@inproceedings{augustyniak-etal-2020-political,
title = "Political Advertising Dataset: the use case of the {P}olish 2020 Presidential Elections",
author = "Augustyniak, Lukasz and
Rajda, Krzysztof and
Kajdanowicz, Tomasz and
Bernaczyk, Micha{\l}",
editor = "Cunha, Rossana and
Shaikh, Samira and
Varis, Erika and
Georgi, Ryan and
Tsai, Alicia and
Anastasopoulos, Antonios and
Chandu, Khyathi Raghavi",
booktitle = "Proceedings of the Fourth Widening Natural Language Processing Workshop",
month = jul,
year = "2020",
address = "Seattle, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.winlp-1.28",
doi = "10.18653/v1/2020.winlp-1.28",
pages = "110--114",
abstract = "Political campaigns are full of political ads posted by candidates on social media. Political advertisements constitute a basic form of campaigning, subjected to various social requirements. We present the first publicly open dataset for detecting specific text chunks and categories of political advertising in the Polish language. It contains 1,705 human-annotated tweets tagged with nine categories, which constitute campaigning under Polish electoral law. We achieved a 0.65 inter-annotator agreement (Cohen{'}s kappa score). An additional annotator resolved the mismatches between the first two annotators improving the consistency and complexity of the annotation process. We used the newly created dataset to train a well established neural tagger (achieving a 70{\%} percent points F1 score). We also present a possible direction of use cases for such datasets and models with an initial analysis of the Polish 2020 Presidential Elections on Twitter.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="augustyniak-etal-2020-political">
<titleInfo>
<title>Political Advertising Dataset: the use case of the Polish 2020 Presidential Elections</title>
</titleInfo>
<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">Krzysztof</namePart>
<namePart type="family">Rajda</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>
<name type="personal">
<namePart type="given">Michał</namePart>
<namePart type="family">Bernaczyk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Widening Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rossana</namePart>
<namePart type="family">Cunha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samira</namePart>
<namePart type="family">Shaikh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erika</namePart>
<namePart type="family">Varis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Georgi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alicia</namePart>
<namePart type="family">Tsai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khyathi</namePart>
<namePart type="given">Raghavi</namePart>
<namePart type="family">Chandu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Political campaigns are full of political ads posted by candidates on social media. Political advertisements constitute a basic form of campaigning, subjected to various social requirements. We present the first publicly open dataset for detecting specific text chunks and categories of political advertising in the Polish language. It contains 1,705 human-annotated tweets tagged with nine categories, which constitute campaigning under Polish electoral law. We achieved a 0.65 inter-annotator agreement (Cohen’s kappa score). An additional annotator resolved the mismatches between the first two annotators improving the consistency and complexity of the annotation process. We used the newly created dataset to train a well established neural tagger (achieving a 70% percent points F1 score). We also present a possible direction of use cases for such datasets and models with an initial analysis of the Polish 2020 Presidential Elections on Twitter.</abstract>
<identifier type="citekey">augustyniak-etal-2020-political</identifier>
<identifier type="doi">10.18653/v1/2020.winlp-1.28</identifier>
<location>
<url>https://aclanthology.org/2020.winlp-1.28</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>110</start>
<end>114</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Political Advertising Dataset: the use case of the Polish 2020 Presidential Elections
%A Augustyniak, Lukasz
%A Rajda, Krzysztof
%A Kajdanowicz, Tomasz
%A Bernaczyk, Michał
%Y Cunha, Rossana
%Y Shaikh, Samira
%Y Varis, Erika
%Y Georgi, Ryan
%Y Tsai, Alicia
%Y Anastasopoulos, Antonios
%Y Chandu, Khyathi Raghavi
%S Proceedings of the Fourth Widening Natural Language Processing Workshop
%D 2020
%8 July
%I Association for Computational Linguistics
%C Seattle, USA
%F augustyniak-etal-2020-political
%X Political campaigns are full of political ads posted by candidates on social media. Political advertisements constitute a basic form of campaigning, subjected to various social requirements. We present the first publicly open dataset for detecting specific text chunks and categories of political advertising in the Polish language. It contains 1,705 human-annotated tweets tagged with nine categories, which constitute campaigning under Polish electoral law. We achieved a 0.65 inter-annotator agreement (Cohen’s kappa score). An additional annotator resolved the mismatches between the first two annotators improving the consistency and complexity of the annotation process. We used the newly created dataset to train a well established neural tagger (achieving a 70% percent points F1 score). We also present a possible direction of use cases for such datasets and models with an initial analysis of the Polish 2020 Presidential Elections on Twitter.
%R 10.18653/v1/2020.winlp-1.28
%U https://aclanthology.org/2020.winlp-1.28
%U https://doi.org/10.18653/v1/2020.winlp-1.28
%P 110-114
Markdown (Informal)
[Political Advertising Dataset: the use case of the Polish 2020 Presidential Elections](https://aclanthology.org/2020.winlp-1.28) (Augustyniak et al., WiNLP 2020)
ACL