@inproceedings{vignesh-etal-2025-skvtrio,
title = "{SKV}trio@{LT}-{EDI}-2025: Hybrid {TF}-{IDF} and {BERT} Embeddings for Multilingual Homophobia and Transphobia Detection in Social Media Comments",
author = "Vignesh, Konkimalla Laxmi and
Krishna, Mahankali Sri Ram and
Keerthana, Dondluru and
B, Premjith",
editor = "Gkirtzou, Katerina and
{\v{Z}}itnik, Slavko and
Gracia, Jorge and
Gromann, Dagmar and
di Buono, Maria Pia and
Monti, Johanna and
Ionov, Maxim",
booktitle = "Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion",
month = sep,
year = "2025",
address = "Naples, Italy",
publisher = "Unior Press",
url = "https://aclanthology.org/2025.ltedi-1.5/",
pages = "26--30",
ISBN = "978-88-6719-334-9",
abstract = "This paper presents a description of the paper submitted to the Shared Task on Homophobia and Transphobia Detection in Social Media Comments, LT-EDI at LDK 2025. We propose a hybrid approach to detect homophobic and transphobic content in low-resource languages using Term Frequency-Inverse Document Frequency (TF-IDF) and Bidirectional Encoder Representations from Transformers (BERT) for contextual embeddings. The TF-IDF helps capture the token{'}s importance, whereas BERT generates contextualized embeddings. This hybridization subsequently generates an embedding that contains statistical surface-level patterns and deep semantic understanding. The system uses principal component analysis (PCA) and a random forest classifier. The application of PCA converts a sparse, very high-dimensional embedding into a dense representation by keeping only the most relevant features. The model achieved robust performance across eight Indian languages, with the highest accuracy in Hindi. However, lower performance in Marathi highlights challenges in low-resource settings. Combining TF-IDF and BERT embeddings leads to better classification results, showing the benefits of integrating simple and complex language models. Limitations include potential feature redundancy and poor performance in languages with complex word forms, indicating a need for future adjustments to support multiple languages and address imbalances."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vignesh-etal-2025-skvtrio">
<titleInfo>
<title>SKVtrio@LT-EDI-2025: Hybrid TF-IDF and BERT Embeddings for Multilingual Homophobia and Transphobia Detection in Social Media Comments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Konkimalla</namePart>
<namePart type="given">Laxmi</namePart>
<namePart type="family">Vignesh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahankali</namePart>
<namePart type="given">Sri</namePart>
<namePart type="given">Ram</namePart>
<namePart type="family">Krishna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dondluru</namePart>
<namePart type="family">Keerthana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Premjith</namePart>
<namePart type="family">B</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katerina</namePart>
<namePart type="family">Gkirtzou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Slavko</namePart>
<namePart type="family">Žitnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Gracia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dagmar</namePart>
<namePart type="family">Gromann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Pia</namePart>
<namePart type="family">di Buono</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Monti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maxim</namePart>
<namePart type="family">Ionov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Unior Press</publisher>
<place>
<placeTerm type="text">Naples, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-88-6719-334-9</identifier>
</relatedItem>
<abstract>This paper presents a description of the paper submitted to the Shared Task on Homophobia and Transphobia Detection in Social Media Comments, LT-EDI at LDK 2025. We propose a hybrid approach to detect homophobic and transphobic content in low-resource languages using Term Frequency-Inverse Document Frequency (TF-IDF) and Bidirectional Encoder Representations from Transformers (BERT) for contextual embeddings. The TF-IDF helps capture the token’s importance, whereas BERT generates contextualized embeddings. This hybridization subsequently generates an embedding that contains statistical surface-level patterns and deep semantic understanding. The system uses principal component analysis (PCA) and a random forest classifier. The application of PCA converts a sparse, very high-dimensional embedding into a dense representation by keeping only the most relevant features. The model achieved robust performance across eight Indian languages, with the highest accuracy in Hindi. However, lower performance in Marathi highlights challenges in low-resource settings. Combining TF-IDF and BERT embeddings leads to better classification results, showing the benefits of integrating simple and complex language models. Limitations include potential feature redundancy and poor performance in languages with complex word forms, indicating a need for future adjustments to support multiple languages and address imbalances.</abstract>
<identifier type="citekey">vignesh-etal-2025-skvtrio</identifier>
<location>
<url>https://aclanthology.org/2025.ltedi-1.5/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>26</start>
<end>30</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SKVtrio@LT-EDI-2025: Hybrid TF-IDF and BERT Embeddings for Multilingual Homophobia and Transphobia Detection in Social Media Comments
%A Vignesh, Konkimalla Laxmi
%A Krishna, Mahankali Sri Ram
%A Keerthana, Dondluru
%A B, Premjith
%Y Gkirtzou, Katerina
%Y Žitnik, Slavko
%Y Gracia, Jorge
%Y Gromann, Dagmar
%Y di Buono, Maria Pia
%Y Monti, Johanna
%Y Ionov, Maxim
%S Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion
%D 2025
%8 September
%I Unior Press
%C Naples, Italy
%@ 978-88-6719-334-9
%F vignesh-etal-2025-skvtrio
%X This paper presents a description of the paper submitted to the Shared Task on Homophobia and Transphobia Detection in Social Media Comments, LT-EDI at LDK 2025. We propose a hybrid approach to detect homophobic and transphobic content in low-resource languages using Term Frequency-Inverse Document Frequency (TF-IDF) and Bidirectional Encoder Representations from Transformers (BERT) for contextual embeddings. The TF-IDF helps capture the token’s importance, whereas BERT generates contextualized embeddings. This hybridization subsequently generates an embedding that contains statistical surface-level patterns and deep semantic understanding. The system uses principal component analysis (PCA) and a random forest classifier. The application of PCA converts a sparse, very high-dimensional embedding into a dense representation by keeping only the most relevant features. The model achieved robust performance across eight Indian languages, with the highest accuracy in Hindi. However, lower performance in Marathi highlights challenges in low-resource settings. Combining TF-IDF and BERT embeddings leads to better classification results, showing the benefits of integrating simple and complex language models. Limitations include potential feature redundancy and poor performance in languages with complex word forms, indicating a need for future adjustments to support multiple languages and address imbalances.
%U https://aclanthology.org/2025.ltedi-1.5/
%P 26-30
Markdown (Informal)
[SKVtrio@LT-EDI-2025: Hybrid TF-IDF and BERT Embeddings for Multilingual Homophobia and Transphobia Detection in Social Media Comments](https://aclanthology.org/2025.ltedi-1.5/) (Vignesh et al., LTEDI 2025)
ACL