Abstract
Towards the end of 2019, Wuhan experienced an outbreak of novel coronavirus, which soon spread worldwide, resulting in a deadly pandemic that infected millions of people around the globe. The public health agencies followed many strategies to counter the fatal virus. However, the virus severely affected the lives of the people. In this paper, we study the sentiments of people from the top five worst affected countries by the virus, namely the USA, Brazil, India, Russia, and South Africa. We propose a deep language-independent Multilevel Attention-based Conv-BiGRU network (MACBiG-Net), which includes embedding layer, word-level encoded attention, and sentence-level encoded attention mechanisms to extract the positive, negative, and neutral sentiments. The network captures the subtle cues in a document by focusing on the local characteristics of text along with the past and future context information for the sentiment classification. We further develop a COVID-19 Sentiment Dataset by crawling the tweets from Twitter and applying topic modeling to extract the hidden thematic structure of the document. The classification results demonstrate that the proposed model achieves an accuracy of 85%, which is higher than other well-known algorithms for sentiment classification. The findings show that the topics which evoked positive sentiments were related to frontline workers, entertainment, motivation, and spending quality time with family. The negative sentiments were related to socio-economic factors like racial injustice, unemployment rates, fake news, and deaths. Finally, this study provides feedback to the government and health professionals to handle future outbreaks and highlight future research directions for scientists and researchers.
- R. M. Anderson, H. Heesterbeek, D. Klinkenberg, and T. D. Hollingsworth. 2020. How will country-based mitigation measures influence the course of the COVID-19 epidemic? The Lancet 395, 10228 (2020), 931–934.Google Scholar
Cross Ref
- K.-W. Fu, H. Liang, N. Saroha, Z. T. Ho, P. Ip, and I. C.-H. Fung. 2016. How people react to Zika virus outbreaks on Twitter? A computational content analysis. American Journal of Infection Control 44, 12 (2016), 1700–1702.Google Scholar
Cross Ref
- A. S. Imran, S. M. Daudpota, Z. Kastrati, and R. Batra. 2019. How did Ebola information spread on Twitter: Broadcasting or viral spreading? BMC Public Health 19, 1 (2019), 1–11.Google Scholar
- K. A. Lachlan, Z. Xu, E. E. Hutter, R. Adam, and P. R. Spence. 2019. A little goes a long way: Serial transmission of Twitter content associated with Hurricane Irma and implications for crisis communication. Journal of Strategic Innovation and Sustainability 14, 1 (2019), 16–26.Google Scholar
- J. Samuel, M. Rahman, G. N. Ali, Y. Samuel, A. Pelaez, P. H. J. Chong, and M. Yakubov. 2020. Feeling positive about reopening? New normal scenarios from COVID-19 US reopen sentiment analytics. IEEE Access 8, 1 (2020), 42173–142190.Google Scholar
Cross Ref
- R. J. Medford, S. N. Saleh, A. Sumarsono, T. M. Perl, and C. U. Lehmann. 2020. An “Infodemic”: Leveraging high-volume Twitter data to understand early public sentiment for the Coronavirus disease 2019 outbreak. Open Forum Infectious Diseases 7, 7 (2020), 1–7.Google Scholar
Cross Ref
- K. Garcia and L. Berton. 2021. Topic detection and sentiment analysis in Twitter content related to COVID-19 from Brazil and the USA. Applied Soft Computing 101 (2021), 1–15.Google Scholar
Cross Ref
- E. Cambria. 2016. Affective computing and sentiment analysis. IEEE Intelligent Systems 31, 2, 1541–1672.Google Scholar
Digital Library
