BdSentiLLM: A Novel LLM Approach to Sentiment Analysis of Product Reviews

Online communication has led to more people expressing themselves in their preferred languages, especially in e-commerce, where product reviews are crucial. Understanding customer sentiment through product reviews and comments can help businesses improve product quality and make informed decisions....

Full description

Saved in:
Bibliographic Details
Main Authors: Atia Shahnaz Ipa, Priyo Nath Roy, Mohammad Abu Tareq Rony, Ali Raza, Norma Latif Fitriyani, Yeonghyeon Gu, Muhammad Syafrudin
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10798428/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850123019619401728
author Atia Shahnaz Ipa
Priyo Nath Roy
Mohammad Abu Tareq Rony
Ali Raza
Norma Latif Fitriyani
Yeonghyeon Gu
Muhammad Syafrudin
author_facet Atia Shahnaz Ipa
Priyo Nath Roy
Mohammad Abu Tareq Rony
Ali Raza
Norma Latif Fitriyani
Yeonghyeon Gu
Muhammad Syafrudin
author_sort Atia Shahnaz Ipa
collection DOAJ
description Online communication has led to more people expressing themselves in their preferred languages, especially in e-commerce, where product reviews are crucial. Understanding customer sentiment through product reviews and comments can help businesses improve product quality and make informed decisions. However, the complexity of written language and the variety of languages used in reviews pose challenges for accurate sentiment analysis. In this study, we explored the linguistic landscape of Bangladeshi product reviews and developed BdSentiLLM, a robust model designed for automatic language classification and sentiment analysis in this context. We collected a dataset of 3,864 product reviews, revealing that 84% were written in English, followed by Bangla, Banglish (Romanized Bangla), and Bangla-English code-switched content. BdSentiLLM can categorize and prepare these language types for sentiment analysis with large language models. We evaluated the performance of four open-source LLMs, Llama-2, Flan-t5, Vicuna, and Falcon, using BdSentiLLM for sentiment analysis.BdSentiLLM with Llama-2 consistently outperformed the other models across most language categories with f1 score of 0.79 for Bangla, 0.70 for Banglish, 0.84 for Bangla_English, 0.90 for English, and 0.89 overall, while Flan-t5 excelled in English sentiment analysis. Compared to existing models, BdSentiLLM demonstrated superior versatility and effectiveness by handling mixed-language data across all categories making it a valuable tool for sentiment analysis in diverse linguistic contexts. Future work will focus on expanding the dataset to enhance BdSentiLLM’s robustness and exploring its applicability beyond e-commerce to broader multilingual sentiment analysis tasks.
format Article
id doaj-art-40a2323b372e4db895caf6d3a3f5c440
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-40a2323b372e4db895caf6d3a3f5c4402025-08-20T02:34:42ZengIEEEIEEE Access2169-35362024-01-011218933018934310.1109/ACCESS.2024.351682610798428BdSentiLLM: A Novel LLM Approach to Sentiment Analysis of Product ReviewsAtia Shahnaz Ipa0https://orcid.org/0009-0006-7308-899XPriyo Nath Roy1Mohammad Abu Tareq Rony2https://orcid.org/0000-0002-0640-1425Ali Raza3https://orcid.org/0000-0001-5429-9835Norma Latif Fitriyani4https://orcid.org/0000-0002-1133-3965Yeonghyeon Gu5https://orcid.org/0000-0002-0002-9386Muhammad Syafrudin6https://orcid.org/0000-0002-5640-4413Department of Mechatronics Engineering, Khulna University of Engineering & Technology, Khulna, BangladeshDepartment of Mechatronics Engineering, Khulna University of Engineering & Technology, Khulna, BangladeshDepartment of Statistics, Noakhali Science & Technology University, Noakhali, BangladeshDepartment of Software Engineering, University of Lahore, Lahore, PakistanDepartment of Artificial Intelligence and Data Science, Sejong University, Seoul, Republic of KoreaDepartment of Artificial Intelligence and Data Science, Sejong University, Seoul, Republic of KoreaDepartment of Artificial Intelligence and Data Science, Sejong University, Seoul, Republic of KoreaOnline communication has led to more people expressing themselves in their preferred languages, especially in e-commerce, where product reviews are crucial. Understanding customer sentiment through product reviews and comments can help businesses improve product quality and make informed decisions. However, the complexity of written language and the variety of languages used in reviews pose challenges for accurate sentiment analysis. In this study, we explored the linguistic landscape of Bangladeshi product reviews and developed BdSentiLLM, a robust model designed for automatic language classification and sentiment analysis in this context. We collected a dataset of 3,864 product reviews, revealing that 84% were written in English, followed by Bangla, Banglish (Romanized Bangla), and Bangla-English code-switched content. BdSentiLLM can categorize and prepare these language types for sentiment analysis with large language models. We evaluated the performance of four open-source LLMs, Llama-2, Flan-t5, Vicuna, and Falcon, using BdSentiLLM for sentiment analysis.BdSentiLLM with Llama-2 consistently outperformed the other models across most language categories with f1 score of 0.79 for Bangla, 0.70 for Banglish, 0.84 for Bangla_English, 0.90 for English, and 0.89 overall, while Flan-t5 excelled in English sentiment analysis. Compared to existing models, BdSentiLLM demonstrated superior versatility and effectiveness by handling mixed-language data across all categories making it a valuable tool for sentiment analysis in diverse linguistic contexts. Future work will focus on expanding the dataset to enhance BdSentiLLM’s robustness and exploring its applicability beyond e-commerce to broader multilingual sentiment analysis tasks.https://ieeexplore.ieee.org/document/10798428/Sentiment analysisproductBangladeshi reviewslarge language modelnatural language processing
spellingShingle Atia Shahnaz Ipa
Priyo Nath Roy
Mohammad Abu Tareq Rony
Ali Raza
Norma Latif Fitriyani
Yeonghyeon Gu
Muhammad Syafrudin
BdSentiLLM: A Novel LLM Approach to Sentiment Analysis of Product Reviews
IEEE Access
Sentiment analysis
product
Bangladeshi reviews
large language model
natural language processing
title BdSentiLLM: A Novel LLM Approach to Sentiment Analysis of Product Reviews
title_full BdSentiLLM: A Novel LLM Approach to Sentiment Analysis of Product Reviews
title_fullStr BdSentiLLM: A Novel LLM Approach to Sentiment Analysis of Product Reviews
title_full_unstemmed BdSentiLLM: A Novel LLM Approach to Sentiment Analysis of Product Reviews
title_short BdSentiLLM: A Novel LLM Approach to Sentiment Analysis of Product Reviews
title_sort bdsentillm a novel llm approach to sentiment analysis of product reviews
topic Sentiment analysis
product
Bangladeshi reviews
large language model
natural language processing
url https://ieeexplore.ieee.org/document/10798428/
work_keys_str_mv AT atiashahnazipa bdsentillmanovelllmapproachtosentimentanalysisofproductreviews
AT priyonathroy bdsentillmanovelllmapproachtosentimentanalysisofproductreviews
AT mohammadabutareqrony bdsentillmanovelllmapproachtosentimentanalysisofproductreviews
AT aliraza bdsentillmanovelllmapproachtosentimentanalysisofproductreviews
AT normalatiffitriyani bdsentillmanovelllmapproachtosentimentanalysisofproductreviews
AT yeonghyeongu bdsentillmanovelllmapproachtosentimentanalysisofproductreviews
AT muhammadsyafrudin bdsentillmanovelllmapproachtosentimentanalysisofproductreviews