@inproceedings{szwoch-etal-2022-creation,
title = "Creation of {P}olish Online News Corpus for Political Polarization Studies",
author = "Szwoch, Joanna and
Staszkow, Mateusz and
Rzepka, Rafal and
Araki, Kenji",
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-1.12",
pages = "86--90",
abstract = "In this paper we describe a Polish news corpus as an attempt to create a filtered, organized and representative set of texts coming from contemporary online press articles from two major Polish TV news providers: commercial TVN24 and state-owned TVP Info. The process consists of web scraping, data cleaning and formatting. A random sample was selected from prepared data to perform a classification task. The random forest achieved the best prediction results out of all considered models. We believe that this dataset is a valuable contribution to existing Polish language corpora as online news are considered to be formal and relatively mistake-free, therefore, a reliable source of correct written language, unlike other online platforms such as blogs or social media. Furthermore, to our knowledge, such corpus from this period of time has not been created before. In the future we would like to expand this dataset with articles coming from other online news providers, repeat the classification task on a bigger scale, utilizing other algorithms. Our data analysis outcomes might be a relevant basis to improve research on a political polarization and propaganda techniques in media.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="szwoch-etal-2022-creation">
<titleInfo>
<title>Creation of Polish Online News Corpus for Political Polarization Studies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joanna</namePart>
<namePart type="family">Szwoch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mateusz</namePart>
<namePart type="family">Staszkow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafal</namePart>
<namePart type="family">Rzepka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenji</namePart>
<namePart type="family">Araki</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>In this paper we describe a Polish news corpus as an attempt to create a filtered, organized and representative set of texts coming from contemporary online press articles from two major Polish TV news providers: commercial TVN24 and state-owned TVP Info. The process consists of web scraping, data cleaning and formatting. A random sample was selected from prepared data to perform a classification task. The random forest achieved the best prediction results out of all considered models. We believe that this dataset is a valuable contribution to existing Polish language corpora as online news are considered to be formal and relatively mistake-free, therefore, a reliable source of correct written language, unlike other online platforms such as blogs or social media. Furthermore, to our knowledge, such corpus from this period of time has not been created before. In the future we would like to expand this dataset with articles coming from other online news providers, repeat the classification task on a bigger scale, utilizing other algorithms. Our data analysis outcomes might be a relevant basis to improve research on a political polarization and propaganda techniques in media.</abstract>
<identifier type="citekey">szwoch-etal-2022-creation</identifier>
<location>
<url>https://aclanthology.org/2022.politicalnlp-1.12</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>86</start>
<end>90</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Creation of Polish Online News Corpus for Political Polarization Studies
%A Szwoch, Joanna
%A Staszkow, Mateusz
%A Rzepka, Rafal
%A Araki, Kenji
%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 szwoch-etal-2022-creation
%X In this paper we describe a Polish news corpus as an attempt to create a filtered, organized and representative set of texts coming from contemporary online press articles from two major Polish TV news providers: commercial TVN24 and state-owned TVP Info. The process consists of web scraping, data cleaning and formatting. A random sample was selected from prepared data to perform a classification task. The random forest achieved the best prediction results out of all considered models. We believe that this dataset is a valuable contribution to existing Polish language corpora as online news are considered to be formal and relatively mistake-free, therefore, a reliable source of correct written language, unlike other online platforms such as blogs or social media. Furthermore, to our knowledge, such corpus from this period of time has not been created before. In the future we would like to expand this dataset with articles coming from other online news providers, repeat the classification task on a bigger scale, utilizing other algorithms. Our data analysis outcomes might be a relevant basis to improve research on a political polarization and propaganda techniques in media.
%U https://aclanthology.org/2022.politicalnlp-1.12
%P 86-90
Markdown (Informal)
[Creation of Polish Online News Corpus for Political Polarization Studies](https://aclanthology.org/2022.politicalnlp-1.12) (Szwoch et al., PoliticalNLP 2022)
ACL