- Y. Susanto, B. C. Ng, A. G. Livingstone, and E. Cambria. 2020. The hourglass model revisited. IEEE Intelligent Systems 35, 5 (2020), 96–102.Google Scholar
Cross Ref
- C. Strapparava and A. Valitutti. 2004. WordNet-affect: An affective extension of Wordnet. Proceedings of the Fourth International Conference on Language Resources and Evaluation. 1083–1086.Google Scholar
- E. Cambria, Y. Li, F. Z. Xing, S. Poria, and K. Kwok. 2020. SenticNet 6: Ensemble application of symbolic and subsymbolic AI for sentiment analysis. Proceedings of the 29th ACM International Conference on Information & Knowledge Management (2020), 105–114.Google Scholar
Digital Library
- E. Cambria, S. Poria, A. Gelbukh, and M. Thelwall. 2017. Sentiment analysis is a big suitcase. IEEE Intelligent Systems 32, 6 (2017), 74–80.Google Scholar
Cross Ref
- S. Poria, D. Hazarika, N. Majumder, and R. Mihalcea. 2020. Beneath the tip of the iceberg: Current challenges and new directions in sentiment analysis research. IEEE Transactions on Affective Computing 1, 1 (2020), 1–29.Google Scholar
Digital Library
- A. Agarwal, A. Yadav, and D. K. Vishwakarma. 2019. Multimodal sentiment analysis via RNN variants. 2019 IEEE International Conference on Big Data, Cloud Computing, Data Science & Engineering (BCD). 19–23.Google Scholar
- D. She, J. Yang, M.-M. Cheng, Y.-K. Lai, P. L. Rosin, and L. Wang. 2020. WSCNet: Weakly supervised coupled networks for visual sentiment classification and detection. IEEE Transactions on Multimedia 22, 5 (2020), 1358–1371.Google Scholar
Cross Ref
- A. Yadav, A. Agarwal, and D. K. Vishwakarma. 2019. XRA-net framework for visual sentiments analysis. IEEE Fifth International Conference on Multimedia Big Data (BigMM). 219–224.Google Scholar
- E. Cambria, A. Hussain, and A. Vinciarelli. 2017. Affective reasoning for big social data analysis. IEEE Transactions on Affective Computing 8, 4 (2017), 426–427.Google Scholar
Digital Library
- D. I. H. Farías, V. Patti, and P. Rosso. 2016. Irony detection in Twitter: The role of affective content. ACM Transactions on Internet Technology (TOIT) 16, 3 (2016), 1–24.Google Scholar
Digital Library
- S. Baccianella, A. Esuli, and F. Sebastiani. 2010. Sentiwordnet 3.0: An enhanced lexical resource for sentiment analysis and opinion mining. Proceedings of the Seventh Conference on International Language Resources 10, 10 (2010), 2200–2204.Google Scholar
- G. A. Miller. 1995. WordNet: A lexical database for English. Communications of the ACM 38, 11 (1995), 39–41.Google Scholar
Digital Library
- T. Wilson, P. Hoffmann, S. Somasundaran, J. Kessler, and J. Wiebe. 2005. OpinionFinder: a System for subjectivity analysis. Proceedings of Empirical Methods in Natural Language Processing. 34–35.Google Scholar
- S. L. Lo, E. Cambria, R. Chiong, and D. Cornforth. 2017. Multilingual sentiment analysis: From formal to informal and scarce resource languages. Artificial Intelligence Review 48, 4 (2017), 499–527.Google Scholar
Digital Library
- K. Dashtipour, S. Poria, A. Hussain, E. Cambria, A. Hawalah, A. Gelbukh, and Q. Zhou. 2016. Multilingual sentiment analysis: State of the art and independent comparison of techniques. Cognitive Computation 8, 4 (2016), 757–771.Google Scholar
Cross Ref
- D. Vilares, H. Peng, R. Satapathy, and E. Cambria. 2018. BabelSenticNet: A commonsense reasoning framework for multilingual sentiment analysis. IEEE Symposium Series on Computational Intelligence. 1292–1298.Google Scholar
- W. X. 2008. Using bilingual knowledge and ensemble techniques for unsupervised Chinese sentiment analysis. Proceedings of the Conference on Empirical Methods in Natural Language Processing. 553–561, 2008.Google Scholar
