JCEEES
Journal of Computer & Electrical and Electronics Engineering Sciences

JCEEES aims to publish original articles covering the theoretical foundations of major computer, electronic and electrical engineering sciences, as well as academic, commercial and educational aspects that propose new ideas for the application and design of artificial intelligence, software and information systems. In addition to wide-ranging regular topics, JCEEES also makes it a principle to include special topics covering specific topics in all areas of interest mainly in computational medicine, artificial intelligence, computer science, and electrical & electronic engineering science.

eISSN: 2980-177X
Creative Commons CC BY-NC-ND 4.0 International License.

Online Manuscript System

Index
Original Article
Investigation of fine-tuned BERT models for sentiment analysis in COVID-19 tweets using a fuzzy logic-based ensemble approach
Abstract
Aims: With the beginning of the COVID-19 pandemic, social media applications such as twitter used more than usual because people started to work at their homes rather than offices. Thus, data on this application has become more important to manage crisis of COVID-19. While conventional deep learning methods have shown success in sentiment analysis, they often encounter challenges in capturing the inherent semantic ambiguity and informal linguistic structures prevalent on social media platforms. To find ambiguity on these texts propose ensemble model enhanced by fuzzy logic designed to improve sensitivity and capability.
Methods: Architecture uses BERT model, fine-tuned for specific data to supply dynamic attributes for MLP, LSTM and BiLSTM elements. Their shared executive is regulated via Mamdani Fuzzy Interference System. Then dynamic weights results from defuzzification after mapping prediction of confidence and validation accuracy value on 7 level fine-grained rule set.
Results: Experiment performed on Kaggle Corona NLP dataset resulted in 91.28% accuracy, 91.23% F1 score and 91.38% precision. System’s robust performance is demonstrated by Mean Square Error of 0.2301.
Conclusion: Relative analysis demonstrates dominance of this approach against traditional models. Fuzzy Ensemble model proposes more trustworthy solution for obstruse tweets with successfully straining noise and dealing semantic uncertainties which is naturally present in social media data.

Keywords : Sentiment analysis, BERT, fuzzy logic, ensemble learning, COVID-19, natural language processing

