@inproceedings{barriere-etal-2022-debating,
title = "Debating {E}urope: A Multilingual Multi-Target Stance Classification Dataset of Online Debates",
author = "Barriere, Valentin and
Balahur, Alexandra and
Ravenet, Brian",
editor = "Afli, Haithem and
Alam, Mehwish and
Bouamor, Houda and
Casagran, Cristina Blasi and
Boland, Colleen and
Ghannay, Sahar",
booktitle = "Proceedings of the LREC 2022 workshop on Natural Language Processing for Political Sciences",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.politicalnlp-1.3",
pages = "16--21",
abstract = "We present a new dataset of online debates in English, annotated with stance. The dataset was scraped from the {``}\textit{Debating Europe}{''} platform, where users exchange opinions over different subjects related to the European Union. The dataset is composed of 2600 comments pertaining to 18 debates related to the {``}\textit{European Green Deal}{''}, in a conversational setting. After presenting the dataset and the annotated sub-part, we pre-train a model for a multilingual stance classification over the X-stance dataset before fine-tuning it over our dataset, and vice-versa. The fine-tuned models are shown to improve stance classification performance on each of the datasets, even though they have different languages, topics and targets. Subsequently, we propose to enhance the performances over {``}\textit{Debating Europe}{''} with an interaction-aware model, taking advantage of the online debate structure of the platform. We also propose a semi-supervised self-training method to take advantage of the imbalanced and unlabeled data from the whole website, leading to a final improvement of accuracy by 3.4{\%} over a Vanilla XLM-R model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="barriere-etal-2022-debating">
<titleInfo>
<title>Debating Europe: A Multilingual Multi-Target Stance Classification Dataset of Online Debates</title>
</titleInfo>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Barriere</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Balahur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Ravenet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the LREC 2022 workshop on Natural Language Processing for Political Sciences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haithem</namePart>
<namePart type="family">Afli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehwish</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="given">Blasi</namePart>
<namePart type="family">Casagran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Colleen</namePart>
<namePart type="family">Boland</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sahar</namePart>
<namePart type="family">Ghannay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a new dataset of online debates in English, annotated with stance. The dataset was scraped from the “Debating Europe” platform, where users exchange opinions over different subjects related to the European Union. The dataset is composed of 2600 comments pertaining to 18 debates related to the “European Green Deal”, in a conversational setting. After presenting the dataset and the annotated sub-part, we pre-train a model for a multilingual stance classification over the X-stance dataset before fine-tuning it over our dataset, and vice-versa. The fine-tuned models are shown to improve stance classification performance on each of the datasets, even though they have different languages, topics and targets. Subsequently, we propose to enhance the performances over “Debating Europe” with an interaction-aware model, taking advantage of the online debate structure of the platform. We also propose a semi-supervised self-training method to take advantage of the imbalanced and unlabeled data from the whole website, leading to a final improvement of accuracy by 3.4% over a Vanilla XLM-R model.</abstract>
<identifier type="citekey">barriere-etal-2022-debating</identifier>
<location>
<url>https://aclanthology.org/2022.politicalnlp-1.3</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>16</start>
<end>21</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Debating Europe: A Multilingual Multi-Target Stance Classification Dataset of Online Debates
%A Barriere, Valentin
%A Balahur, Alexandra
%A Ravenet, Brian
%Y Afli, Haithem
%Y Alam, Mehwish
%Y Bouamor, Houda
%Y Casagran, Cristina Blasi
%Y Boland, Colleen
%Y Ghannay, Sahar
%S Proceedings of the LREC 2022 workshop on Natural Language Processing for Political Sciences
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F barriere-etal-2022-debating
%X We present a new dataset of online debates in English, annotated with stance. The dataset was scraped from the “Debating Europe” platform, where users exchange opinions over different subjects related to the European Union. The dataset is composed of 2600 comments pertaining to 18 debates related to the “European Green Deal”, in a conversational setting. After presenting the dataset and the annotated sub-part, we pre-train a model for a multilingual stance classification over the X-stance dataset before fine-tuning it over our dataset, and vice-versa. The fine-tuned models are shown to improve stance classification performance on each of the datasets, even though they have different languages, topics and targets. Subsequently, we propose to enhance the performances over “Debating Europe” with an interaction-aware model, taking advantage of the online debate structure of the platform. We also propose a semi-supervised self-training method to take advantage of the imbalanced and unlabeled data from the whole website, leading to a final improvement of accuracy by 3.4% over a Vanilla XLM-R model.
%U https://aclanthology.org/2022.politicalnlp-1.3
%P 16-21
Markdown (Informal)
[Debating Europe: A Multilingual Multi-Target Stance Classification Dataset of Online Debates](https://aclanthology.org/2022.politicalnlp-1.3) (Barriere et al., PoliticalNLP 2022)
ACL