No Access

Aspect-Based Sentiment Analysis Using Fabricius Ringlet-Based Hybrid Deep Learning for Online Reviews

Department of Computer Science and Engineering, M. S. Ramaiah University of Applied Sciences, Bangalore 560058, Karnataka, India

E-mail Address: santoshik29@gmail.com

Corresponding author.

Search for more papers by this author

and

T. P. Pushphavathi

Department of Computer Science and Engineering, M. S. Ramaiah University of Applied Sciences, Bangalore 560058, Karnataka, India

E-mail Address: acepushpa@gmail.com

Search for more papers by this author

https://doi.org/10.1142/S0219467825500056Cited by:0 (Source: Crossref)

Abstract

The sentiment analysis relying on the aspect of online reviews is utilized for identifying the polarity of the given review. Nowadays, many methods are introduced for aspect-based sentiment analysis (ABSA) using neural networks, and many methods failed to consider contextual information exploitation to make the performance more accurate. Hence, this research proposed an optimized deep learning method for the detection of the aspect and to identify the polarity. Hence, in this research, an optimized deep learning technique for the ABSA is introduced by considering the online reviews, in which the deep learning classifiers are trained with the proposed Fabricius ringlet optimization (FRO) algorithm to reduce the loss that helps to enhance the accuracy of sentiment polarity prediction. The proposed FRO is developed by the hybridization of the behavioral nature of the Fabricius and the ringlet in feeding for the determination of the global best solution. The tuning of the weights and biases of the classifier enhance the performance of the classifier. The objective behind the tuning is to minimize the loss function while training and to enhance the accuracy of aspect extraction and polarity prediction of sentiment. Based on a study of the existing approach, the suggested FRO-based hybrid deep learning method is significantly improved; its accuracy, sensitivity, and specificity are 87.06%, 90.83%, and 79.37%, respectively, with a training percentage of 40%. The accuracy, sensitivity, and specificity of the existing technique have also been enhanced for aspect restaurant values, which are 87.53%, 96.06%, and 79.88% with a 60% training percentage. Similar to that, Twitter values for accuracy, sensitivity, and specificity are reported to be 89.08%, 99.35%, and 79.70%, respectively, with an 80% training percentage. The proposed method obtained the 90.13%, 99.35%, and 81.10% accuracy, sensitivity, and specificity from the assessment of the FRO-based hybrid deep learning.

Keywords:

Remember to check out the Check out our Most Cited Articles!
Check out these titles on Image Analysis

