A Deep Learning Approach for Sentiment Analysis of COVID-19 Reviews
Source abstract
Abstract
User-generated multi-media content, such as images, text, videos, and speech, has recently become more popular on social media sites as a means for people to share their ideas and opinions. One of the most popular social media sites for providing public sentiment towards events that occurred during the COVID-19 period is Twitter. This is because Twitter posts are short and constantly being generated. This paper presents a deep learning approach for sentiment analysis of Twitter data related to COVID-19 reviews. The proposed algorithm is based on an LSTM-RNN-based network and enhanced featured weighting by attention layers. This algorithm uses an enhanced feature transformation framework via the attention mechanism. A total of four class labels (sad, joy, fear, and anger) from publicly available Twitter data posted in the Kaggle database were used in this study. Based on the use of attention layers with the existing LSTM-RNN approach, the proposed deep learning approach significantly improved the performance metrics, with an increase of 20% in accuracy and 10% to 12% in precision but only 12–13% in recall as compared with the current approaches. Out of a total of 179,108 COVID-19-related tweets, tweets with positive, neutral, and negative sentiments were found to account for 45%, 30%, and 25%, respectively. This shows that the proposed deep learning approach is efficient and practical and can be easily implemented for sentiment classification of COVID-19 reviews.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Hate Speech and Cyberbullying Detection · Sentiment Analysis and Opinion Mining · Misinformation and Its Impacts
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Engineering and Technology, Central Queensland University, Melbourne, VIC 3000, Australia
School of Business and Law, Central Queensland University, Melbourne, VIC 3000, Australia
References (44)
Show source-provided references
1. Sentiment analysis of COVID-19 tweets by deep learning classifiers–A study to show how popularity is affecting accuracy in social media10.1016/j.asoc.2020.106754 ↗
2. Twitter sentiment analysis using support vector machine and K-NN classifiers10.29322/IJSRP.8.10.2018.p8252 ↗
3. Sentiment analysis of social media response on the COVID-19 outbreak10.1016/j.bbi.2020.05.006 ↗
4. Nunan Fake news, social media and marketing: A systematic review10.1016/j.jbusres.2020.11.037 ↗
5. Meng, H., Lei, T., Li, M., Li, K., Xiong, N., and Wang, L. (2020). An integrated non-linear deep learning method for sentiment classification of online reviews. Advances in Natural Computation, Fuzzy Systems and Knowledge Discovery, Springer.
6. A sentiment-enhanced hybrid recommender system for movie recommendation: An extensive data analytics framework10.1155/2018/8263704 ↗
7. Learning multiple layers of knowledge representation for aspect-based sentiment analysis10.1016/j.datak.2017.06.001 ↗
8. Analysis of twitter data with the bayesian fused graphical lasso10.1371/journal.pone.0235596 ↗
9. Schmidt, A., and Wiegand, M. (2017, January 3). A survey on hate speech detection using natural language processing. Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media, Valencia, Spain.10.18653/v1/W17-1101 ↗
10. Jnoub, N., Al Machot, F., and Klas, W. (2020). A domain-independent classification model for sentiment analysis using neural models. Appl. Sci., 10.10.3390/app10186221 ↗
11. Deep convolution neural networks for twitter sentiment analysis10.1109/ACCESS.2017.2776930 ↗
12. Singh, C., Wibowo, S., and Grandhi, S. (2021, January 28–30). A deep learning approach for human face sentiment classification. Proceedings of the 2021 21st ACIS International Semi-Virtual Winter Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD-Winter 2021, Ho Chi Minh City, Vietnam.10.1109/SNPDWinter52325.2021.00015 ↗
13. Han, J., Qian, K., Song, M., Yang, Z., Ren, Z., Liu, S., and Li, X. (2020). An early study on intelligent analysis of speech under COVID-19: Severity, sleep quality, fatigue, and anxiety. arXiv.10.21437/Interspeech.2020-2223 ↗
14. Spatiotemporal-based sentiment analysis on tweets for risk assessment of event using deep learning approach10.1002/spe.2851 ↗
15. Bootstrapping social emotion classifcation with semantically rich hybrid neural networks10.1109/TAFFC.2017.2716930 ↗
16. A short text sentiment-topic model for product reviews10.1016/j.neucom.2018.02.034 ↗
17. Convolutional recurrent deep learning model for sentence classification10.1109/ACCESS.2018.2814818 ↗
