@inproceedings{ababu-woldeyohannis-2022-afaan,
title = "Afaan {O}romo Hate Speech Detection and Classification on Social Media",
author = "Ababu, Teshome Mulugeta and
Woldeyohannis, Michael Melese",
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.712",
pages = "6612--6619",
abstract = "Hate and offensive speech on social media is targeted to attack an individual or group of community based on protected characteristics such as gender, ethnicity, and religion. Hate and offensive speech on social media is a global problem that suffers the community especially, for an under-resourced language like Afaan Oromo language. One of the most widely spoken Cushitic language families is Afaan Oromo. Our objective is to develop and test a model used to detect and classify Afaan Oromo hate speech on social media. We developed numerous models that were used to detect and classify Afaan Oromo hate speech on social media by using different machine learning algorithms (classical, ensemble, and deep learning) with the combination of different feature extraction techniques such as BOW, TF-IDF, word2vec, and Keras Embedding layers. To perform the task, we required Afaan Oromo datasets, but the datasets were unavailable. By concentrating on four thematic areas of hate speech, such as gender, religion, race, and offensive speech, we were able to collect a total of 12,812 posts and comments from Facebook. BiLSTM with pre-trained word2vec feature extraction is an outperformed algorithm that achieves better accuracy of 0.84 and 0.88 for eight classes and two classes, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ababu-woldeyohannis-2022-afaan">
<titleInfo>
<title>Afaan Oromo Hate Speech Detection and Classification on Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Teshome</namePart>
<namePart type="given">Mulugeta</namePart>
<namePart type="family">Ababu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="given">Melese</namePart>
<namePart type="family">Woldeyohannis</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 Thirteenth 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">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>
</relatedItem>
<abstract>Hate and offensive speech on social media is targeted to attack an individual or group of community based on protected characteristics such as gender, ethnicity, and religion. Hate and offensive speech on social media is a global problem that suffers the community especially, for an under-resourced language like Afaan Oromo language. One of the most widely spoken Cushitic language families is Afaan Oromo. Our objective is to develop and test a model used to detect and classify Afaan Oromo hate speech on social media. We developed numerous models that were used to detect and classify Afaan Oromo hate speech on social media by using different machine learning algorithms (classical, ensemble, and deep learning) with the combination of different feature extraction techniques such as BOW, TF-IDF, word2vec, and Keras Embedding layers. To perform the task, we required Afaan Oromo datasets, but the datasets were unavailable. By concentrating on four thematic areas of hate speech, such as gender, religion, race, and offensive speech, we were able to collect a total of 12,812 posts and comments from Facebook. BiLSTM with pre-trained word2vec feature extraction is an outperformed algorithm that achieves better accuracy of 0.84 and 0.88 for eight classes and two classes, respectively.</abstract>
<identifier type="citekey">ababu-woldeyohannis-2022-afaan</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.712</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6612</start>
<end>6619</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Afaan Oromo Hate Speech Detection and Classification on Social Media
%A Ababu, Teshome Mulugeta
%A Woldeyohannis, Michael Melese
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F ababu-woldeyohannis-2022-afaan
%X Hate and offensive speech on social media is targeted to attack an individual or group of community based on protected characteristics such as gender, ethnicity, and religion. Hate and offensive speech on social media is a global problem that suffers the community especially, for an under-resourced language like Afaan Oromo language. One of the most widely spoken Cushitic language families is Afaan Oromo. Our objective is to develop and test a model used to detect and classify Afaan Oromo hate speech on social media. We developed numerous models that were used to detect and classify Afaan Oromo hate speech on social media by using different machine learning algorithms (classical, ensemble, and deep learning) with the combination of different feature extraction techniques such as BOW, TF-IDF, word2vec, and Keras Embedding layers. To perform the task, we required Afaan Oromo datasets, but the datasets were unavailable. By concentrating on four thematic areas of hate speech, such as gender, religion, race, and offensive speech, we were able to collect a total of 12,812 posts and comments from Facebook. BiLSTM with pre-trained word2vec feature extraction is an outperformed algorithm that achieves better accuracy of 0.84 and 0.88 for eight classes and two classes, respectively.
%U https://aclanthology.org/2022.lrec-1.712
%P 6612-6619
Markdown (Informal)
[Afaan Oromo Hate Speech Detection and Classification on Social Media](https://aclanthology.org/2022.lrec-1.712) (Ababu & Woldeyohannis, LREC 2022)
ACL