@inproceedings{naeen-etal-2025-polyhope,
title = "{P}oly{H}ope-{M} at {RANLP}2025 Subtask-1 Binary Hope Speech Detection: {S}panish Language Classification Approach with Comprehensive Learning Using Transformer, and Traditional {ML}, and {DL}",
author = "Naeen, Md. Julkar and
Das, Sourav Kumar and
Khushbu, Sharun Akter and
Ramit, Shahriar Sultan and
Alo, Alaya Parven",
editor = "Angelova, Galia and
Kunilovskaya, Maria and
Escribe, Marie and
Mitkov, Ruslan",
booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.ranlp-1.90/",
pages = "780--786",
abstract = "This paper presents our system for the RANLP 2025 shared task on multilingual binary sentiment classification for Task-2 Spanish datasets for domains including social media and customer reviews. We experimented with various models from traditional machine learning approaches{---}Naive Bayes and LightGBM{---}to deep learning architectures like LSTM. Among them, the transformer-based XLM-RoBERTa model performed best with an F1 of 0.85, demonstrating its promise for multilingual sentiment work. Basic text preprocessing techniques were used for data quality assurance and improving model performance. Our comparison reflects the superiority of transformer-based models over the traditional methods in binary sentiment classification for multilingual and low-resource environments. This study enables the development of cross-lingual sentiment classification by establishing strong baselines and paying close attention to model performance in joint task settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="naeen-etal-2025-polyhope">
<titleInfo>
<title>PolyHope-M at RANLP2025 Subtask-1 Binary Hope Speech Detection: Spanish Language Classification Approach with Comprehensive Learning Using Transformer, and Traditional ML, and DL</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Julkar</namePart>
<namePart type="family">Naeen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sourav</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharun</namePart>
<namePart type="given">Akter</namePart>
<namePart type="family">Khushbu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shahriar</namePart>
<namePart type="given">Sultan</namePart>
<namePart type="family">Ramit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alaya</namePart>
<namePart type="given">Parven</namePart>
<namePart type="family">Alo</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 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
</titleInfo>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kunilovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Escribe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</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>This paper presents our system for the RANLP 2025 shared task on multilingual binary sentiment classification for Task-2 Spanish datasets for domains including social media and customer reviews. We experimented with various models from traditional machine learning approaches—Naive Bayes and LightGBM—to deep learning architectures like LSTM. Among them, the transformer-based XLM-RoBERTa model performed best with an F1 of 0.85, demonstrating its promise for multilingual sentiment work. Basic text preprocessing techniques were used for data quality assurance and improving model performance. Our comparison reflects the superiority of transformer-based models over the traditional methods in binary sentiment classification for multilingual and low-resource environments. This study enables the development of cross-lingual sentiment classification by establishing strong baselines and paying close attention to model performance in joint task settings.</abstract>
<identifier type="citekey">naeen-etal-2025-polyhope</identifier>
<location>
<url>https://aclanthology.org/2025.ranlp-1.90/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>780</start>
<end>786</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PolyHope-M at RANLP2025 Subtask-1 Binary Hope Speech Detection: Spanish Language Classification Approach with Comprehensive Learning Using Transformer, and Traditional ML, and DL
%A Naeen, Md. Julkar
%A Das, Sourav Kumar
%A Khushbu, Sharun Akter
%A Ramit, Shahriar Sultan
%A Alo, Alaya Parven
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F naeen-etal-2025-polyhope
%X This paper presents our system for the RANLP 2025 shared task on multilingual binary sentiment classification for Task-2 Spanish datasets for domains including social media and customer reviews. We experimented with various models from traditional machine learning approaches—Naive Bayes and LightGBM—to deep learning architectures like LSTM. Among them, the transformer-based XLM-RoBERTa model performed best with an F1 of 0.85, demonstrating its promise for multilingual sentiment work. Basic text preprocessing techniques were used for data quality assurance and improving model performance. Our comparison reflects the superiority of transformer-based models over the traditional methods in binary sentiment classification for multilingual and low-resource environments. This study enables the development of cross-lingual sentiment classification by establishing strong baselines and paying close attention to model performance in joint task settings.
%U https://aclanthology.org/2025.ranlp-1.90/
%P 780-786
Markdown (Informal)
[PolyHope-M at RANLP2025 Subtask-1 Binary Hope Speech Detection: Spanish Language Classification Approach with Comprehensive Learning Using Transformer, and Traditional ML, and DL](https://aclanthology.org/2025.ranlp-1.90/) (Naeen et al., RANLP 2025)
ACL
- Md. Julkar Naeen, Sourav Kumar Das, Sharun Akter Khushbu, Shahriar Sultan Ramit, and Alaya Parven Alo. 2025. PolyHope-M at RANLP2025 Subtask-1 Binary Hope Speech Detection: Spanish Language Classification Approach with Comprehensive Learning Using Transformer, and Traditional ML, and DL. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 780–786, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.