A Yu, Bei
%A Li, Yingya
%A Wang, Jun
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F yu-etal-2019-detecting
%X Causal interpretation of correlational findings from observational studies has been a major type of misinformation in science communication. Prior studies on identifying inappropriate use of causal language relied on manual content analysis, which is not scalable for examining a large volume of science publications. In this study, we first annotated a corpus of over 3,000 PubMed research conclusion sentences, then developed a BERT-based prediction model that classifies conclusion sentences into “no relationship”, “correlational”, “conditional causal”, and “direct causal” categories, achieving an accuracy of 0.90 and a macro-F1 of 0.88. We then applied the prediction model to measure the causal language use in the research conclusions of about 38,000 observational studies in PubMed. The prediction result shows that 21.7% studies used direct causal language exclusively in their conclusions, and 32.4% used some direct causal language. We also found that the ratio of causal language use differs among authors from different countries, challenging the notion of a shared consensus on causal language use in the global science community. Our prediction model could also be used to help identify the inappropriate use of causal language in science publications.
%R 10.18653/v1/D19-1473
%U https://aclanthology.org/D19-1473
%U https://doi.org/10.18653/v1/D19-1473
%P 4664-4674
Markdown (Informal)
[Detecting Causal Language Use in Science Findings](https://aclanthology.org/D19-1473) (Yu et al., EMNLP-IJCNLP 2019)
ACL
- Bei Yu, Yingya Li, and Jun Wang. 2019. Detecting Causal Language Use in Science Findings. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 4664–4674, Hong Kong, China. Association for Computational Linguistics.