OpExBERT: Opinion EXTRACTION and Classification of Reviews using BERT Model
OpExBERT: Opinion EXTRACTION and Classification of Reviews using BERT Model |
||
 |
 |
|
| © 2023 by IJETT Journal | ||
| Volume-71 Issue-11 |
||
| Year of Publication : 2023 | ||
| Author : Ankur Ratmele, Ramesh Thakur, Archana Thakur |
||
| DOI : 10.14445/22315381/IJETT-V71I11P222 | ||
How to Cite?
Ankur Ratmele, Ramesh Thakur, Archana Thakur, "OpExBERT: Opinion EXTRACTION and Classification of Reviews using BERT Model," International Journal of Engineering Trends and Technology, vol. 71, no. 11, pp. 208-217, 2023. Crossref, https://doi.org/10.14445/22315381/IJETT-V71I11P222
Abstract
Sellers and merchants have started asking customers to comment on the products at online marketplaces in recent years. It might be really difficult for a potential buyer to decide whether to buy a product after analyzing the vast amounts of evaluations. This research introduces a solution for tackling this problem, employing a hierarchical attention network approach. In this proposed framework, the initial step involves preprocessing the Amazon Smartphone Review dataset using natural language processing techniques. Subsequently, the BERT (Bidirectional Encoder Representations from Transformers) model is applied to make word vector illustrations of the reviews, capturing their contextual meaning. Developed by Google AI Language, BERT is a deep learning model explicitly designed to pre-train text in an unsupervised manner by considering context from both the left and right directions across all its layers. This is in contrast to previous language representation models that were unidirectional. The pre-trained BERT model can be fine-tuned with just one output layer for different tasks related to language understanding, such as opinion mining and question answering. This allows efficient adaptation to specific tasks without modifying the model's underlying architecture. Studies show that the suggested framework works better in expressions of accuracy, precision, and recall than the standard methods. Worthy results were attained by the OpExBERT model, including 98.55% accuracy, 91.67% precision, 91.25% recall, and 91.14% f-score.
Keywords
BERT model, Opinion Extraction (OE), Natural Language Processing (NLP), Machine learning.
References
[1] A. Palaniammal, and P. Anandababu, “Robust Sarcasm Detection Using Artificial Rabbits Optimizer with Multilayer Convolutional Encoder-Decoder Neural Network on Social Media,” SSRG International Journal of Electronics and Communication Engineering, vol. 10, no. 5, pp. 1-13, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Jinzhan Feng, Shuqin Cai, and Xiaomeng Ma, “Enhanced Sentiment Labeling and Implicit Aspect Identifcation by Integration of Deep Convolution Neural Network and Sequential Algorithm,” Cluster Computing, vol. 22, pp. 5839-5857, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Himanshu Thakur, and Aman Kumar Sharma, “Supervised Machine Learning Classifiers: Computation of Best Result of Classification Accuracy,” International Journal of Computer Trends and Technology, vol. 68, no. 10, pp. 1-8, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Wanliang Tan, Xinyu Wang, and Xinyu Xu, “Sentiment Analysis for Amazon Reviews,” International Conference, pp. 1-5, 2019.
[Google Scholar] [Publisher Link]
[5] Anh-Dung Vo, Quang-Phuoc Nguyen, and Cheol-Young Ock, “Opinion-Aspect Relations in Cognizing Customer Feelings via Reviews,” IEEE Access, vol. 6, pp. 5415-5426, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Yequan Wang et al., “Attention-Based LSTM for Aspect-Level Sentiment Classifcation, Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 606-615, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Rui Wang et al., “A Survey on Opinion Mining: from Stance to Product Aspect,” IEEE Access, vol. 7, pp. 41101-41124, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Jiyao Wei et al., “BiLSTM with Multipolarity Orthogonal Attention for Implicit Sentiment Analysis,” Neurocomputing, vol. 383, pp. 165- 173, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Chuhan Wu et al., “A Hybrid Unsupervised Method for Aspect Term and Opinion Target Extraction,” Knowledge-Based Systems, vol. 148, pp. 66-73, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Zichao Yang et al., “Hierarchical Attention Networks for Document Classification,” Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1480-1489, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Shanshan Yi, and Xiaofang Liu, “Machine Learning Based Customer Sentiment Analysis for Recommending Shoppers, Shops Based On Customers’ Review,” Complex and Intelligent Systems, vol. 6, pp. 621-634, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Min Zhang et al., “Mining Product Innovation Ideas from Online Reviews,” Information Processing and Management, vol. 58, no. 1, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Petr Hajek, Aliaksandr Barushka, and Michal Munk, “Opinion Mining of Consumer Reviews Using Deep Neural Networks with WordSentiment Associations,” IFIP International Conference on Artificial Intelligence Applications and Innovations, pp. 419-429, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Tanjim Ul Haque, Nudrat Nawal Saber, and Faisal Muhammad Shah, “Sentiment Analysis on Large Scale Amazon Product Reviews,” 2018 IEEE International Conference on Innovative Research and Development (ICIRD), pp. 1-6, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Ankur Ratmele, and Ramesh, “Thakur OpExHAN: Opinion Extraction Using Hierarchical Attention Network from Unstructured Reviews,” Social Network Analysis and Mining, vol. 12, no. 148, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Doaa Mohey El-Din Mohamed Hussein, “A Survey on Sentiment Analysis Challenges,” Journal of King Saud University - Engineering Sciences, vol. 30, no. 4, pp. 330-338, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Ruixin Ma et al., “Featurebased Compositing Memory Networks for Aspect-Based Sentiment Classification in Social Internet of Things,” Future Generation Computer Systems, vol. 92, pp. 879-888, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Yi Tay, Luu Anh Tuan, and Siu Cheung Hui, “Learning to Attend via Word-Aspect Associative Fusion for Aspect-Based Sentiment Analysis,” Proceedings of the AAAI Conference on Artifcial Intelligence, vol. 32, no. 1, pp. 1-8, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Peter D. Turney, “Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classifcation of Reviews,” arXiv, pp. 1- 8, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Prajwal Madhusudhana Reddy, “Conducting Sentiment Analysis on Twitter Tweets to Predict the Outcomes of the Upcoming Karnataka State Elections,” SSRG International Journal of Computer Science and Engineering , vol. 10, no. 6, pp. 22-35, 2023.
[CrossRef] [Publisher Link]
[21] Zhao Jianqiang, Gui Xiaolin, and Zhang Xuejun, “Deep Convolution Neural Networks for Twitter Sentiment Analysis,” IEEE Access, vol. 6, pp. 23253-23260, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Z. Jianqiang, and G. Xiaolin, “Comparison Research on Text Preprocessing Methods on Twitter Sentiment Analysis,” IEEE Access, vol. 5, pp. 2870-2879, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Spyridon Kardakis et al., “Examining Attention Mechanisms in Deep Learning Models for Sentiment Analysis,” Applied Sciences, vol. 11, no. 9, pp. 1-14, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Khaled Abdalgader, and Aysha Al Shibli, “Experimental Results on Customer Reviews Using Lexicon-Based Word Polarity Identifcation Method,” IEEE Access, vol. 8, pp. 179955-179969, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Madiha Khalid et al., “GBSVM: Sentiment Classification from Unstructured Reviews Using Ensemble Classifier,” Applied Sciences, vol. 10, no. 8, pp. 1-20, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Erick Kauffmann et al., “Managing Marketing Decision-Making with Sentiment Analysis: An Evaluation of the Main Product Features Using Text Data Mining,” Sustainability, vol. 11, no. 15, pp. 1-19, 2019.
[CrossRef] [Google Scholar] [Publisher Link]