18. Preethi, G., Krishna, P., Mohammad, S., Obaidat, V., Sartha, V., and Yenduri, S. (2017, January 21–23). Application of deep learning to sentiment analysis for recommender system on cloud. Proceedings of the International Conference on Computer, Information and Telecommunication Systems, Dalian, China.10.1109/CITS.2017.8035341 ↗
19. On negative results when using sentiment analysis tools for software engineering research10.1007/s10664-016-9493-x ↗
20. Sentiment analysis of Tweets using support vector machine
21. Jagdale, R.S., Shirsat, V.S., and Deshmukh, S.N. (2019). Sentiment analysis on product reviews using machine learning techniques. Cognitive Informatics and Soft Computing, Springer.10.1007/978-981-13-0617-4_61 ↗
22. Arras, L., Montavon, G., Müller, K.R., and Samek, W. (2017). Explaining recurrent neural network predictions in sentiment analysis. arXiv.10.18653/v1/W17-5221 ↗
23. Enhanced Twitter sentiment analysis using hybrid approach and by accounting local contextual semantic
24. Du, J., Xu, Y., Song, H., and Tao, C. (2017). Leveraging machine learning-based approaches to assess human papilloma virus vaccination sentiment trends with Twitter data. BMC Med., 17.10.1186/s12911-017-0469-6 ↗
25. Geetha, R., Karthika, S., and Mohanavalli, S. (2020). Tweet classification using deep learning approach to predict sensitive personal data. Advances in Electrical and Computer Technologies, Springer.10.1007/978-981-15-5558-9_17 ↗
26. Hosseini, H., Xiao, B., Jaiswal, M., and Poovendran, R. (2017, January 18–21). On the limitation of convolutional neural networks in recognizing negative images. Proceedings of the 16th IEEE International Conference on Machine Learning and Applications (ICMLA), Cancun, Mexico.10.1109/ICMLA.2017.0-136 ↗
27. Ghimire, S., Thapa, A.K., Jha, A., Kumar, A., Kumar, A., and Adhikari, S. (2020, January 5–7). AI and IoT solutions for tackling COVID-19 pandemic. Proceedings of the 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA), Coimbatore, India.10.1109/ICECA49313.2020.9297454 ↗
28. Chloe for COVID-19: Evolution of an intelligent conversational agent to address infodemic management needs during the COVID-19 pandemic
29. Dhakal, P., Damacharla, P., Javaid, A.Y., Vege, H.K., and Devabhaktuni, V.K. (2020, January 24–26). IVACS: Intelligent voice assistant for coronavirus disease (COVID-19) self-assessment. Proceedings of the 2020 International Conference on Artificial Intelligence & Modern Assistive Technology (ICAIMAT), Riyadh, Saudi Arabia.10.1109/ICAIMAT51101.2020.9308013 ↗
30. Smart technologies driven approaches to tackle COVID-19 pandemic: A review
31. Mujahid, M., Lee, E., Rustam, F., Washington, P.B., Ullah, S., Reshi, A.A., and Ashraf, I. (2021). Sentiment analysis and topic modeling on Tweets about online education during COVID-19. Appl. Sci., 11.10.3390/app11188438 ↗
32. Sawik, B., and Płonka, J. (2022). Project and prototype of mobile application for monitoring the global COVID-19 epidemiological situation. Int. J. Environ. Res. Public Health, 19.10.3390/ijerph19031416 ↗
33. New approach to detect and classify stroke in skull CT images via analysis of brain tissue densities10.1016/j.cmpb.2017.06.011 ↗
34. A deep supervised approach for ischemic lesion segmentation from multimodal MRI using fully convolutional network10.1016/j.asoc.2019.105685 ↗
35. Vijayaprabakaran, K., and Sathiyamurthy, K. (J. King Saud Uni. Comput. Inform. Sci., 2020). Towards activation function search for long short-term model network: A differential evolution-based approach, J. King Saud Uni. Comput. Inform. Sci., in press.
36. A performance comparison of supervised machine learning models for Covid-19 tweets sentiment analysis10.1371/journal.pone.0245909 ↗
37. Dong, X., and de Mel, G. (2018, January 15–20). A helping hand: Transfer learning for deep sentiment analysis. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Melbourne, Australia.10.18653/v1/P18-1235 ↗
38. Predictive analysis and modelling football results using machine learning approach for English premier league10.1016/j.ijforecast.2018.01.003 ↗
39. Attention-based sentiment reasoner for aspect-based sentiment analysis10.1186/s13673-019-0196-3 ↗
40. A hybrid CNN-LSTM model for improving accuracy of movie reviews sentiment analysis10.1007/s11042-019-07788-7 ↗
41. Hernández, A., and Amigó, J.M. (2021). Attention mechanisms and their applications to complex systems. Entropy, 23.10.3390/e23030283 ↗
42. Kardakis, S., Perikos, I., Grivokostopoulou, F., and Hatzilygeroudis, I. (2021). Examining attention mechanisms in deep learning models for sentiment analysis. Appl. Sci., 11.10.3390/app11093883 ↗
43. Twitter sentiment analysis using hybrid cuckoo search method10.1016/j.ipm.2017.02.004 ↗
44. The pandemic of social media panic travels faster than the COVID-19 outbreak10.1093/jtm/taaa031 ↗