- X. Meng, F. Wei, X. Liu, M. Zhou, G. Xu, and H. Wang. 2012. Cross-lingual mixture model for sentiment classification. Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics 1 (2012) 572–581.Google Scholar
- M. Araújo, A. Pereira, and F. Benevenuto. 2020. A comparative study of machine translation for multilingual sentence-level sentiment analysis. Information Sciences 512 (2020), 1078–1102.Google Scholar
Digital Library
- H. Nankani, H. Dutta, H. Shrivastava, P. V. N. S. Rama Krishna, D. Mahata, and R. R. Shah. 2020. Multilingual sentiment analysis. Deep Learning-Based Approaches for Sentiment Analysis. 193–236.Google Scholar
- A. Yadav and D. Vishwakarma. 2020. A multilingual framework of CNN and Bi-LSTM for emotion classification. 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT) (2020). 1–6.Google Scholar
- T. Mikolov, I. Sutskever, K. Chen, G. Corrado, and J. Dean. 2013. Distributed representations of words and phrases and their compositionality. Advances in Neural Information Processing Systems. 3111–3119.Google Scholar
- Q. Le and T. Mikolov. 2014. Distributed representations of sentences and documents. International Conference on Machine Learning. 1188–1196, 2014.Google Scholar
- J. Pennington, R. Socher, and C. D. Manning. 2014. Glove: Global vectors for word representation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). 1532–1543, 2014.Google Scholar
Cross Ref
- P. Bojanowski, E. Grave, A. Joulin, and T. Mikolov. 2017. Enriching word vectors with subword information. Transactions of the Association for Computational Linguistics 5 (2017), 135–146.Google Scholar
Cross Ref
- S. Ghosh, P. Chakraborty, E. Cohn, J. S. Brownstein, and N. Ramakrishnan. 2016. Characterizing diseases from unstructured text: A vocabulary driven Word2vec approach. Proceedings of the 25th ACM International on Conference on Information and Knowledge Management. 1129–1138, 2016.Google Scholar
- A. Khatua, A. Khatua, and E. Cambria. 2019. A tale of two epidemics: Contextual Word2Vec for classifying Twitter streams during outbreaks. Information Processing and Management 56, 1 (2019), 247–257.Google Scholar
Cross Ref
- A. Sciandra. 2020. COVID-19 outbreak through Tweeters' words: Monitoring Italian social media communication about COVID-19 with text mining and word embeddings. IEEE Symposium on Computers and Communications (ISCC). 1–6.Google Scholar
- C.-K. Wang, O. Singh, Z.-L. Tang, and H.-J. Dai. 2017. Using a recurrent neural network model for classification of tweets conveyed influenza-related information. Proceedings of the International Workshop on Digital Disease Detection using Social Media. 33–38.Google Scholar
- V. Lampos, B. Zou, and I. J. Cox. 2017. Enhancing feature selection using word embeddings: The case of flu surveillance. Proceedings of the 26th International Conference on World Wide Web. 695–704.Google Scholar
- K. Kowsari, K. J. Meimandi, M. Heidarysafa, S. Mendu, L. Barnes, and D. Brown. 2019. Text classification algorithms: A survey. Information 10, 4 (2019).Google Scholar
- K. Denecke and Y. Deng. 2015. Sentiment analysis in medical settings: New opportunities and challenges. Artificial Intelligence in Medicine 64 (2015), 17–27.Google Scholar
Digital Library
- A. Yadav and D. K. Vishwakarma. 2020. A weighted text representation framework for sentiment analysis of medical drug reviews. IEEE Sixth International Conference on Multimedia Big Data (BigMM). 326–332.Google Scholar
- F.-C. Yang, A. J. Lee, and S.-C. Kuo. 2016. Mining health social media with sentiment analysis. Journal of Medical Systems 40, 11 (2016), 1–8.Google Scholar
Digital Library
