Sentiment Analysis Using Pre-Trained Language Model With No Fine-Tuning and Less Resource
Sentiment analysis has become popular when Natural Language Processing algorithms were proven to be able to process complex sentences with good accuracy. Recently, pre-trained language models such as BERT and mBERT, have been shown to be effective for improving language tasks. Most of the work in im...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2022-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9912410/ |
_version_ | 1811182336549584896 |
---|---|
author | Yuheng Kit Musa Mohd Mokji |
author_facet | Yuheng Kit Musa Mohd Mokji |
author_sort | Yuheng Kit |
collection | DOAJ |
description | Sentiment analysis has become popular when Natural Language Processing algorithms were proven to be able to process complex sentences with good accuracy. Recently, pre-trained language models such as BERT and mBERT, have been shown to be effective for improving language tasks. Most of the work in implementing the models focuses on fine-tuning BERT to achieve desirable results. However, this approach is resource-intensive and requires a long training time, up to a few hours on a GPU, depending on the dataset. Hence, this paper proposes a less complex system with less training time using the BERT model without the fine-tuning process and adopting a feature reduction algorithm to reduce sentence embeddings. The experimental results show that with 50% fewer sentence embeddings, the proposed system improves the accuracy by 1-2% with 71% less training time and 89% less memory usage. The proposed approach has also been proven to work for multilingual tasks by using a single mBERT model. |
first_indexed | 2024-04-11T09:30:49Z |
format | Article |
id | doaj.art-07c91a3ad7d04f86b61512071538bcad |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-04-11T09:30:49Z |
publishDate | 2022-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-07c91a3ad7d04f86b61512071538bcad2022-12-22T04:31:53ZengIEEEIEEE Access2169-35362022-01-011010705610706510.1109/ACCESS.2022.32123679912410Sentiment Analysis Using Pre-Trained Language Model With No Fine-Tuning and Less ResourceYuheng Kit0https://orcid.org/0000-0002-3114-4408Musa Mohd Mokji1https://orcid.org/0000-0002-7590-8481Faculty of Engineering, School of Electrical Engineering, Universiti Teknologi Malaysia, Johor Bahru, MalaysiaFaculty of Engineering, School of Electrical Engineering, Universiti Teknologi Malaysia, Johor Bahru, MalaysiaSentiment analysis has become popular when Natural Language Processing algorithms were proven to be able to process complex sentences with good accuracy. Recently, pre-trained language models such as BERT and mBERT, have been shown to be effective for improving language tasks. Most of the work in implementing the models focuses on fine-tuning BERT to achieve desirable results. However, this approach is resource-intensive and requires a long training time, up to a few hours on a GPU, depending on the dataset. Hence, this paper proposes a less complex system with less training time using the BERT model without the fine-tuning process and adopting a feature reduction algorithm to reduce sentence embeddings. The experimental results show that with 50% fewer sentence embeddings, the proposed system improves the accuracy by 1-2% with 71% less training time and 89% less memory usage. The proposed approach has also been proven to work for multilingual tasks by using a single mBERT model.https://ieeexplore.ieee.org/document/9912410/Sentiment analysisnatural language processing |
spellingShingle | Yuheng Kit Musa Mohd Mokji Sentiment Analysis Using Pre-Trained Language Model With No Fine-Tuning and Less Resource IEEE Access Sentiment analysis natural language processing |
title | Sentiment Analysis Using Pre-Trained Language Model With No Fine-Tuning and Less Resource |
title_full | Sentiment Analysis Using Pre-Trained Language Model With No Fine-Tuning and Less Resource |
title_fullStr | Sentiment Analysis Using Pre-Trained Language Model With No Fine-Tuning and Less Resource |
title_full_unstemmed | Sentiment Analysis Using Pre-Trained Language Model With No Fine-Tuning and Less Resource |
title_short | Sentiment Analysis Using Pre-Trained Language Model With No Fine-Tuning and Less Resource |
title_sort | sentiment analysis using pre trained language model with no fine tuning and less resource |
topic | Sentiment analysis natural language processing |
url | https://ieeexplore.ieee.org/document/9912410/ |
work_keys_str_mv | AT yuhengkit sentimentanalysisusingpretrainedlanguagemodelwithnofinetuningandlessresource AT musamohdmokji sentimentanalysisusingpretrainedlanguagemodelwithnofinetuningandlessresource |