@inproceedings{bertsch-bethard-2021-detection,
title = "Detection of Puffery on the {E}nglish {W}ikipedia",
author = "Bertsch, Amanda and
Bethard, Steven",
editor = "Xu, Wei and
Ritter, Alan and
Baldwin, Tim and
Rahimi, Afshin",
booktitle = "Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)",
month = nov,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wnut-1.36",
doi = "10.18653/v1/2021.wnut-1.36",
pages = "329--333",
abstract = "On Wikipedia, an online crowdsourced encyclopedia, volunteers enforce the encyclopedia{'}s editorial policies. Wikipedia{'}s policy on maintaining a neutral point of view has inspired recent research on bias detection, including {``}weasel words{''} and {``}hedges{''}. Yet to date, little work has been done on identifying {``}puffery,{''} phrases that are overly positive without a verifiable source. We demonstrate that collecting training data for this task requires some care, and construct a dataset by combining Wikipedia editorial annotations and information retrieval techniques. We compare several approaches to predicting puffery, and achieve 0.963 f1 score by incorporating citation features into a RoBERTa model. Finally, we demonstrate how to integrate our model with Wikipedia{'}s public infrastructure to give back to the Wikipedia editor community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bertsch-bethard-2021-detection">
<titleInfo>
<title>Detection of Puffery on the English Wikipedia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="family">Bertsch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afshin</namePart>
<namePart type="family">Rahimi</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>On Wikipedia, an online crowdsourced encyclopedia, volunteers enforce the encyclopedia’s editorial policies. Wikipedia’s policy on maintaining a neutral point of view has inspired recent research on bias detection, including “weasel words” and “hedges”. Yet to date, little work has been done on identifying “puffery,” phrases that are overly positive without a verifiable source. We demonstrate that collecting training data for this task requires some care, and construct a dataset by combining Wikipedia editorial annotations and information retrieval techniques. We compare several approaches to predicting puffery, and achieve 0.963 f1 score by incorporating citation features into a RoBERTa model. Finally, we demonstrate how to integrate our model with Wikipedia’s public infrastructure to give back to the Wikipedia editor community.</abstract>
<identifier type="citekey">bertsch-bethard-2021-detection</identifier>
<identifier type="doi">10.18653/v1/2021.wnut-1.36</identifier>
<location>
<url>https://aclanthology.org/2021.wnut-1.36</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>329</start>
<end>333</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Detection of Puffery on the English Wikipedia
%A Bertsch, Amanda
%A Bethard, Steven
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%Y Rahimi, Afshin
%S Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online
%F bertsch-bethard-2021-detection
%X On Wikipedia, an online crowdsourced encyclopedia, volunteers enforce the encyclopedia’s editorial policies. Wikipedia’s policy on maintaining a neutral point of view has inspired recent research on bias detection, including “weasel words” and “hedges”. Yet to date, little work has been done on identifying “puffery,” phrases that are overly positive without a verifiable source. We demonstrate that collecting training data for this task requires some care, and construct a dataset by combining Wikipedia editorial annotations and information retrieval techniques. We compare several approaches to predicting puffery, and achieve 0.963 f1 score by incorporating citation features into a RoBERTa model. Finally, we demonstrate how to integrate our model with Wikipedia’s public infrastructure to give back to the Wikipedia editor community.
%R 10.18653/v1/2021.wnut-1.36
%U https://aclanthology.org/2021.wnut-1.36
%U https://doi.org/10.18653/v1/2021.wnut-1.36
%P 329-333
Markdown (Informal)
[Detection of Puffery on the English Wikipedia](https://aclanthology.org/2021.wnut-1.36) (Bertsch & Bethard, WNUT 2021)
ACL
- Amanda Bertsch and Steven Bethard. 2021. Detection of Puffery on the English Wikipedia. In Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021), pages 329–333, Online. Association for Computational Linguistics.