@inproceedings{markantonatou-etal-2024-corpus,
title = "The Corpus {AIKIA}: Using Ranking Annotation for Offensive Language Detection in {M}odern {G}reek",
author = "Markantonatou, Stella and
Stamou, Vivian and
Christodoulou, Christina and
Apostolopoulou, Georgia and
Balas, Antonis and
Ioannakis, George",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1378/",
pages = "15861--15871",
abstract = "We introduce a new corpus, named AIKIA, for Offensive Language Detection (OLD) in Modern Greek (EL). EL is a less-resourced language regarding OLD. AIKIA offers free access to annotated data leveraged from EL Twitter and fiction texts using the lexicon of offensive terms, ERIS, that originates from HurtLex. AIKIA has been annotated for offensive values with the Best Worst Scaling (BWS) method, which is designed to avoid problems of categorical and scalar annotation methods. BWS assigns continuous offensive scores in the form of floating point numbers instead of binary arithmetical or categorical values. AIKIA`s performance in OLD was tested by fine-tuning a variety of pre-trained language models in a binary classification task. Experimentation with a number of thresholds showed that the best mapping of the continuous values to binary labels should occur at the range [0.5-0.6] of BWS values and that the pre-trained models on EL data achieved the highest Macro-F1 scores. Greek-Media-BERT outperformed all models with a threshold of 0.6 by obtaining a Macro-F1 score of 0.92"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="markantonatou-etal-2024-corpus">
<titleInfo>
<title>The Corpus AIKIA: Using Ranking Annotation for Offensive Language Detection in Modern Greek</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stella</namePart>
<namePart type="family">Markantonatou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivian</namePart>
<namePart type="family">Stamou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christina</namePart>
<namePart type="family">Christodoulou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georgia</namePart>
<namePart type="family">Apostolopoulou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonis</namePart>
<namePart type="family">Balas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Ioannakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce a new corpus, named AIKIA, for Offensive Language Detection (OLD) in Modern Greek (EL). EL is a less-resourced language regarding OLD. AIKIA offers free access to annotated data leveraged from EL Twitter and fiction texts using the lexicon of offensive terms, ERIS, that originates from HurtLex. AIKIA has been annotated for offensive values with the Best Worst Scaling (BWS) method, which is designed to avoid problems of categorical and scalar annotation methods. BWS assigns continuous offensive scores in the form of floating point numbers instead of binary arithmetical or categorical values. AIKIA‘s performance in OLD was tested by fine-tuning a variety of pre-trained language models in a binary classification task. Experimentation with a number of thresholds showed that the best mapping of the continuous values to binary labels should occur at the range [0.5-0.6] of BWS values and that the pre-trained models on EL data achieved the highest Macro-F1 scores. Greek-Media-BERT outperformed all models with a threshold of 0.6 by obtaining a Macro-F1 score of 0.92</abstract>
<identifier type="citekey">markantonatou-etal-2024-corpus</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1378/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>15861</start>
<end>15871</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Corpus AIKIA: Using Ranking Annotation for Offensive Language Detection in Modern Greek
%A Markantonatou, Stella
%A Stamou, Vivian
%A Christodoulou, Christina
%A Apostolopoulou, Georgia
%A Balas, Antonis
%A Ioannakis, George
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F markantonatou-etal-2024-corpus
%X We introduce a new corpus, named AIKIA, for Offensive Language Detection (OLD) in Modern Greek (EL). EL is a less-resourced language regarding OLD. AIKIA offers free access to annotated data leveraged from EL Twitter and fiction texts using the lexicon of offensive terms, ERIS, that originates from HurtLex. AIKIA has been annotated for offensive values with the Best Worst Scaling (BWS) method, which is designed to avoid problems of categorical and scalar annotation methods. BWS assigns continuous offensive scores in the form of floating point numbers instead of binary arithmetical or categorical values. AIKIA‘s performance in OLD was tested by fine-tuning a variety of pre-trained language models in a binary classification task. Experimentation with a number of thresholds showed that the best mapping of the continuous values to binary labels should occur at the range [0.5-0.6] of BWS values and that the pre-trained models on EL data achieved the highest Macro-F1 scores. Greek-Media-BERT outperformed all models with a threshold of 0.6 by obtaining a Macro-F1 score of 0.92
%U https://aclanthology.org/2024.lrec-main.1378/
%P 15861-15871
Markdown (Informal)
[The Corpus AIKIA: Using Ranking Annotation for Offensive Language Detection in Modern Greek](https://aclanthology.org/2024.lrec-main.1378/) (Markantonatou et al., LREC-COLING 2024)
ACL