Optimized aspect level sentiment analysis of tweet data using deep learning and rule-based techniques

S. N. Enemuo; O. N. Akande; M. O. Lawrence; I. C. Saidu

doi:10.46481/jnsps.2025.2300

Authors

S. N. Enemuo Computer Science Department, Landmark University, Kwara State, Nigeria
O. N. Akande
[email protected]
Computer Science Department, Nile University, Abuja
M. O. Lawrence Computer Science Department, Baze University, Abuja
I. C. Saidu Computer Science Department, Baze University, Abuja

Keywords:

Aspects Extraction , Sentiment Analysis, Deep Learning, Data Security

Abstract

Social media platforms are no longer just for interacting with others and having fun; they are also now a place for people to voice their opinions on topics that are important to them. It has developed into a potent platform in recent years whereby elections can be won or lost. Governments and organizations are therefore becoming more and more interested in the opinions that citizens voice on social media platforms. Towards coming up with a localized sentiment analysis system, this research explored the use of rules and optimized Convolutional Neural Network (CNN) Deep Learning (DL) technique for aspect-level sentiment analysis of users’ tweets. A total of 26,401 tweets about the security situation in Nigeria were used as the test data. Most tweets in the Nigerian Twitter space are expressed in Pidgin language, which is a blend of English and local words, therefore, a rule-based technique was used to capture the local words and abbreviated character representations used in the Nigerian tweet data used for testing. Moreover, existing works have shown that CNN does not adequately capture modeling sequence information and long[1]distance dependency of texts. Therefore, this study employed existing word embedding to boost the performance of CNN for sentiment polarity classification. The proposed rule and optimized CNN model outperformed the traditional CNN and state-of-the-art Glove and word2Vec models with an accuracy of 89.31%, a recall value of 88.21%, a precision value of 88.15%, and an F1 score of 87.62%.

Dimensions

REFERENCES

[1] M. Abdelgwad, T. Hassan, A. Soliman, A. I. Taloba & M. Fawzy, “Arabic aspect-based sentiment analysis using bidirectional GRU-based models”, Journal of King Saud University – Computer Information Science 34 (2021) 6652. https://doi.org/10.1016/j.jksuci.2021.08.030

[2] O. N. Akande, E. S. Nnaemeka, O. C. Abikoye, H. B. Akande, A. Balogun & J. Ayoola, TWEERIFY: A web-based sentiment analysis system using rule and deep learning techniques, In Proceedings of International Conference on Computational Intelligence and Data Engineering, ICCIDE, Singapore: Springer Nature Singapore, 2021, pp. 75–87. https://doi.org/10.1007/978-981-16-7182-1 7.

[3] O. Edeama, “The Role of Social Media and Social Networking in Information Service Provision: A Practical View”, in Social Media Strategies for Dynamic Library Service Development, 2015, pp. 124–139. https://doi.org/10.4018/978-1-4666-7415-8.ch007

[4] P. Borah, “Facebook Use in the 2012 USA Presidential Campaign”, in Social Media in Politics: Case Studies on the Political Power of Social Media, 2014, pp. 201–211. https://doi.org/10.1007/978-3-319-04666-2

[5] S. Bute, “The role of social media in mobilizing people for riots and revolutions”, in Social Media in Politics: Case Studies on the Political Power of Social Media, 2014, pp. 213–223. https://doi.org/10.1007/978-3-319-04666-2

[6] D. Irak, “A close-knit bunch: Political concentration in Turkey’s Anadolu Agency through Twitter interactions”, Turkish Studies 17 (2016) 336. https://doi.org/10.1080/14683849.2016.1138287

[7] B. Bansal & S. Srivastava, “On predicting elections with hybrid topic based sentiment analysis of tweets”, Procedia Computer Science 135 (2018) 346. https://doi.org/10.1016/j.procs.2018.08.183

[8] T. R. White & T. Anderson, “The use of Twitter in the 2013 Italian political election”, in Social Media in Politics: Case Studies on the Political Power of Social Media, 2014, pp. 63–77. https://doi.org/10.1007/978-3-319-04666-2

[9] P. Borah, “Facebook use in the 2012 USA Presidential Campaign”, in Social Media in Politics: Case Studies on the Political Power of Social Media, 2014, pp. 213–223. https://doi.org/10.1007/978-3-319-04666-2

[10] E. Bulut & E. Yor¨ uk, “Digital populism: Trolls and Political Polarization of Twitter in Turkey”, International Journal of Communication 11 (2017) 4093. https://ijoc.org/index.php/ijoc/article/view/6702.

[11] P. Chikersal, S. Poria & E. Cambria, SeNTU: Sentiment analysis of tweets by combining a rule-based classifier with supervised learning, Proceedings of the 9th international workshop on semantic evaluation, 2015, pp. 647–651. https://aclanthology.org/S15-2108/.

[12] U. U. Ibekwe, U. M. Mbanaso, N. A. Nnanna & U. A. Ibrahim, “A machine learning sentiment classification of factors that shape trust in smart contracts”, Journal of the Nigerian Society of Physical Sciences 7 (2025) 2177. https://doi.org/10.46481/jnsps.2025.2177.

[13] P. Ray & A. Chakrabarti, “A mixed approach of deep learning method and rule-based method to improve aspect level sentiment analysis”, Applied Computing and Informatics 18 (2020) 163. https://doi.org/10.1016/j.aci.2019.02.002.

