NLP and Machine Learning for Sentiment Analysis in COVID-19 Tweets: A Comparative Study

Shahedhadeennisa Shaik; Chaitra  S P

doi:10.4108/eetpht.10.7051

Authors

Shahedhadeennisa Shaik Visvesvaraya Technological University https://orcid.org/0000-0002-5411-6880
Chaitra S P Visvesvaraya Technological University https://orcid.org/0000-0002-3090-1075

DOI:

https://doi.org/10.4108/eetpht.10.7051

Keywords:

Sentiment analysis, Machine learning Algorithms, Performance evaluation, NLP (Natural Language Processing), Sentiment classification, Bidi- rectional Long Short-Term Memory (BLSTM), Decision Tree Classifier, Logistic Regression, K Nearest Neighbors (KNN)

Abstract

In response to the COVID-19 pandemic, a novel technique is given for assessing the sentiment of individuals using Twitter data obtained from the UCI repository. Our approach involves the identification of tweets with a discernible sentiment, followed by the application of specific data preprocessing techniques to enhance data quality. We have developed a robust model capable of effectively discerning the sentiments behind these tweets. To evaluate the performance of our model, we employ four distinct machine learning algorithms: logistic regres sion, decision tree, k-nearest neighbor and BLSTM. We classify the tweets into three categories: positive, neutral, and negative sentiments. Our performance evaluation is based on several key metrics, including accuracy, precision, recall, and F1-score. Our experimental results indicate that our proposed model excels in accurately capturing the perceptions of individuals regarding the COVID-19 pandemic.

Downloads

Download data is not yet available.

References

[1] N. Ahmad and J. Siddique, “Personality assessment using Twitter tweets,” Procedia Com- put. Sci., vol. 112, pp. 1964–1973, Sep. 2017.

[2] T. Ahmad, A. Ramsay, and H. Ahmed, “Detecting emotions in English and Arabic tweets,” Information, vol. 10, no. 3, p. 98, Mar. 2019.

[3] A. Bandi and A. Fellah, “Socio-analyzer: A sentiment analysis using social media data,” in Proc. 28th Int. Conf. Softw. Eng. Data Eng., in EPiC Series in Computing, vol. 64, F. Harris,

[4] S. Dascalu, S. Sharma, and R. Wu, Eds. Amsterdam, The Netherlands: EasyChair, 2019, pp. 61–67.

[5] F. Barbieri and H. Saggion, “Automatic detection of irony and humour in Twitter,” in Proc. ICCC, 2014, pp. 155–162.

[6] R. Bhat, V. K. Singh, N. Naik, C. R. Kamath, P. Mulimani, and N. Kulkarni, “COVID 2019 outbreak: The disappointment in Indian teachers,” Asian J. Psychiatry, vol. 50, Apr. 2020, Art. no. 102047.

[7] D. M. Blei, A. Y. Ng, and M. I. Jordan, “Latent Dirichlet allocation,” J. Mach. Learn. Res., vol. 3, pp. 993–1022, Jan. 2003.

[8] P. Boldog, T. Tekeli, Z. Vizi, A. Dénes, F. A. Bartha, and G. Röst, “Risk assessment of novel coronavirus COVID-19 outbreaks outside China,” J. Clin. Med., vol. 9, no. 2, p. 571, Feb. 2020.

[9] G. Carducci, G. Rizzo, D. Monti, E. Palumbo, and M. Morisio, “TwitPersonality: Compu- ting personality traits from tweets using word embeddings and supervised learning,” Infor- mation, vol. 9, no. 5, p. 127, May 2018.

[10] X. Carreras and L. Màrquez, “Boosting trees for anti-spam email filtering,” 2001, arXiv:cs/0109015. [Online]. Available: https://arxiv.org/ abs/cs/0109015.

[11] J. P. Carvalho, H. Rosa, G. Brogueira, and F. Batista, “MISNIS: An intelligent platform for Twitter topic mining,” Expert Syst. Appl., vol. 89, pp. 374–388, Dec. 2017.

[12] B. K. Chae, “Insights from hashtag #supplychain and Twitter analytics: Considering Twitter and Twitter data for supply chain practice and research,” Int. J. Prod. Econ., vol. 165, pp. 247–259, Jul. 2015.

