Simple view

Full metadata view

Authors

Statistics

Approaching automatic cyberbullying detection for Polish tweets

2019
book section
conference proceedings
Publisher
Polska Akademia Nauk
80
Author
Wróbel Krzysztof
Editor
Ogrodniczuk Maciej

Kobyliński Łukasz
Book title / Journal title
Proceedings of the PolEval 2019 Workshop
Place of publication: Publisher
Warszawa : Institute of Computer Sciences. Polish Academy of Sciences
Pages
135-140
ISBN
978-83-63159-28-3
Keywords in English

natural language processing

Polish

text classification

cyberbullying detection

URL
http://2019.poleval.pl/files/poleval2019.pdf
Date accessed
2020-01-22
Language
English
Book language / Journal language
English
Abstract in English

This paper presents contribution to PolEval 20191 automatic cyberbullying detection task. The goal of the task is to classify tweets as harmful or normal. Firstly, the data is preprocessed. Then two classifiers adjusted to the problem are tested: Flair and fastText. Flair utilizes character-based language models, which are evaluated using perplexity. Both classifiers obtained similar scores on test data.

Conference
PolEval 2019 Workshop
Conference start date
2019-05-31
End date conference
2019-05-31
Conference city
Warszawa
Conference country
Polska
Conference type
international
Affiliation
Wydział Zarządzania i Komunikacji Społecznej : Katedra Systemów Informatycznych
dc.abstract.enThis paper presents contribution to PolEval 20191 automatic cyberbullying detection task. The goal of the task is to classify tweets as harmful or normal. Firstly, the data is preprocessed. Then two classifiers adjusted to the problem are tested: Flair and fastText. Flair utilizes character-based language models, which are evaluated using perplexity. Both classifiers obtained similar scores on test data.pl
dc.affiliationWydział Zarządzania i Komunikacji Społecznej : Katedra Systemów Informatycznychpl
dc.conferencePolEval 2019 Workshop
dc.conference.cityWarszawa
dc.conference.countryPolska
dc.conference.datefinish2019-05-31
dc.conference.datestart2019-05-31
dc.contributor.authorWróbel, Krzysztof - 241958 pl
dc.contributor.editorOgrodniczuk, Maciejpl
dc.contributor.editorKobyliński, Łukaszpl
dc.date.accession2020-01-22pl
dc.date.accessioned2020-02-12T11:48:22Z
dc.date.available2020-02-12T11:48:22Z
dc.date.issued2019pl
dc.date.openaccess0
dc.description.accesstimew momencie opublikowania
dc.description.conftypeinternationalpl
dc.description.physical135-140pl
dc.description.publication0,4pl
dc.description.versionostateczna wersja wydawcy
dc.identifier.isbn978-83-63159-28-3pl
dc.identifier.projectROD UJ / OPpl
dc.identifier.urihttps://ruj.uj.edu.pl/xmlui/handle/item/148794
dc.identifier.weblinkhttp://2019.poleval.pl/files/poleval2019.pdfpl
dc.languageengpl
dc.language.containerengpl
dc.pubinfoWarszawa : Institute of Computer Sciences. Polish Academy of Sciencespl
dc.publisher.ministerialPolska Akademia Naukpl
dc.rightsUdzielam licencji. Uznanie autorstwa 4.0 Międzynarodowa*
dc.rights.licenceCC-BY
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/legalcode.pl*
dc.share.typeinne
dc.sourceinfoliczba autorów 38; liczba stron 163; liczba arkuszy wydawniczych 10,8;pl
dc.subject.ennatural language processingpl
dc.subject.enPolishpl
dc.subject.entext classificationpl
dc.subject.encyberbullying detectionpl
dc.subtypeConferenceProceedingspl
dc.titleApproaching automatic cyberbullying detection for Polish tweetspl
dc.title.containerProceedings of the PolEval 2019 Workshoppl
dc.typeBookSectionpl
dspace.entity.typePublication
dc.abstract.enpl
This paper presents contribution to PolEval 20191 automatic cyberbullying detection task. The goal of the task is to classify tweets as harmful or normal. Firstly, the data is preprocessed. Then two classifiers adjusted to the problem are tested: Flair and fastText. Flair utilizes character-based language models, which are evaluated using perplexity. Both classifiers obtained similar scores on test data.
dc.affiliationpl
Wydział Zarządzania i Komunikacji Społecznej : Katedra Systemów Informatycznych
dc.conference
PolEval 2019 Workshop
dc.conference.city
Warszawa
dc.conference.country
Polska
dc.conference.datefinish
2019-05-31
dc.conference.datestart
2019-05-31
dc.contributor.authorpl
Wróbel, Krzysztof - 241958
dc.contributor.editorpl
Ogrodniczuk, Maciej
dc.contributor.editorpl
Kobyliński, Łukasz
dc.date.accessionpl
2020-01-22
dc.date.accessioned
2020-02-12T11:48:22Z
dc.date.available
2020-02-12T11:48:22Z
dc.date.issuedpl
2019
dc.date.openaccess
0
dc.description.accesstime
w momencie opublikowania
dc.description.conftypepl
international
dc.description.physicalpl
135-140
dc.description.publicationpl
0,4
dc.description.version
ostateczna wersja wydawcy
dc.identifier.isbnpl
978-83-63159-28-3
dc.identifier.projectpl
ROD UJ / OP
dc.identifier.uri
https://ruj.uj.edu.pl/xmlui/handle/item/148794
dc.identifier.weblinkpl
http://2019.poleval.pl/files/poleval2019.pdf
dc.languagepl
eng
dc.language.containerpl
eng
dc.pubinfopl
Warszawa : Institute of Computer Sciences. Polish Academy of Sciences
dc.publisher.ministerialpl
Polska Akademia Nauk
dc.rights*
Udzielam licencji. Uznanie autorstwa 4.0 Międzynarodowa
dc.rights.licence
CC-BY
dc.rights.uri*
http://creativecommons.org/licenses/by/4.0/legalcode.pl
dc.share.type
inne
dc.sourceinfopl
liczba autorów 38; liczba stron 163; liczba arkuszy wydawniczych 10,8;
dc.subject.enpl
natural language processing
dc.subject.enpl
Polish
dc.subject.enpl
text classification
dc.subject.enpl
cyberbullying detection
dc.subtypepl
ConferenceProceedings
dc.titlepl
Approaching automatic cyberbullying detection for Polish tweets
dc.title.containerpl
Proceedings of the PolEval 2019 Workshop
dc.typepl
BookSection
dspace.entity.type
Publication
Affiliations
Wydział Zarządzania i Komunikacji Społecznej
Wróbel, Krzysztof
No affiliation
Ogrodniczuk, Maciej
Kobyliński, Łukasz

* The migration of download and view statistics prior to the date of April 8, 2024 is in progress.

Views
13
Views per month
Views per city
South Tangerang
3
Boardman
2
Columbus
2
Wroclaw
2
Ashburn
1
Des Moines
1
Dublin
1
Los Angeles
1
Downloads
wrobel_approaching_automatic_cyberbulliyng_detection_2019.pdf
15
wrobel_approaching_automatic_cyberbulliyng_detection_2019.odt
10

Open Access

Thumbnail Image
License
CC-BY

Except as otherwise noted, this item is licensed under : Udzielam licencji. Uznanie autorstwa 4.0 Międzynarodowa

Collections
Research publications
ROD UJ
Social sciences