@inproceedings{wuhrl-klinger-2021-claim,
title = "Claim Detection in Biomedical {T}witter Posts",
author = {W{\"u}hrl, Amelie and
Klinger, Roman},
editor = "Demner-Fushman, Dina and
Cohen, Kevin Bretonnel and
Ananiadou, Sophia and
Tsujii, Junichi",
booktitle = "Proceedings of the 20th Workshop on Biomedical Language Processing",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.bionlp-1.15/",
doi = "10.18653/v1/2021.bionlp-1.15",
pages = "131--142",
abstract = "Social media contains unfiltered and unique information, which is potentially of great value, but, in the case of misinformation, can also do great harm. With regards to biomedical topics, false information can be particularly dangerous. Methods of automatic fact-checking and fake news detection address this problem, but have not been applied to the biomedical domain in social media yet. We aim to fill this research gap and annotate a corpus of 1200 tweets for implicit and explicit biomedical claims (the latter also with span annotations for the claim phrase). With this corpus, which we sample to be related to COVID-19, measles, cystic fibrosis, and depression, we develop baseline models which detect tweets that contain a claim automatically. Our analyses reveal that biomedical tweets are densely populated with claims (45 {\%} in a corpus sampled to contain 1200 tweets focused on the domains mentioned above). Baseline classification experiments with embedding-based classifiers and BERT-based transfer learning demonstrate that the detection is challenging, however, shows acceptable performance for the identification of explicit expressions of claims. Implicit claim tweets are more challenging to detect."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wuhrl-klinger-2021-claim">
<titleInfo>
<title>Claim Detection in Biomedical Twitter Posts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amelie</namePart>
<namePart type="family">Wührl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Klinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Workshop on Biomedical Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="given">Bretonnel</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Social media contains unfiltered and unique information, which is potentially of great value, but, in the case of misinformation, can also do great harm. With regards to biomedical topics, false information can be particularly dangerous. Methods of automatic fact-checking and fake news detection address this problem, but have not been applied to the biomedical domain in social media yet. We aim to fill this research gap and annotate a corpus of 1200 tweets for implicit and explicit biomedical claims (the latter also with span annotations for the claim phrase). With this corpus, which we sample to be related to COVID-19, measles, cystic fibrosis, and depression, we develop baseline models which detect tweets that contain a claim automatically. Our analyses reveal that biomedical tweets are densely populated with claims (45 % in a corpus sampled to contain 1200 tweets focused on the domains mentioned above). Baseline classification experiments with embedding-based classifiers and BERT-based transfer learning demonstrate that the detection is challenging, however, shows acceptable performance for the identification of explicit expressions of claims. Implicit claim tweets are more challenging to detect.</abstract>
<identifier type="citekey">wuhrl-klinger-2021-claim</identifier>
<identifier type="doi">10.18653/v1/2021.bionlp-1.15</identifier>
<location>
<url>https://aclanthology.org/2021.bionlp-1.15/</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>131</start>
<end>142</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Claim Detection in Biomedical Twitter Posts
%A Wührl, Amelie
%A Klinger, Roman
%Y Demner-Fushman, Dina
%Y Cohen, Kevin Bretonnel
%Y Ananiadou, Sophia
%Y Tsujii, Junichi
%S Proceedings of the 20th Workshop on Biomedical Language Processing
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F wuhrl-klinger-2021-claim
%X Social media contains unfiltered and unique information, which is potentially of great value, but, in the case of misinformation, can also do great harm. With regards to biomedical topics, false information can be particularly dangerous. Methods of automatic fact-checking and fake news detection address this problem, but have not been applied to the biomedical domain in social media yet. We aim to fill this research gap and annotate a corpus of 1200 tweets for implicit and explicit biomedical claims (the latter also with span annotations for the claim phrase). With this corpus, which we sample to be related to COVID-19, measles, cystic fibrosis, and depression, we develop baseline models which detect tweets that contain a claim automatically. Our analyses reveal that biomedical tweets are densely populated with claims (45 % in a corpus sampled to contain 1200 tweets focused on the domains mentioned above). Baseline classification experiments with embedding-based classifiers and BERT-based transfer learning demonstrate that the detection is challenging, however, shows acceptable performance for the identification of explicit expressions of claims. Implicit claim tweets are more challenging to detect.
%R 10.18653/v1/2021.bionlp-1.15
%U https://aclanthology.org/2021.bionlp-1.15/
%U https://doi.org/10.18653/v1/2021.bionlp-1.15
%P 131-142
Markdown (Informal)
[Claim Detection in Biomedical Twitter Posts](https://aclanthology.org/2021.bionlp-1.15/) (Wührl & Klinger, BioNLP 2021)
ACL
- Amelie Wührl and Roman Klinger. 2021. Claim Detection in Biomedical Twitter Posts. In Proceedings of the 20th Workshop on Biomedical Language Processing, pages 131–142, Online. Association for Computational Linguistics.