[13] M. De Choudhury, S. Counts, and E. Horvitz, “Predicting postpartum changes in emotion and behavior via social media,” in Proc. SIGCHI Conf. Hum. Factors Comput. Syst., Apr. 2013, pp. 3267–3276.

[14] A. Depoux, S. Martin, E. Karafillakis, R. Preet, A. Wilder-Smith, and H. Larson, “The pan- demic of social media panic travels faster than the COVID-19 outbreak,” J. Travel Med., vol. 27, no. 3, Apr. 2020, Art. no. taaa031.

[15] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirec- tional transformers for language understanding,” in Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Human Lang. Technol., vol. 1. Minneapolis, MN, USA: Association for Computational Linguistics, Jun. 2019, pp. 4171–4186.

[16] M. E. El Zowalaty and J. D. Järhult, “From SARS to COVID-19: A previously unknown SARS-related coronavirus (SARS-CoV-2) of pandemic potential infecting humans—Call for a one health approach,” One Health, vol. 9, Jun. 2020, Art. no. 100124.

[17] I. Fung et al., “Pedagogical demonstration of Twitter data analysis: A case study of world AIDS day, 2014,” Data, vol. 4, no. 2, p. 84, Jun. 2019.

[18] V. Gupta and G. S. Lehal, “A survey of text mining techniques and applications,” J. Emerg. Technol. Web Intell., vol. 1, no. 1, pp. 60–76, Aug. 2009.

[19] K. M. Hammouda and M. S. Kamel, “Efficient phrase-based document indexing for Web document clustering,” IEEE Trans. Knowl. Data Eng., vol. 16, no. 10, pp. 1279–1296, Oct. 2004.

[20] X. Han, J. Wang, M. Zhang, and X. Wang, “Using social media to mine and analyze public opinion related to COVID-19 in China,” Int. J. Environ. Res. Public Health, vol. 17, no. 8, p. 2788, Apr. 2020.

[21] Jung, S.; Akhmetzhanov, A.R.; Hayashi, K.; Linton, N.M.; Yang, Y.; Yuan, B.; Kobayashi, T.; Kinoshita, R.; Nishiura, H. Real-Time Estimation of the Risk of Death from Novel Coro- navirus (COVID-19) Infection: Inference Using Exported Cases. J. Clin. Med. 2020, 9, 523.

[22] National Health Commission of the People’s Republic of China. Announcement of the Na- tional Health Commission of the People’s Republic of China.

[23] China News. International Opinion Praises China’s Completion of HuoShenshan Hospital on the 10th.

[24] Sina Finance. “Guardian Alliance” of “Two Mountain Hospitals”: China Construction Three Bureau Undertakes the Maintenance Tasks of Vulcan Mountain and Thunder Mountain Hospital.

[25] National Health Commission of the People’s Republic of China. The Latest Situation of the New Coronavirus Pneumonia Epidemic Situation as of 24:00 on February 10.

[26] Han, X.; Wang, J. Using Social Media to Mine and Analyze Public Sentiment during a Dis- aster: A Case Study of the 2018 Shouguang City Flood in China. Int. J. Geo Inf. 2019, 8, 185.

[27] Wang, Z.; Ye, X. Social media analytics for natural disaster management. Int. J. Geogr. Inf. Sci. 2018, 32, 49–72.

[28] Liu, Q.; Gao, Y.; Chen, Y. Study on disaster information management system compatible with VGI and crowdsourcing. In Proceedings of the 2014 IEEE Workshop on Advanced Research and Technology in Industry Applications (WARTIA), Ottawa, ON, Canada, 29– 30 September 2014; pp. 464–468.

[29] Michael, F.; Goodchild, J.; Glennon, A. Crowdsourcing geographic information for disaster response: A research frontier. Int. J. Digit. Earth 2010, 3, 231–241.

[30] Chae, J.; Thom, D.; Jang, Y.; Kim, S.Y.; Ertl, T.; Ebert, D.S. Public behavior response anal- ysis in disaster events utilizing visual analytics of microblog data. Comput. Graph. 2014, 38, 51–60.

[31] Steiger, E.; Resch, B.; Zipf, A. Exploration of spatiotemporal and semantic clusters of Twit- ter data using unsupervised neural networks. Int. J. Geogr. Inf. Sci. 2016, 30, 1694–1716.