Download Article


1. Airlangga, G. (2024). Spam detection in YouTube comments using deep learning models: a comparative study of MLP, CNN, LSTM, BiLSTM, GRU, and attention mechanisms. MALCOM: Indonesian Journal of Machine Learning and Computer Science, 4(4), 1533-1538.
2. Alam, M. S., Mrida, M. S. H., & Rahman, M. A. (2025). Sentiment analysis in social media: how data science impacts public opinion knowledge integrates natural language processing (NLP) with artificial intelligence (AI). American Journal of Scholarly Research and Innovation, 4(1), 63-100.
3. Anwar, Z., Afzal, H., Altaf, N., Kadry, S., & Kim, J. (2024). Fuzzy ensemble of fine-tuned BERT models for domain-specific sentiment analysis of software engineering dataset. PLOS ONE, 19(5), e0300279. https://doi.org/10.1371/journal.pone.0300279
4. Arslan, S., Orman, Z., & Akan, A. (2021). A novel fuzzy logic-based text classification method for tracking rare events on Twitter. IEEE Access, 9, 36915-36929. https://doi.org/10.1109/ACCESS.2021.3062345
5. Bashar, M. K., Monjur, O., Islam, S., Shams, M. G., & Quader, N. (2025). Exploring synergistic ensemble learning: uniting CNNs, MLP-mixers, and vision transformers to enhance image classification. arXiv. https://arxiv.org/abs/2504.09076
6. Bello, A., Ng, S. C., & Leung, M. F. (2023). A BERT framework for sentiment analysis of tweets. Sensors, 23(1), 506. https://doi.org/10.3390/s23010506
7. Bilal, A. A., Erdem, O. A., & Toklu, S. (2023). Applying sentiment analysis on children’s stories. Gazi University Journal of Science Part A: Engineering and Innovation, 10(1), 71-84.
8. Bilal, A. A., Erdem, O. A., & Toklu, S. (2024). Children’s sentiment analysis from texts by using weight updated tuned with random forest classification. IEEE Access, 12, 70103-70116. https://doi.org/10.1109/ACCESS.2024.3400992
9. Cai, R., Qin, B., Chen, Y., Zhang, L., Yang, R., Chen, S., & Wang, W. (2020). Sentiment analysis about investors and consumers in energy market based on BERT-BiLSTM. IEEE Access, 8, 171408-171416. https://doi.org/10.1109/ACCESS.2020.3024417
10. Chen, X., Cong, P., & Lv, S. (2022). A long-text classification method of Chinese news based on BERT and CNN. IEEE Access, 10, 34094-34105. https://doi.org/10.1109/ACCESS.2022.3161545
11. Dhanalakshmi, P., Reddy, U. J., Ravikanth, G., Samathoti, P., & Ramu, G. (2024). COVID-19 Twitter data analysis using LSTM and BERT techniques. International Journal of Engineering Trends and Technology, 72(1), 219-228.
12. Elgabry, M., & Hamdi, A. (2025). Confidence-credibility aware weighted ensembles of small LLMs outperform large LLMs in emotion detection. arXiv. https://arxiv.org/abs/2512.17630
13. Garcia-Plaza, A. P., Fresno, V., & Martinez, R. (2008). Web page clustering using a fuzzy logic based representation and self-organizing maps. In Proceedings of IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology.
14. Haroon, N. H., Abdulsada, Z. R., Sharif, H., Ahmed, W. S., Saleem, M., & Jawad, I. A. (2023). Social media analysis using fuzzy natural language processing with an extension of semantic queries. In Proceedings of AICERA/ICIS. https://doi.org/10.1109/AICERA59538.2023.10420086
15. Howells, K., & Ertugan, A. (2017). Applying fuzzy logic for sentiment analysis of social media network data in marketing. Procedia Computer Science, 120, 664-670. https://doi.org/10.1016/j.procs.2017.11.293
16. Jang, J. S. R., Sun, C. T., & Mizutani, E. (1997). Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence. Prentice Hall.
17. Kale, K., Esfahanizadeh, H., Elias, N., Baser, O., Médard, M., & Vishwanath, S. (2024). TexShape: information theoretic sentence embedding for language models. arXiv. https://arxiv.org/abs/2402.05132
18. Karaca, Y. E., & Aslan, S. (2021). Sentiment analysis of COVID-19 tweets using LSTM. Journal of Computer Science (IDAP Special Issue), 366-374.
19. Kumar, G., Agrawal, R., Sharma, K., Gundalwar, P. R., Kazi, A., Agrawal, P., ..., & Salagrama, S. (2024). Combining BERT and CNN for sentiment analysis: a case study on COVID-19. IJACSA, 15(10), 676-686.
20. Liu, M., Zhang, H., Xu, Z., & Ding, K. (2024). The fusion of fuzzy theories and natural language processing: a state-of-the-art survey. Applied Soft Computing, 162, 111818. https://doi.org/10.1016/j.asoc.2024.111818
21. Mendel, J. M. (1995). Fuzzy logic systems for engineering: a tutorial. Proceedings of the IEEE, 83(3), 345-377. https://doi.org/10.1109/5.364486
22. Minaee, S., Kalchbrenner, N., Cambria, E., Nikzad, N., Chenaghlu, M., & Gao, J. (2021). Deep learning-based text classification: a comprehensive review. ACM Computing Surveys, 54(3), 1-40. https://doi.org/10.1145/3439726
23. Nandi, S., Subrahmanyan, P., & Singh, S. (2025). Fuzzy-based ensemble learning for sentiment analysis in social media data. Global Journal of Engineering Innovations & Interdisciplinary Research, 5(1), 1-8.
24. Rahman, M. M., Shiplu, A. I., Watanobe, Y., & Alam, M. A. (2025). RoBERTa-BiLSTM: a context-aware hybrid model for sentiment analysis. arXiv. https://arxiv.org/abs/2406.00367
25. Singh, C., Imam, T., Wibowo, S., & Grandhi, S. (2022). A deep learning approach for sentiment analysis of COVID-19 reviews. Applied Sciences, 12(8), 3709. https://doi.org/10.3390/app12083709
26. Seth, T., & Muhuri, P. K. (2024). Enriching word embeddings with fuzzy systems for NLP tasks. In IEEE FUZZ Conference. https://doi.org/10.1109/FUZZ-IEEE60900.2024.10611949
27. Sherin, A., Lokesh, S., Deepa, S. N., & Jeya, I. J. S. (2025). Fusion of deep recurrent neural network models and fuzzy decision support system for tweet sentiment analysis. Automatika, 66(4), 28-50. https://doi.org/10.1080/00051144.2025.XXXXXX
28. Xu, C., & Kechadi, M.-T. (2024). An enhanced fake news detection system with fuzzy deep learning. IEEE Access, 12, 88009-88022. https://doi.org/10.1109/ACCESS.2024.3418340
29. Yang, L., Wang, J., & Qiu, W. (2025). RoBERTa-based multi-feature integrated BiLSTM and CNN model for ceramic review analysis. IEEE Access, 13, 103681-103692.
30. Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2018). BERT: pre-training of deep bidirectional transformers for language understanding. arXiv. https://arxiv.org/abs/1810.04805
31. Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., ..., & Stoyanov, V. (2019). RoBERTa: a robustly optimized BERT pretraining approach. arXiv. https://arxiv.org/abs/1907.11692
32. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780. https://doi.org/10.1162/neco.1997. 9.8.1735
33. Schuster, M., & Paliwal, K. K. (1997). Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing, 45(11), 2673-2681. https://doi.org/10.1109/78.650093
34. Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088), 533-536. <a href="https://doi.org/10.1038/323533a0">https://doi.org/10.1038/323533a0</a>
Article available in :
Volume 4, Issue 1, 2026
Page : 17-26
https://doi.org/10.51271/JCEEES-0033
Article Information
Received : 19 Oca 2026
Accepted : 24 Şub 2026
Published : 25 Nis 2026
Corresponding Author :

Mustafa Sefa Evgin: Department of Computer Engineering, Faculty of Technology, Gazi University, Ankara, Turkiye

[email protected]
Citation : Evgin, M. S., & Toklu, S. (2026). Investigation of fine-tuned BERT models for sentiment analysis in COVID-19 tweets using a fuzzy logic-based ensemble approach. J Comp Electr Electron Eng Sci, 4(1), 17-26.

Read: 24
Download : 73
Cited: 0
_Footer