@inproceedings{baran-etal-2022-twitter,
title = "Does {T}witter know your political views? {POL}i{T}weets dataset and semi-automatic method for political leaning discovery",
author = "Baran, Joanna and
Kajstura, Micha{\l} and
Ziolkowski, Maciej and
Rajda, Krzysztof",
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-1.8",
pages = "56--61",
abstract = "Every day, the world is flooded by millions of messages and statements posted on Twitter or Facebook. Social media platforms try to protect users{'} personal data, but there still is a real risk of misuse, including elections manipulation. Did you know, that only 10 posts addressing important or controversial topics for society are enough to predict one{'}s political affiliation with a 0.85 F1-score? To examine this phenomenon, we created a novel universal method of semi-automated political leaning discovery. It relies on a heuristical data annotation procedure, which was evaluated to achieve 0.95 agreement with human annotators (counted as an accuracy metric). We also present POLiTweets - the first publicly open Polish dataset for political affiliation discovery in a multi-party setup, consisting of over 147k tweets from almost 10k Polish-writing users annotated heuristically and almost 40k tweets from 166 users annotated manually as a test set. We used our data to study the aspects of domain shift in the context of topics and the type of content writers - ordinary citizens vs. professional politicians.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="baran-etal-2022-twitter">
<titleInfo>
<title>Does Twitter know your political views? POLiTweets dataset and semi-automatic method for political leaning discovery</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joanna</namePart>
<namePart type="family">Baran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michał</namePart>
<namePart type="family">Kajstura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maciej</namePart>
<namePart type="family">Ziolkowski</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>
<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>Every day, the world is flooded by millions of messages and statements posted on Twitter or Facebook. Social media platforms try to protect users’ personal data, but there still is a real risk of misuse, including elections manipulation. Did you know, that only 10 posts addressing important or controversial topics for society are enough to predict one’s political affiliation with a 0.85 F1-score? To examine this phenomenon, we created a novel universal method of semi-automated political leaning discovery. It relies on a heuristical data annotation procedure, which was evaluated to achieve 0.95 agreement with human annotators (counted as an accuracy metric). We also present POLiTweets - the first publicly open Polish dataset for political affiliation discovery in a multi-party setup, consisting of over 147k tweets from almost 10k Polish-writing users annotated heuristically and almost 40k tweets from 166 users annotated manually as a test set. We used our data to study the aspects of domain shift in the context of topics and the type of content writers - ordinary citizens vs. professional politicians.</abstract>
<identifier type="citekey">baran-etal-2022-twitter</identifier>
<location>
<url>https://aclanthology.org/2022.politicalnlp-1.8</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>56</start>
<end>61</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Does Twitter know your political views? POLiTweets dataset and semi-automatic method for political leaning discovery
%A Baran, Joanna
%A Kajstura, Michał
%A Ziolkowski, Maciej
%A Rajda, Krzysztof
%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-twitter
%X Every day, the world is flooded by millions of messages and statements posted on Twitter or Facebook. Social media platforms try to protect users’ personal data, but there still is a real risk of misuse, including elections manipulation. Did you know, that only 10 posts addressing important or controversial topics for society are enough to predict one’s political affiliation with a 0.85 F1-score? To examine this phenomenon, we created a novel universal method of semi-automated political leaning discovery. It relies on a heuristical data annotation procedure, which was evaluated to achieve 0.95 agreement with human annotators (counted as an accuracy metric). We also present POLiTweets - the first publicly open Polish dataset for political affiliation discovery in a multi-party setup, consisting of over 147k tweets from almost 10k Polish-writing users annotated heuristically and almost 40k tweets from 166 users annotated manually as a test set. We used our data to study the aspects of domain shift in the context of topics and the type of content writers - ordinary citizens vs. professional politicians.
%U https://aclanthology.org/2022.politicalnlp-1.8
%P 56-61
Markdown (Informal)
[Does Twitter know your political views? POLiTweets dataset and semi-automatic method for political leaning discovery](https://aclanthology.org/2022.politicalnlp-1.8) (Baran et al., PoliticalNLP 2022)
ACL