Transfer Learning-Based Framework for Sentiment Classification of Cosmetics Products Reviews
The exponential growth in online reviews and recommendations availability drives sentiment classification, an interesting topic in industrial research. There is a vital requirement for organizations to explore client behaviour to assess the competitive business environment. This study aspires to ex...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
The University of Lahore
2022-10-01
|
Series: | Pakistan Journal of Engineering & Technology |
Subjects: | |
Online Access: | https://sites2.uol.edu.pk/journals/pakjet/article/view/2133 |
_version_ | 1811198741695168512 |
---|---|
author | Ashra Sahar Muhammad Ayoub Shabir Hussain Yang Yu Akmal Khan |
author_facet | Ashra Sahar Muhammad Ayoub Shabir Hussain Yang Yu Akmal Khan |
author_sort | Ashra Sahar |
collection | DOAJ |
description |
The exponential growth in online reviews and recommendations availability drives sentiment classification, an interesting topic in industrial research. There is a vital requirement for organizations to explore client behaviour to assess the competitive business environment. This study aspires to examine and predict customer reviews using Transfer learning (TL) approaches. Reviews can span so many domains that it is challenging to gather annotated training data for all of them. Hence, this paper proposed an annotation algorithm to label a large unlabeled dataset. These reviews must be pulled and examined to predict the sentiment polarity, whether the review is positive, neutral, or negative. We propose a deep learning-based approach that learns to extract a meaningful representation for each review in an unsupervised fashion. Sentiment classifiers trained with this high-level feature representation outperform state-of-the-art methods on a benchmark of reviews of cosmetics brands on Amazon or other platforms. Using the BERT for sentiment analysis, we achieved the highest accuracy of 93.21% compared to previous studies.
|
first_indexed | 2024-04-12T01:36:23Z |
format | Article |
id | doaj.art-965135614c4d46da892bd2b507a59f77 |
institution | Directory Open Access Journal |
issn | 2664-2042 2664-2050 |
language | English |
last_indexed | 2024-04-12T01:36:23Z |
publishDate | 2022-10-01 |
publisher | The University of Lahore |
record_format | Article |
series | Pakistan Journal of Engineering & Technology |
spelling | doaj.art-965135614c4d46da892bd2b507a59f772022-12-22T03:53:19ZengThe University of LahorePakistan Journal of Engineering & Technology2664-20422664-20502022-10-015310.51846/vol5iss3pp38-43Transfer Learning-Based Framework for Sentiment Classification of Cosmetics Products ReviewsAshra Sahar0Muhammad Ayoub1Shabir Hussain2Yang Yu3Akmal Khan4Department of Computer Science, National College of Business Administration and Economics, Rahim Yar khan, 64200, PakistanSchool of Computer Science and Engineering, Central South University, ChinaSchool of Information Engineering, Zhengzhou University, Zhengzhou, ChinaDistributed Systems Group, University of Duisburg-Essen, Duisburg, GermanyDepartment of Data Science, the Islamia University of Bahawalpur, Bahawalpur, Pakistan The exponential growth in online reviews and recommendations availability drives sentiment classification, an interesting topic in industrial research. There is a vital requirement for organizations to explore client behaviour to assess the competitive business environment. This study aspires to examine and predict customer reviews using Transfer learning (TL) approaches. Reviews can span so many domains that it is challenging to gather annotated training data for all of them. Hence, this paper proposed an annotation algorithm to label a large unlabeled dataset. These reviews must be pulled and examined to predict the sentiment polarity, whether the review is positive, neutral, or negative. We propose a deep learning-based approach that learns to extract a meaningful representation for each review in an unsupervised fashion. Sentiment classifiers trained with this high-level feature representation outperform state-of-the-art methods on a benchmark of reviews of cosmetics brands on Amazon or other platforms. Using the BERT for sentiment analysis, we achieved the highest accuracy of 93.21% compared to previous studies. https://sites2.uol.edu.pk/journals/pakjet/article/view/2133Text miningSentiment analysisCosmetic purchase behaviour |
spellingShingle | Ashra Sahar Muhammad Ayoub Shabir Hussain Yang Yu Akmal Khan Transfer Learning-Based Framework for Sentiment Classification of Cosmetics Products Reviews Pakistan Journal of Engineering & Technology Text mining Sentiment analysis Cosmetic purchase behaviour |
title | Transfer Learning-Based Framework for Sentiment Classification of Cosmetics Products Reviews |
title_full | Transfer Learning-Based Framework for Sentiment Classification of Cosmetics Products Reviews |
title_fullStr | Transfer Learning-Based Framework for Sentiment Classification of Cosmetics Products Reviews |
title_full_unstemmed | Transfer Learning-Based Framework for Sentiment Classification of Cosmetics Products Reviews |
title_short | Transfer Learning-Based Framework for Sentiment Classification of Cosmetics Products Reviews |
title_sort | transfer learning based framework for sentiment classification of cosmetics products reviews |
topic | Text mining Sentiment analysis Cosmetic purchase behaviour |
url | https://sites2.uol.edu.pk/journals/pakjet/article/view/2133 |
work_keys_str_mv | AT ashrasahar transferlearningbasedframeworkforsentimentclassificationofcosmeticsproductsreviews AT muhammadayoub transferlearningbasedframeworkforsentimentclassificationofcosmeticsproductsreviews AT shabirhussain transferlearningbasedframeworkforsentimentclassificationofcosmeticsproductsreviews AT yangyu transferlearningbasedframeworkforsentimentclassificationofcosmeticsproductsreviews AT akmalkhan transferlearningbasedframeworkforsentimentclassificationofcosmeticsproductsreviews |