@inproceedings{lande-etal-2023-kaustubhsharedtask,
title = "{K}austubh{S}hared{T}ask@{LT}-{EDI} 2023: Homophobia-Transphobia Detection in Social Media Comments with {NLPAUG}-driven Data Augmentation",
author = "Lande, Kaustubh and
Ponnusamy, Rahul and
Kumaresan, Prasanna Kumar and
Chakravarthi, Bharathi Raja",
editor = "Chakravarthi, Bharathi R. and
Bharathi, B. and
Griffith, Joephine and
Bali, Kalika and
Buitelaar, Paul",
booktitle = "Proceedings of the Third Workshop on Language Technology for Equality, Diversity and Inclusion",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.ltedi-1.10",
pages = "71--77",
abstract = "Our research in Natural Language Processing (NLP) aims to detect hate speech comments specifically targeted at the LGBTQ+ community within the YouTube platform shared task conducted by LTEDI workshop. The dataset provided by the organizers exhibited a high degree of class imbalance, and to mitigate this, we employed NLPAUG, a data augmentation library. We employed several classification methods and reported the results using recall, precision, and F1-score metrics. The classification models discussed in this paper include a Bidirectional Long Short-Term Memory (BiLSTM) model trained with Word2Vec embeddings, a BiLSTM model trained with Twitter GloVe embeddings, transformer models such as BERT, DistiBERT, RoBERTa, and XLM-RoBERTa, all of which were trained and fine-tuned. We achieved a weighted F1-score of 0.699 on the test data and secured fifth place in task B with 7 classes for the English language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lande-etal-2023-kaustubhsharedtask">
<titleInfo>
<title>KaustubhSharedTask@LT-EDI 2023: Homophobia-Transphobia Detection in Social Media Comments with NLPAUG-driven Data Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kaustubh</namePart>
<namePart type="family">Lande</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">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">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Language Technology for Equality, Diversity and Inclusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">B</namePart>
<namePart type="family">Bharathi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joephine</namePart>
<namePart type="family">Griffith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Buitelaar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Our research in Natural Language Processing (NLP) aims to detect hate speech comments specifically targeted at the LGBTQ+ community within the YouTube platform shared task conducted by LTEDI workshop. The dataset provided by the organizers exhibited a high degree of class imbalance, and to mitigate this, we employed NLPAUG, a data augmentation library. We employed several classification methods and reported the results using recall, precision, and F1-score metrics. The classification models discussed in this paper include a Bidirectional Long Short-Term Memory (BiLSTM) model trained with Word2Vec embeddings, a BiLSTM model trained with Twitter GloVe embeddings, transformer models such as BERT, DistiBERT, RoBERTa, and XLM-RoBERTa, all of which were trained and fine-tuned. We achieved a weighted F1-score of 0.699 on the test data and secured fifth place in task B with 7 classes for the English language.</abstract>
<identifier type="citekey">lande-etal-2023-kaustubhsharedtask</identifier>
<location>
<url>https://aclanthology.org/2023.ltedi-1.10</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>71</start>
<end>77</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KaustubhSharedTask@LT-EDI 2023: Homophobia-Transphobia Detection in Social Media Comments with NLPAUG-driven Data Augmentation
%A Lande, Kaustubh
%A Ponnusamy, Rahul
%A Kumaresan, Prasanna Kumar
%A Chakravarthi, Bharathi Raja
%Y Chakravarthi, Bharathi R.
%Y Bharathi, B.
%Y Griffith, Joephine
%Y Bali, Kalika
%Y Buitelaar, Paul
%S Proceedings of the Third Workshop on Language Technology for Equality, Diversity and Inclusion
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F lande-etal-2023-kaustubhsharedtask
%X Our research in Natural Language Processing (NLP) aims to detect hate speech comments specifically targeted at the LGBTQ+ community within the YouTube platform shared task conducted by LTEDI workshop. The dataset provided by the organizers exhibited a high degree of class imbalance, and to mitigate this, we employed NLPAUG, a data augmentation library. We employed several classification methods and reported the results using recall, precision, and F1-score metrics. The classification models discussed in this paper include a Bidirectional Long Short-Term Memory (BiLSTM) model trained with Word2Vec embeddings, a BiLSTM model trained with Twitter GloVe embeddings, transformer models such as BERT, DistiBERT, RoBERTa, and XLM-RoBERTa, all of which were trained and fine-tuned. We achieved a weighted F1-score of 0.699 on the test data and secured fifth place in task B with 7 classes for the English language.
%U https://aclanthology.org/2023.ltedi-1.10
%P 71-77
Markdown (Informal)
[KaustubhSharedTask@LT-EDI 2023: Homophobia-Transphobia Detection in Social Media Comments with NLPAUG-driven Data Augmentation](https://aclanthology.org/2023.ltedi-1.10) (Lande et al., LTEDI-WS 2023)
ACL