@inproceedings{miao-etal-2020-detecting,
title = "Detecting Troll Tweets in a Bilingual Corpus",
author = "Miao, Lin and
Last, Mark and
Litvak, Marina",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.766",
pages = "6247--6254",
abstract = "During the past several years, a large amount of troll accounts has emerged with efforts to manipulate public opinion on social network sites. They are often involved in spreading misinformation, fake news, and propaganda with the intent of distracting and sowing discord. This paper aims to detect troll tweets in both English and Russian assuming that the tweets are generated by some {``}troll farm.{''} We reduce this task to the authorship verification problem of determining whether a single tweet is authored by a {``}troll farm{''} account or not. We evaluate a supervised classification approach with monolingual, cross-lingual, and bilingual training scenarios, using several machine learning algorithms, including deep learning. The best results are attained by the bilingual learning, showing the area under the ROC curve (AUC) of 0.875 and 0.828, for tweet classification in English and Russian test sets, respectively. It is noteworthy that these results are obtained using only raw text features, which do not require manual feature engineering efforts. In this paper, we introduce a resource of English and Russian troll tweets containing original tweets and translation from English to Russian, Russian to English. It is available for academic purposes.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="miao-etal-2020-detecting">
<titleInfo>
<title>Detecting Troll Tweets in a Bilingual Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lin</namePart>
<namePart type="family">Miao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Last</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marina</namePart>
<namePart type="family">Litvak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</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>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>During the past several years, a large amount of troll accounts has emerged with efforts to manipulate public opinion on social network sites. They are often involved in spreading misinformation, fake news, and propaganda with the intent of distracting and sowing discord. This paper aims to detect troll tweets in both English and Russian assuming that the tweets are generated by some “troll farm.” We reduce this task to the authorship verification problem of determining whether a single tweet is authored by a “troll farm” account or not. We evaluate a supervised classification approach with monolingual, cross-lingual, and bilingual training scenarios, using several machine learning algorithms, including deep learning. The best results are attained by the bilingual learning, showing the area under the ROC curve (AUC) of 0.875 and 0.828, for tweet classification in English and Russian test sets, respectively. It is noteworthy that these results are obtained using only raw text features, which do not require manual feature engineering efforts. In this paper, we introduce a resource of English and Russian troll tweets containing original tweets and translation from English to Russian, Russian to English. It is available for academic purposes.</abstract>
<identifier type="citekey">miao-etal-2020-detecting</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.766</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6247</start>
<end>6254</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Detecting Troll Tweets in a Bilingual Corpus
%A Miao, Lin
%A Last, Mark
%A Litvak, Marina
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F miao-etal-2020-detecting
%X During the past several years, a large amount of troll accounts has emerged with efforts to manipulate public opinion on social network sites. They are often involved in spreading misinformation, fake news, and propaganda with the intent of distracting and sowing discord. This paper aims to detect troll tweets in both English and Russian assuming that the tweets are generated by some “troll farm.” We reduce this task to the authorship verification problem of determining whether a single tweet is authored by a “troll farm” account or not. We evaluate a supervised classification approach with monolingual, cross-lingual, and bilingual training scenarios, using several machine learning algorithms, including deep learning. The best results are attained by the bilingual learning, showing the area under the ROC curve (AUC) of 0.875 and 0.828, for tweet classification in English and Russian test sets, respectively. It is noteworthy that these results are obtained using only raw text features, which do not require manual feature engineering efforts. In this paper, we introduce a resource of English and Russian troll tweets containing original tweets and translation from English to Russian, Russian to English. It is available for academic purposes.
%U https://aclanthology.org/2020.lrec-1.766
%P 6247-6254
Markdown (Informal)
[Detecting Troll Tweets in a Bilingual Corpus](https://aclanthology.org/2020.lrec-1.766) (Miao et al., LREC 2020)
ACL
- Lin Miao, Mark Last, and Marina Litvak. 2020. Detecting Troll Tweets in a Bilingual Corpus. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 6247–6254, Marseille, France. European Language Resources Association.