@inproceedings{alam-etal-2025-bnsentmix,
title = "{B}n{S}ent{M}ix: A Diverse {B}engali-{E}nglish Code-Mixed Dataset for Sentiment Analysis",
author = "Alam, Sadia and
Ishmam, Md Farhan and
Alvee, Navid Hasin and
Siddique, Md Shahnewaz and
Hossain, Md Azam and
Kamal, Abu Raihan Mostofa",
editor = "Hettiarachchi, Hansi and
Ranasinghe, Tharindu and
Rayson, Paul and
Mitkov, Ruslan and
Gaber, Mohamed and
Premasiri, Damith and
Tan, Fiona Anting and
Uyangodage, Lasitha",
booktitle = "Proceedings of the First Workshop on Language Models for Low-Resource Languages",
month = jan,
year = "2025",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.loreslm-1.4/",
pages = "68--77",
abstract = "The widespread availability of code-mixed data in digital spaces can provide valuable insights into low-resource languages like Bengali, which have limited annotated corpora. Sentiment analysis, a pivotal text classification task, has been explored across multiple languages, yet code-mixed Bengali remains underrepresented with no large-scale, diverse benchmark. Code-mixed text is particularly challenging as it requires the understanding of multiple languages and their interaction in the same text. We address this limitation by introducing BnSentMix, a sentiment analysis dataset on code-mixed Bengali comprising 20,000 samples with 4 sentiment labels, sourced from Facebook, YouTube, and e-commerce sites. By aggregating multiple sources, we ensure linguistic diversity reflecting realistic code-mixed scenarios. We implement a novel automated text filtering pipeline using fine-tuned language models to detect code-mixed samples and expand code-mixed text corpora. We further propose baselines using machine learning, neural networks, and transformer-based language models. The availability of a diverse dataset is a critical step towards democratizing NLP and ultimately contributing to a better understanding of code-mixed languages."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alam-etal-2025-bnsentmix">
<titleInfo>
<title>BnSentMix: A Diverse Bengali-English Code-Mixed Dataset for Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sadia</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Farhan</namePart>
<namePart type="family">Ishmam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Navid</namePart>
<namePart type="given">Hasin</namePart>
<namePart type="family">Alvee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Shahnewaz</namePart>
<namePart type="family">Siddique</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Azam</namePart>
<namePart type="family">Hossain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abu</namePart>
<namePart type="given">Raihan</namePart>
<namePart type="given">Mostofa</namePart>
<namePart type="family">Kamal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Language Models for Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hansi</namePart>
<namePart type="family">Hettiarachchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</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>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Gaber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damith</namePart>
<namePart type="family">Premasiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fiona</namePart>
<namePart type="given">Anting</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lasitha</namePart>
<namePart type="family">Uyangodage</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The widespread availability of code-mixed data in digital spaces can provide valuable insights into low-resource languages like Bengali, which have limited annotated corpora. Sentiment analysis, a pivotal text classification task, has been explored across multiple languages, yet code-mixed Bengali remains underrepresented with no large-scale, diverse benchmark. Code-mixed text is particularly challenging as it requires the understanding of multiple languages and their interaction in the same text. We address this limitation by introducing BnSentMix, a sentiment analysis dataset on code-mixed Bengali comprising 20,000 samples with 4 sentiment labels, sourced from Facebook, YouTube, and e-commerce sites. By aggregating multiple sources, we ensure linguistic diversity reflecting realistic code-mixed scenarios. We implement a novel automated text filtering pipeline using fine-tuned language models to detect code-mixed samples and expand code-mixed text corpora. We further propose baselines using machine learning, neural networks, and transformer-based language models. The availability of a diverse dataset is a critical step towards democratizing NLP and ultimately contributing to a better understanding of code-mixed languages.</abstract>
<identifier type="citekey">alam-etal-2025-bnsentmix</identifier>
<location>
<url>https://aclanthology.org/2025.loreslm-1.4/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>68</start>
<end>77</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BnSentMix: A Diverse Bengali-English Code-Mixed Dataset for Sentiment Analysis
%A Alam, Sadia
%A Ishmam, Md Farhan
%A Alvee, Navid Hasin
%A Siddique, Md Shahnewaz
%A Hossain, Md Azam
%A Kamal, Abu Raihan Mostofa
%Y Hettiarachchi, Hansi
%Y Ranasinghe, Tharindu
%Y Rayson, Paul
%Y Mitkov, Ruslan
%Y Gaber, Mohamed
%Y Premasiri, Damith
%Y Tan, Fiona Anting
%Y Uyangodage, Lasitha
%S Proceedings of the First Workshop on Language Models for Low-Resource Languages
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F alam-etal-2025-bnsentmix
%X The widespread availability of code-mixed data in digital spaces can provide valuable insights into low-resource languages like Bengali, which have limited annotated corpora. Sentiment analysis, a pivotal text classification task, has been explored across multiple languages, yet code-mixed Bengali remains underrepresented with no large-scale, diverse benchmark. Code-mixed text is particularly challenging as it requires the understanding of multiple languages and their interaction in the same text. We address this limitation by introducing BnSentMix, a sentiment analysis dataset on code-mixed Bengali comprising 20,000 samples with 4 sentiment labels, sourced from Facebook, YouTube, and e-commerce sites. By aggregating multiple sources, we ensure linguistic diversity reflecting realistic code-mixed scenarios. We implement a novel automated text filtering pipeline using fine-tuned language models to detect code-mixed samples and expand code-mixed text corpora. We further propose baselines using machine learning, neural networks, and transformer-based language models. The availability of a diverse dataset is a critical step towards democratizing NLP and ultimately contributing to a better understanding of code-mixed languages.
%U https://aclanthology.org/2025.loreslm-1.4/
%P 68-77
Markdown (Informal)
[BnSentMix: A Diverse Bengali-English Code-Mixed Dataset for Sentiment Analysis](https://aclanthology.org/2025.loreslm-1.4/) (Alam et al., LoResLM 2025)
ACL