[14] Z. Hu, Z. Yang, R. Salakhutdinov & E. Xing, “Deep neural networks with massive learned knowledge”, in International Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, 2016, pp. 1670–1679. https://doi.org/10.18653/v1/D16-1173.

[15] Z. Hu, X. Ma, Z. Liu, E. Hovy & E. Xing, “Harnessing deep neural networks with logic rules”, in Fifty-Fourth Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, 2016, pp. 2410–2420. https://doi.org/10.18653/v1/P16-1228.

[16] S. Al-dabet, S. Tedmori & M. Al-smadi, “Enhancing Arabic aspect-based sentiment analysis using deep learning models”, Computer Speech & Language 69 (2021) 1. https://doi.org/10.1016/j.csl.2021.101224.

[17] B. Liang, H. Su, L. Gui, E. Cambria & R. Xu, “Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks”, Knowledge-Based Systems 235 (2022) 107711. https://doi.org/10.1016/j.knosys.2021.107711.

[18] B. Ozyurt & M. A. Akcayol, “A new topic modeling-based approach for aspect extraction in aspect-based sentiment analysis: SS-LDA”, Expert Systems with Applications 168 (2021) 114231. https://doi.org/10.1016/j.eswa.2020.114231.

[19] R. K. Yadav, L. Jiao, M. Goodwin & O. Granmo, “Positionless aspect-based sentiment analysis using attention mechanism”, Knowledge Based Systems 226 (2021) 107136. https://doi.org/10.1016/j.knosys.2021.107136.

[20] K. Ahmed, M. I. Nadeem, Z. Zheng, D. Li, I. Ullah, M. Assam, Y. Y. Ghadi & H. G. Mohamed, “Breaking down linguistic complexities: A structured approach to aspect-based sentiment analysis”, Journal of King Saud University - Computer and Information Sciences 35 (2023) 101651. https://doi.org/10.1016/j.jksuci.2023.101651.

[21] J. Chen, H. Fan & W. Wang, “Syntactic and semantic aware graph convolutional network for aspect-based sentiment analysis”, IEEE Access 12 (2024) 22500. https://doi.org/10.1109/ACCESS.2024.3364353.

[22] O. N. Akande, “Tweet data about security situation in Nigeria”, Mendeley Data 1 (2022). https://doi.org/10.17632/cvtznrzmx2.1.

[23] S. Al-dabet, S. Tedmori & M. Al-smadi, “Enhancing Arabic aspect-based sentiment analysis using deep learning models”, Computer Speech & Language 69 (2021) 101224. https://doi.org/10.1016/j.csl.2021.101224.

[24] U. A. Siddiqua, T. Ahsan & A. N. Chy, “Combining a rule-based classifier with weakly supervised learning for Twitter sentiment analysis”, in International Conference on Innovation, Science and Engineering Technology (ICISET), 2016, pp. 1–4. https://doi.org/10.1109/ICISET.2016.7856499.

[25] A. Braoudaki, E. Kanellou, C. Kozanitis & P. Fatourou, “Hybrid data driven and rule-based sentiment analysis on Greek text”, Procedia Computer Science 178 (2020) 234. https://doi.org/10.1016/j.procs.2020.11.025.

[26] S. Yoo, J. Song & O. Jeong, “Social media contents-based sentiment analysis and prediction system”, Expert Systems with Applications 105 (2018) 102. https://doi.org/10.1016/j.eswa.2018.03.055.

[27] M. Birjali, A. Beni-hssane & M. Erritali, “Machine learning and semantic sentiment analysis-based algorithms for suicide sentiment prediction in social networks”, Procedia Computer Science 113 (2017) 65. https://doi.org/10.1016/j.procs.2017.08.290.

[28] K. Sailunaz & R. Alhajj, “Emotion and sentiment analysis from Twitter text”, Journal of Computer Science 36 (2019). https://doi.org/10.1016/j.jocs.2019.05.009.

[29] S. Poria, E. Cambria & A. Gelbukh, “Aspect extraction for opinion mining with a deep convolutional neural network”, Knowledge-Based Systems 108 (2016) 42. https://doi.org/10.1016/j.knosys.2016.06.009.

[30] R. Yin, P. Li & B. Wang, “Sentiment lexical-augmented convolutional neural networks for sentiment analysis”, in International Conference on Data Science Cyberspace (DSC), 2017, pp. 630–635.

[31] R. Bharathi, R. Bhavani & R. Priya, “Leveraging deep learning models for automated aspect-based sentiment analysis and classification”, International Journal of Electrical and Electronics Engineering 10 (2023) 120. https://doi.org/10.14445/23488379/ijeee-v10i5p111.

[32] M. Yang, W. Zhao, J. Ye, Z. Lei, Z. Zhao & S. Zhang, “Investigating Capsule Networks with Dynamic Routing for Text Classification”, in International Conference on Empirical Methods in Natural Language Processing, 2018, pp. 3110–3119. https://doi.org/10.18653/v1/d18-1350.

[33] B. Zhang, X. Xu, X. Li, X. Chen, Y. Ye & Z. Wang, “Sentiment analysis through critic learning for optimizing convolutional neural networks with rules”, Neurocomputing 356 (2019) 21. https://doi.org/10.1016/j.neucom.2019.04.038.