- S. Sabra, K. M. Malik, and M. Alobaidi. 2018. Prediction of venous thromboembolism using semantic and sentiment analyses of clinical narratives. Computers in Biology and Medicine 94 (2018), 1–10.Google Scholar
Cross Ref
- M. Moh, T. Moh, Y. Peng, and L. Wu. 2017. On adverse drug event extractions using Twitter sentiment analysis. Network Modeling Analysis in Health Informatics and Bioinformatics 6, 1 (2017), 1–12.Google Scholar
Cross Ref
- S. M. Jiménez-Zafra, M. T. Martín-Valdivia, M. D. Molina-González, and L. A. Ureña-López. 2019. How do we talk about doctors and drugs? Sentiment analysis in forums expressing opinions for medical domain. Artificial Intelligence in Medicine 93 (2019), 50–57.Google Scholar
Digital Library
- I. Korkontzelos, A. Nikfarjam, M. Shardlow, A. Sarker, S. Ananiadou, and G. H. Gonzalez. 2016. Analysis of the effect of sentiment analysis on extracting adverse drug reactions from tweets and forum posts. Journal of Biomedical Informatics 62 (2016), 148–158.Google Scholar
Digital Library
- N. Limsopatham and N. Collier. 2016. Normalising medical concepts in social media texts by learning semantic representation. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. 1014–1023.Google Scholar
- H. Grisstte and E. Nfaoui. 2019. Daily life patients sentiment analysis model based on well-encoded embedding vocabulary for related-medication text. IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining. 921–928.Google Scholar
- H. Talpada, M. N. Halgamuge, and N. T. Q. Vinh. 2019. An analysis on use of deep learning and lexical-semantic based sentiment analysis method on Twitter data to understand the demographic trend of telemedicine. 11th International Conference on Knowledge and Systems Engineering (KSE), Vietnam. 1–9.Google Scholar
Cross Ref
- A. Yadav and D. K. Vishwakarma. 2019. Sentiment analysis using deep learning architectures: A review. Artificial Intelligence Review 53, 6 (2019), 4335–4385.Google Scholar
Cross Ref
- M. Mokhlesur Rahman, G. N. Ali, X. J. Li, J. Samuel, K. C. Paul, P. H. Chong, and M. Yakubov. 2021. Socioeconomic factors analysis for COVID-19 US reopening sentiment with Twitter and census data. Heliyon 7, 2 (2021), 1–11.Google Scholar
- S. A. Imran, S. Daudpota, Z. Kastrati, and R. Batra. 2020. Cross-cultural polarity and emotion detection using sentiment analysis and deep learning on COVID-19 related tweets. IEEE Access 8 (2020), 181074–181090.Google Scholar
- A. Alamoodi, B. Zaidan, A. Zaidan, O. Albahri, K. Mohammad, R. Malik, E. Almahdi, M. Chyad, and Z. Tareq. 2021. Sentiment analysis and its applications in fighting COVID-19 and infectious diseases: A systematic review. Expert Systems With Applications, 167, 1–13.Google Scholar
Cross Ref
- H. Jelodar, Y. Wang, R. Orji, and S. Huang. 2020. Deep sentiment classification and topic discovery on novel coronavirus or COVID-19 online discussions: NLP using LSTM recurrent neural network approach. IEEE Journal of Biomedical and Health Informatics 24, 10 (2020), 2733–2742.Google Scholar
Cross Ref
- Z. Yang, D. Yang, C. Dyer, X. He, A. Smola, and E. Hovy. 2016. Hierarchical attention networks for document classification. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego. 1480–1489.Google Scholar
- S. Sukhbaatar, A. Szlam, J. Weston, and R. Fergus. 2015. End-to-end memory networks. Proceedings of the 28th International Conference on Neural Information Processing Systems 2 (2015) 2440–2448.Google Scholar
- A. Yadav and D. K. Vishwakarma. 2020. A comparative study on bio-inspired algorithms for sentiment analysis. Cluster Computing 23, 4 (2020), 2969–2989.Google Scholar
Cross Ref
- S. Hochreiter and J. Schmidhuber. 1997. Long short-term memory. Neural Computation 9, 8 (1997), 1735–1780.Google Scholar
Digital Library