References

1. N. Zhao, H. Gao, X. Wen and H. Li, “Combination of convolutional neural network and gated recurrent unit for aspect-based sentiment analysis,” IEEE Access 9, 15561–15569 (2021). Crossref, Web of Science, Google Scholar
2. A. Zhao and Y. Yu, “Knowledge-enabled BERT for aspect-based sentiment analysis,” Knowl.-Based Syst. 227, 107220 (2021). Crossref, Web of Science, Google Scholar
3. W. Peishu, H. Li, N. Zeng and F. Li, “FMD-Yolo: An efficient face mask detection method for COVID-19 prevention and control in public,” Image Vis. Comput. 117, 104341 (2022). Crossref, Google Scholar
4. B. Liang, H. Su, L. Gui, E. Cambria and R. Xu, “Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks,” Knowl.-Based Syst. 235, 107643 (2022). Crossref, Web of Science, Google Scholar
5. Z. Nianyin, P. Wu, Z. Wang, H. Li, W. Liu and X. Liu, “A small-sized object detection oriented multi-scale feature fusion approach with application to defect detection,” IEEE Trans. Instrum. Meas. 71, 1–14 (2022). Google Scholar
6. Y. Bie and Y. Yang, “A multitask multiview neural network for end-to-end aspect-based sentiment analysis,” Big Data Min. Anal. 4(3), 195–207 (2021). Crossref, Web of Science, Google Scholar
7. P. Chen, Z. Sun, L. Bing and W. Yang, “Recurrent attention network on memory for aspect sentiment analysis,” in Proc. 2017 Conf. Empirical Methods in Natural Language Processing (2017), pp. 452–461. Crossref, Google Scholar
8. L. Han, N. Zeng, P. Wu and K. Clawson, “Cov-Net: A computer-aided diagnosis method for recognizing COVID-19 from chest X-ray images via machine vision,” Expert Syst. Appl. 207, 118029 (2022). Crossref, Google Scholar
9. Y. Wang, M. Huang, X. Zhu and L. Zhao, “Attention-based LSTM for aspect-level sentiment classification,” in Proc. 2016 Conf. Empirical Methods in Natural Language Processing (2016), Association for Computational Linguistics, pp. 606–615. Crossref, Google Scholar
10. D. Tang, B. Qin, X. Feng and T. Liu, “Effective LSTMs for target-dependent sentiment classification,” preprint (2015), arXiv:1512.01100 [cs.CL]. Google Scholar
11. Y. Lin, C. Wang, H. Song and Y. Li, “Multi-head self-attention transformation networks for aspect-based sentiment analysis,” IEEE Access 9, 8762–8770 (2021). Crossref, Web of Science, Google Scholar
12. H. Yan, J. Dai, X. Qiu and Z. Zhang, “A unified generative framework for aspect-based sentiment analysis,” preprint (2021), arXiv:2106.04300 [cs.CL]. Google Scholar
13. A. H. Sweidan, N. El-Bendary and H. Al-Feel, “Sentence-level aspect-based sentiment analysis for classifying adverse drug reactions (ADRs) using hybrid ontology-XLNet transfer learning,” IEEE Access 9, 90828–90846 (2021). Crossref, Web of Science, Google Scholar
14. E. S. Alamoudi and N. S. Alghamdi, “Sentiment classification and aspect-based sentiment analysis on yelp reviews using deep learning and word embeddings,” J. Decis. Syst. 30(2–3), 259–281 (2021). Crossref, Web of Science, Google Scholar
15. C. Sergio, L. Barbaglia and S. Manzan, “Fine-grained, aspect-based sentiment analysis on economic and financial lexicon,” Knowl.-Based Syst. 247, 108781 (2022). Crossref, Google Scholar
16. H. Jiangtao, A. Wumaier, Z. Kadeer, W. Sun, X. Xin and L. Zheng, “A local and global context focus multilingual learning model for aspect-based sentiment analysis,” IEEE Access 10, 84135–84146 (2022). Crossref, Google Scholar
17. M. Pontiki, D. Galanis, J. Pavlopoulos, H. Papageorgiou, I. Androutsopoulos and S. Manandhar, “SemEval-2014 Task 4: Aspect based sentiment analysis,” in Proc. 8th Int. Workshop on Semantic Evaluation (SemEval 2014) (Association for Computational Linguistics, Dublin, Ireland, 2014), pp. 27–35. Crossref, Google Scholar
18. Kaggle dataset, https://www.kaggle.com/general/164904 (accessed on July 2022). Google Scholar
19. Z. Geng, Z. Chen, Q. Meng and Y. Han, “Novel transformer based on gated convolutional neural network for dynamic soft sensor modeling of industrial processes,” IEEE Trans. Ind. Inform. 18(3), 1521–1529 (2021). Crossref, Google Scholar
20. O. Tarkhaneh, N. Alipour, A. Chapnevis and H. Shen, “Golden tortoise beetle optimizer: A novel nature-inspired meta-heuristic algorithm for engineering problems,” preprint (2021), arXiv:2104.01521 [cs.NE]. Google Scholar
21. S. Arora and S. Singh, “Butterfly optimization algorithm: A novel approach for global optimization,” Soft Comput. 23(3), 715–734 (2019). Crossref, Web of Science, Google Scholar
22. D. Binu and B. S. Kariyappa, “Rider-deep-LSTM network for hybrid distance score-based fault prediction in analog circuits,” IEEE Trans. Ind. Electron. 68(10), 10097–10106 (2020). Crossref, Google Scholar
23. M. E. Basiri, R. S. Chegeni, A. N. Karimvand and S. Nemati, “Bidirectional LSTM deep model for online doctor reviews polarity detection,” 2020 6th Int. Conf. Web Research (ICWR), Tehran, Iran, 2020, pp. 100–105. Crossref, Google Scholar