[32] Miller, H.J.; Goodchild, M.F. Data-driven geography. GeoJournal 2015, 80, 449–461.

[33] Gruebner, O.; Lowe, S.; Sykora, M.; Sankardass, K.; Subramanian, S.; Galea, S. Spatio- temporal distribution of negative emotions in New York City after a natural disaster as seen in social media. Int. J. Environ. Res. Public Health 2018, 15, 2275.

[34] Dahal, B.; Kumar, S.A.P.; Li, Z. Topic modeling and sentiment analysis of global climate change tweets. Soc. Netw. Anal. Min. 2019, 9, 24.

[35] Wang, Z.; Ye, X.; Tsou, M.H. Spatial, temporal, and content analysis of Twitter for wildfire hazards. Nat. Hazards 2016, 83, 523–540.

[36] Ye, X.; Li, S.; Yang, X.; Qin, C. Use of Social Media for the Detection and Analysis of Infectious Diseases in China. ISPRS Int. J. Geo Inf. 2016, 5, 156.

[37] Zong, Q.; Yang, S.; Chen, Y.; Shen, H. Behavior of Social Media Users in Disaster Area under the Outburst Disasters: A Content Analysis and Longitudinal Study of Explosion in Tianjin 12(th) August 2015. J. Inf. Resour. Manag. 2017, 7, 13–19. (In Chinese).

[38] Wang, Y.; Wang, T.; Ye, X.; Zhu, J.; Lee, J. Using social media for emergency response and urban sustainability: A case study of the 2012 Beijing rainstorm. Sustainability 2016, 8, 25.

[39] Saffari, A.; Leistner, C.; Santner, J.; Godec, M.; Bischof, H. On-line Random Forests. In Proceedings of the 2009 IEEE 12th International Conference on Computer Vision Work- shops (ICCV Workshops), Kyoto, Japan, 27 September–4 October 2009.

[40] Griffiths, T.L.; Steyvers, M. Finding scientific topics. Proc. Natl. Acad. Sci. USA 2004, 101, 5228–5235.

[41] Blei, D.M.; Ng, A.Y.; Jordan, M.I. Latent dirichlet allocation. J. Mach. Learn. Res. 2012, 3, 993–1022.

[42] Bokaee Nezhad, Z.; Deihimi, M.A. Twitter sentiment analysis from Iran about COVID 19 vaccine. Diabetes Metab. Syndr. Clin. Res. Rev. 2022.

[43] He, K.; Mao, R.; Gong, T.; Li, C.; Cambria, E. Meta-based Self-training and Re-weighting for Aspect-based Sentiment Analysis. IEEE Trans. Affect. Comput. 2022.

[44] Chandra, R.; Krishna, A. COVID-19 sentiment analysis via deep learning during the rise of novel cases. PLoS ONE 2021.

[45] Anitha, S.; Metilda, M. Apache Hadoop based effective sentiment analysis on demonetiza- tion and covid-19 tweets. Glob. Transit. Proc. 2022.

[46] Kumar, V. Spatiotemporal sentiment variation analysis of geotagged COVID-19 tweets from India using a hybrid deep learning model. Sci. Rep. 2022

[47] Abd-Alrazaq, A.; Alhuwail, D.; Househ, M.; Hai, M.; Shah, Z. Top Concerns of Tweeters during the COVID-19 Pandemic: Infoveillance Study. J. Med. Internet Res. 2020.

[48] Liang, B.; Su, H.; Gui, L.; Cambria, E.; Xu, R. Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks. Knowl.-Based Syst. 2022.

[49] Chakraborty, A.K.; Das, S.; Kolya, A.K. Sentiment Analysis of Covid-19 Tweets Using Evolutionary Classification-Based LSTM Model. Adv. Intell. Syst. Comput. 2021.

[50] Storey, V.C.; O’leary, D.E. Text Analysis of Evolving Emotions and Sentiments in COVID- 19 Twitter Communication. Cognit. Comput. 2022.

[51] C. C. Aggarwal and C. K. Reddy, Data Clustering: Algorithms and Applications. Boca Ra- ton, FL, USA: CRC Press, 2013.