@inproceedings{baran-etal-2022-electoral,
title = "Electoral Agitation Dataset: The Use Case of the {P}olish Election",
author = "Baran, Mateusz and
W{\'o}jcik, Mateusz and
Kolebski, Piotr and
Bernaczyk, Micha{\l} and
Rajda, Krzysztof and
Augustyniak, Lukasz and
Kajdanowicz, Tomasz",
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-1.5",
pages = "32--36",
abstract = "The popularity of social media makes politicians use it for political advertisement. Therefore, social media is full of electoral agitation (electioneering), especially during the election campaigns. The election administration cannot track the spread and quantity of messages that count as agitation under the election code. It addresses a crucial problem, while also uncovering a niche that has not been effectively targeted so far. Hence, we present the first publicly open data set for detecting electoral agitation in the Polish language. It contains 6,112 human-annotated tweets tagged with four legally conditioned categories. We achieved a 0.66 inter-annotator agreement (Cohen{'}s kappa score). An additional annotator resolved the mismatches between the first two improving the consistency and complexity of the annotation process. The newly created data set was used to fine-tune a Polish Language Model called HerBERT (achieving a 68{\%} F1 score). We also present a number of potential use cases for such data sets and models, enriching the paper with an analysis of the Polish 2020 Presidential Election on Twitter.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="baran-etal-2022-electoral">
<titleInfo>
<title>Electoral Agitation Dataset: The Use Case of the Polish Election</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mateusz</namePart>
<namePart type="family">Baran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mateusz</namePart>
<namePart type="family">Wójcik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Kolebski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michał</namePart>
<namePart type="family">Bernaczyk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krzysztof</namePart>
<namePart type="family">Rajda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lukasz</namePart>
<namePart type="family">Augustyniak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomasz</namePart>
<namePart type="family">Kajdanowicz</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>The popularity of social media makes politicians use it for political advertisement. Therefore, social media is full of electoral agitation (electioneering), especially during the election campaigns. The election administration cannot track the spread and quantity of messages that count as agitation under the election code. It addresses a crucial problem, while also uncovering a niche that has not been effectively targeted so far. Hence, we present the first publicly open data set for detecting electoral agitation in the Polish language. It contains 6,112 human-annotated tweets tagged with four legally conditioned categories. We achieved a 0.66 inter-annotator agreement (Cohen’s kappa score). An additional annotator resolved the mismatches between the first two improving the consistency and complexity of the annotation process. The newly created data set was used to fine-tune a Polish Language Model called HerBERT (achieving a 68% F1 score). We also present a number of potential use cases for such data sets and models, enriching the paper with an analysis of the Polish 2020 Presidential Election on Twitter.</abstract>
<identifier type="citekey">baran-etal-2022-electoral</identifier>
<location>
<url>https://aclanthology.org/2022.politicalnlp-1.5</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>32</start>
<end>36</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Electoral Agitation Dataset: The Use Case of the Polish Election
%A Baran, Mateusz
%A Wójcik, Mateusz
%A Kolebski, Piotr
%A Bernaczyk, Michał
%A Rajda, Krzysztof
%A Augustyniak, Lukasz
%A Kajdanowicz, Tomasz
%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 baran-etal-2022-electoral
%X The popularity of social media makes politicians use it for political advertisement. Therefore, social media is full of electoral agitation (electioneering), especially during the election campaigns. The election administration cannot track the spread and quantity of messages that count as agitation under the election code. It addresses a crucial problem, while also uncovering a niche that has not been effectively targeted so far. Hence, we present the first publicly open data set for detecting electoral agitation in the Polish language. It contains 6,112 human-annotated tweets tagged with four legally conditioned categories. We achieved a 0.66 inter-annotator agreement (Cohen’s kappa score). An additional annotator resolved the mismatches between the first two improving the consistency and complexity of the annotation process. The newly created data set was used to fine-tune a Polish Language Model called HerBERT (achieving a 68% F1 score). We also present a number of potential use cases for such data sets and models, enriching the paper with an analysis of the Polish 2020 Presidential Election on Twitter.
%U https://aclanthology.org/2022.politicalnlp-1.5
%P 32-36
Markdown (Informal)
[Electoral Agitation Dataset: The Use Case of the Polish Election](https://aclanthology.org/2022.politicalnlp-1.5) (Baran et al., PoliticalNLP 2022)
ACL
- Mateusz Baran, Mateusz Wójcik, Piotr Kolebski, Michał Bernaczyk, Krzysztof Rajda, Lukasz Augustyniak, and Tomasz Kajdanowicz. 2022. Electoral Agitation Dataset: The Use Case of the Polish Election. In Proceedings of the LREC 2022 workshop on Natural Language Processing for Political Sciences, pages 32–36, Marseille, France. European Language Resources Association.