@inproceedings{zheng-etal-2022-stanceosaurus,
title = "Stanceosaurus: Classifying Stance Towards Multicultural Misinformation",
author = "Zheng, Jonathan and
Baheti, Ashutosh and
Naous, Tarek and
Xu, Wei and
Ritter, Alan",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.138",
doi = "10.18653/v1/2022.emnlp-main.138",
pages = "2132--2151",
abstract = "We present Stanceosaurus, a new corpus of 28,033 tweets in English, Hindi and Arabic annotated with stance towards 250 misinformation claims. As far as we are aware, it is the largest corpus annotated with stance towards misinformation claims. The claims in Stanceosaurus originate from 15 fact-checking sources that cover diverse geographical regions and cultures. Unlike existing stance datasets, we introduce a more fine-grained 5-class labeling strategy with additional subcategories to distinguish implicit stance. Pre-trained transformer-based stance classifiers that are fine-tuned on our corpus show good generalization on unseen claims and regional claims from countries outside the training data. Cross-lingual experiments demonstrate Stanceosaurus{'} capability of training multilingual models, achieving 53.1 F1 on Hindi and 50.4 F1 on Arabic without any target-language fine-tuning. Finally, we show how a domain adaptation method can be used to improve performance on Stanceosaurus using additional RumourEval-2019 data. We will make Stanceosaurus publicly available to the research community upon publication and hope it will encourage further work on misinformation identification across languages and cultures.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-etal-2022-stanceosaurus">
<titleInfo>
<title>Stanceosaurus: Classifying Stance Towards Multicultural Misinformation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashutosh</namePart>
<namePart type="family">Baheti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tarek</namePart>
<namePart type="family">Naous</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present Stanceosaurus, a new corpus of 28,033 tweets in English, Hindi and Arabic annotated with stance towards 250 misinformation claims. As far as we are aware, it is the largest corpus annotated with stance towards misinformation claims. The claims in Stanceosaurus originate from 15 fact-checking sources that cover diverse geographical regions and cultures. Unlike existing stance datasets, we introduce a more fine-grained 5-class labeling strategy with additional subcategories to distinguish implicit stance. Pre-trained transformer-based stance classifiers that are fine-tuned on our corpus show good generalization on unseen claims and regional claims from countries outside the training data. Cross-lingual experiments demonstrate Stanceosaurus’ capability of training multilingual models, achieving 53.1 F1 on Hindi and 50.4 F1 on Arabic without any target-language fine-tuning. Finally, we show how a domain adaptation method can be used to improve performance on Stanceosaurus using additional RumourEval-2019 data. We will make Stanceosaurus publicly available to the research community upon publication and hope it will encourage further work on misinformation identification across languages and cultures.</abstract>
<identifier type="citekey">zheng-etal-2022-stanceosaurus</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.138</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.138</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>2132</start>
<end>2151</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Stanceosaurus: Classifying Stance Towards Multicultural Misinformation
%A Zheng, Jonathan
%A Baheti, Ashutosh
%A Naous, Tarek
%A Xu, Wei
%A Ritter, Alan
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F zheng-etal-2022-stanceosaurus
%X We present Stanceosaurus, a new corpus of 28,033 tweets in English, Hindi and Arabic annotated with stance towards 250 misinformation claims. As far as we are aware, it is the largest corpus annotated with stance towards misinformation claims. The claims in Stanceosaurus originate from 15 fact-checking sources that cover diverse geographical regions and cultures. Unlike existing stance datasets, we introduce a more fine-grained 5-class labeling strategy with additional subcategories to distinguish implicit stance. Pre-trained transformer-based stance classifiers that are fine-tuned on our corpus show good generalization on unseen claims and regional claims from countries outside the training data. Cross-lingual experiments demonstrate Stanceosaurus’ capability of training multilingual models, achieving 53.1 F1 on Hindi and 50.4 F1 on Arabic without any target-language fine-tuning. Finally, we show how a domain adaptation method can be used to improve performance on Stanceosaurus using additional RumourEval-2019 data. We will make Stanceosaurus publicly available to the research community upon publication and hope it will encourage further work on misinformation identification across languages and cultures.
%R 10.18653/v1/2022.emnlp-main.138
%U https://aclanthology.org/2022.emnlp-main.138
%U https://doi.org/10.18653/v1/2022.emnlp-main.138
%P 2132-2151
Markdown (Informal)
[Stanceosaurus: Classifying Stance Towards Multicultural Misinformation](https://aclanthology.org/2022.emnlp-main.138) (Zheng et al., EMNLP 2022)
ACL