@inproceedings{kumaresan-etal-2024-dataset-identification,
title = "Dataset for Identification of Homophobia and Transphobia for {T}elugu, {K}annada, and {G}ujarati",
author = "Kumaresan, Prasanna Kumar and
Ponnusamy, Rahul and
Sharma, Dhruv and
Buitelaar, Paul and
Chakravarthi, Bharathi Raja",
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.393",
pages = "4404--4411",
abstract = "Users of social media platforms are negatively affected by the proliferation of hate or abusive content. There has been a rise in homophobic and transphobic content in recent years targeting LGBT+ individuals. The increasing levels of homophobia and transphobia online can make online platforms harmful and threatening for LGBT+ persons, potentially inhibiting equality, diversity, and inclusion. We are introducing a new dataset for three languages, namely Telugu, Kannada, and Gujarati. Additionally, we have created an expert-labeled dataset to automatically identify homophobic and transphobic content within comments collected from YouTube. We provided comprehensive annotation rules to educate annotators in this process. We collected approximately 10,000 comments from YouTube for all three languages. Marking the first dataset of these languages for this task, we also developed a baseline model with pre-trained transformers.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kumaresan-etal-2024-dataset-identification">
<titleInfo>
<title>Dataset for Identification of Homophobia and Transphobia for Telugu, Kannada, and Gujarati</title>
</titleInfo>
<name type="personal">
<namePart type="given">Prasanna</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Kumaresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Ponnusamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhruv</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Buitelaar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</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>Users of social media platforms are negatively affected by the proliferation of hate or abusive content. There has been a rise in homophobic and transphobic content in recent years targeting LGBT+ individuals. The increasing levels of homophobia and transphobia online can make online platforms harmful and threatening for LGBT+ persons, potentially inhibiting equality, diversity, and inclusion. We are introducing a new dataset for three languages, namely Telugu, Kannada, and Gujarati. Additionally, we have created an expert-labeled dataset to automatically identify homophobic and transphobic content within comments collected from YouTube. We provided comprehensive annotation rules to educate annotators in this process. We collected approximately 10,000 comments from YouTube for all three languages. Marking the first dataset of these languages for this task, we also developed a baseline model with pre-trained transformers.</abstract>
<identifier type="citekey">kumaresan-etal-2024-dataset-identification</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.393</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4404</start>
<end>4411</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dataset for Identification of Homophobia and Transphobia for Telugu, Kannada, and Gujarati
%A Kumaresan, Prasanna Kumar
%A Ponnusamy, Rahul
%A Sharma, Dhruv
%A Buitelaar, Paul
%A Chakravarthi, Bharathi Raja
%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 kumaresan-etal-2024-dataset-identification
%X Users of social media platforms are negatively affected by the proliferation of hate or abusive content. There has been a rise in homophobic and transphobic content in recent years targeting LGBT+ individuals. The increasing levels of homophobia and transphobia online can make online platforms harmful and threatening for LGBT+ persons, potentially inhibiting equality, diversity, and inclusion. We are introducing a new dataset for three languages, namely Telugu, Kannada, and Gujarati. Additionally, we have created an expert-labeled dataset to automatically identify homophobic and transphobic content within comments collected from YouTube. We provided comprehensive annotation rules to educate annotators in this process. We collected approximately 10,000 comments from YouTube for all three languages. Marking the first dataset of these languages for this task, we also developed a baseline model with pre-trained transformers.
%U https://aclanthology.org/2024.lrec-main.393
%P 4404-4411
Markdown (Informal)
[Dataset for Identification of Homophobia and Transphobia for Telugu, Kannada, and Gujarati](https://aclanthology.org/2024.lrec-main.393) (Kumaresan et al., LREC-COLING 2024)
ACL
- Prasanna Kumar Kumaresan, Rahul Ponnusamy, Dhruv Sharma, Paul Buitelaar, and Bharathi Raja Chakravarthi. 2024. Dataset for Identification of Homophobia and Transphobia for Telugu, Kannada, and Gujarati. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 4404–4411, Torino, Italia. ELRA and ICCL.