Data-Augmentation for Bangla-English Code-Mixed Sentiment Analysis: Enhancing Cross Linguistic Contextual Understanding
In today’s digital world, automated sentiment analysis from online reviews can contribute to a wide variety of decision-making processes. One example is examining typical perceptions of a product based on customer feedbacks to have a better understanding of consumer expectations, which ca...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2023-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10129187/ |
_version_ | 1797812850255724544 |
---|---|
author | Mohammad Tareq Md. Fokhrul Islam Swakshar Deb Sejuti Rahman Abdullah Al Mahmud |
author_facet | Mohammad Tareq Md. Fokhrul Islam Swakshar Deb Sejuti Rahman Abdullah Al Mahmud |
author_sort | Mohammad Tareq |
collection | DOAJ |
description | In today’s digital world, automated sentiment analysis from online reviews can contribute to a wide variety of decision-making processes. One example is examining typical perceptions of a product based on customer feedbacks to have a better understanding of consumer expectations, which can help enhance everything from customer service to product offerings. Online review comments, on the other hand, frequently mix different languages, use non-native scripts and do not adhere to strict grammar norms. For a low-resource language like Bangla, the lack of annotated code-mixed data makes automated sentiment analysis more challenging. To address this, we collect online reviews of different products and construct an annotated Bangla-English code mix (BE-CM) dataset (Dataset and other resources are available at <uri>https://github.com/fokhruli/CM-seti-anlysis</uri>). On our sentiment corpus, we also compare several alternative models from the existing literature. We present a simple but effective data augmentation method that can be utilized with existing word embedding algorithms without the need for a parallel corpus to improve cross-lingual contextual understanding. Our experimental results suggest that training word embedding models (e.g., Word2vec, FastText) with our data augmentation strategy can help the model in capturing the cross-lingual relationship for code-mixed sentences, thereby improving the overall performance of existing classifiers in both supervised learning and zero-shot cross-lingual adaptability. With extensive experimentations, we found that XGBoost with Fasttext embedding trained on our proposed data augmentation method outperforms other alternative models in automated sentiment analysis on code-mixed Bangla-English dataset, with a weighted F1 score of 87%. |
first_indexed | 2024-03-13T07:44:31Z |
format | Article |
id | doaj.art-193822f7daa74fb7b09d51aeabf0d872 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-03-13T07:44:31Z |
publishDate | 2023-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-193822f7daa74fb7b09d51aeabf0d8722023-06-02T23:00:32ZengIEEEIEEE Access2169-35362023-01-0111516575167110.1109/ACCESS.2023.327778710129187Data-Augmentation for Bangla-English Code-Mixed Sentiment Analysis: Enhancing Cross Linguistic Contextual UnderstandingMohammad Tareq0Md. Fokhrul Islam1https://orcid.org/0000-0002-0031-4937Swakshar Deb2Sejuti Rahman3https://orcid.org/0000-0001-6226-2434Abdullah Al Mahmud4https://orcid.org/0000-0003-1140-4505Department of Accounting and Information Systems, University of Dhaka, Dhaka, BangladeshDepartment of Robotics and Mechatronics Engineering, University of Dhaka, Dhaka, BangladeshDepartment of Robotics and Mechatronics Engineering, University of Dhaka, Dhaka, BangladeshDepartment of Robotics and Mechatronics Engineering, University of Dhaka, Dhaka, BangladeshDepartment of Banking and Insurance, University of Dhaka, Dhaka, BangladeshIn today’s digital world, automated sentiment analysis from online reviews can contribute to a wide variety of decision-making processes. One example is examining typical perceptions of a product based on customer feedbacks to have a better understanding of consumer expectations, which can help enhance everything from customer service to product offerings. Online review comments, on the other hand, frequently mix different languages, use non-native scripts and do not adhere to strict grammar norms. For a low-resource language like Bangla, the lack of annotated code-mixed data makes automated sentiment analysis more challenging. To address this, we collect online reviews of different products and construct an annotated Bangla-English code mix (BE-CM) dataset (Dataset and other resources are available at <uri>https://github.com/fokhruli/CM-seti-anlysis</uri>). On our sentiment corpus, we also compare several alternative models from the existing literature. We present a simple but effective data augmentation method that can be utilized with existing word embedding algorithms without the need for a parallel corpus to improve cross-lingual contextual understanding. Our experimental results suggest that training word embedding models (e.g., Word2vec, FastText) with our data augmentation strategy can help the model in capturing the cross-lingual relationship for code-mixed sentences, thereby improving the overall performance of existing classifiers in both supervised learning and zero-shot cross-lingual adaptability. With extensive experimentations, we found that XGBoost with Fasttext embedding trained on our proposed data augmentation method outperforms other alternative models in automated sentiment analysis on code-mixed Bangla-English dataset, with a weighted F1 score of 87%.https://ieeexplore.ieee.org/document/10129187/Code mixedsentiment analysisBangla-English corpusbi-lingualzero-shot learning |
spellingShingle | Mohammad Tareq Md. Fokhrul Islam Swakshar Deb Sejuti Rahman Abdullah Al Mahmud Data-Augmentation for Bangla-English Code-Mixed Sentiment Analysis: Enhancing Cross Linguistic Contextual Understanding IEEE Access Code mixed sentiment analysis Bangla-English corpus bi-lingual zero-shot learning |
title | Data-Augmentation for Bangla-English Code-Mixed Sentiment Analysis: Enhancing Cross Linguistic Contextual Understanding |
title_full | Data-Augmentation for Bangla-English Code-Mixed Sentiment Analysis: Enhancing Cross Linguistic Contextual Understanding |
title_fullStr | Data-Augmentation for Bangla-English Code-Mixed Sentiment Analysis: Enhancing Cross Linguistic Contextual Understanding |
title_full_unstemmed | Data-Augmentation for Bangla-English Code-Mixed Sentiment Analysis: Enhancing Cross Linguistic Contextual Understanding |
title_short | Data-Augmentation for Bangla-English Code-Mixed Sentiment Analysis: Enhancing Cross Linguistic Contextual Understanding |
title_sort | data augmentation for bangla english code mixed sentiment analysis enhancing cross linguistic contextual understanding |
topic | Code mixed sentiment analysis Bangla-English corpus bi-lingual zero-shot learning |
url | https://ieeexplore.ieee.org/document/10129187/ |
work_keys_str_mv | AT mohammadtareq dataaugmentationforbanglaenglishcodemixedsentimentanalysisenhancingcrosslinguisticcontextualunderstanding AT mdfokhrulislam dataaugmentationforbanglaenglishcodemixedsentimentanalysisenhancingcrosslinguisticcontextualunderstanding AT swakshardeb dataaugmentationforbanglaenglishcodemixedsentimentanalysisenhancingcrosslinguisticcontextualunderstanding AT sejutirahman dataaugmentationforbanglaenglishcodemixedsentimentanalysisenhancingcrosslinguisticcontextualunderstanding AT abdullahalmahmud dataaugmentationforbanglaenglishcodemixedsentimentanalysisenhancingcrosslinguisticcontextualunderstanding |