- A. Graves and J. Schmidhuber. 2005. Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Networks 18, 5–6 (2005), 602–610.Google Scholar
Digital Library
- Y. Kim. 2014. Convolutional neural networks for sentence classification. Empirical Methods in Natural Language Processing. 1746–1751.Google Scholar
- S. Lai, L. Xu, K. Liu, and J. Zhao. 2015. Recurrent convolutional neural networks for text classification. Twenty-ninth AAAI Conference on Artificial Intelligence. 2267–2273.Google Scholar
- Z. Lin, M. Feng, C. Nogueira, M. Yu, B. Xiang, B. Zhou, and Y. Bengio. 2017. A structured self-attentive sentence embedding. International Conference on Learning Representations. 2017.Google Scholar
- Y. Wang, A. Sun, J. Han, Y. Liu, and X. Zhu. 2018. Sentiment analysis by capsules. Proceedings of the 2018 World Wide Web Conference. 1165–1174.Google Scholar
- J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT). 4171–4186.Google Scholar
- C. Sievert and K. S. Shirley. 2014. LDAvis: A method for visualizing and interpreting topics. Proceedings of the Workshop on Interactive Language Learning, Visualization, and Interfaces. 63–70.Google Scholar
- K. Stevens, P. Kegelmeyer, D. Andrzejewski, and D. Buttler. 2012. Exploring topic coherence over many models and many topics. Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. 952–961.Google Scholar
- “India to observe 'Janata curfew' on Sunday amid spurt in Coronavirus cases,” [Online]. Available: https://economictimes.indiatimes.com/news/politics-and-nation/india-to-observe-janata-curfew-on-sunday-amid-spurt-in-coronavirus-cases/articleshow/74750784.cms?from=mdr.Google Scholar
- “IPL postponed, India ODIs called off: How coronavirus has rocked cricketing world,” [Online]. Available: https://www.indiatoday.in/sports/story/ipl-2020-postponed-india-vs-south-africa-called-off-coronavirus-impact-on-cric-ket-1655346-2020-03-14.Google Scholar
- “30 Per Cent Of Coronavirus Cases Linked To Delhi Mosque Event: Government,” [Online]. Available: https://www.ndtv.com/india-news/coronavirus-tablighi-jamaat-30-per-cent-of-coronavirus-cases-linked-to-delhi-mosq-ue-event-government-2206163.Google Scholar
- “Mumbai accounts for over 62% cases in Maharashtra: How can worst-hit Indian city stop spread of coronavirus,” [Online]. Available: https://www.indiatoday.in/india/story/mumbai-cases-maharashtra-worst-hit-indian-stop-spread-coronavirus-bmc-commissioner-1682328-2020-05-27.Google Scholar
- “India Climbs To 7th From 9th Spot Among 10 Nations Worst-Hit By COVID-19,” [Online]. Available: https://www.ndtv.com/india-news/india-climbs-to-8th-from-9th-spot-among-10-nations-worst-hit-by-coronavirus-with-over-1-85-lakh-cases-2238310.Google Scholar
- “Sonu Sood, the 'messiah' of migrant workers, bags UN honour,” [Online]. Available: https://www.newindianexpress.com/entertainment/hindi/2020/sep/29/sonu-sood-the-messiah-of-migrant-workers-bags-un-honour-2203485.html#:∼:text=Sood%20helped%20more%20than%2015%2C000,people%20struck%20in%20the%20lockdown.Google Scholar
- “First two cases of coronavirus infection detected in Russia,” [Online]. Available: https://tass.ru/obschestvo/7656549.Google Scholar
- “Moscow mayor orders all residents to stay at home,” [Online]. Available: https://www.business-standard.com/article/pti-stories/moscow-mayor-orders-all-residents-to-stay-at-home-120033000008_1.html.Google Scholar
- “Exclusive: Russia to roll out its first approved COVID-19 drug next week,” [Online]. Available: https://www.reuters.com/article/us-health-coronavirus-russia-exclusive/exclusive-russia-after-approving-japanese-covid-19-drug-to-roll-out-game-changer-next-week-idUSKBN2381FR.Google Scholar
- A. Yadav and D. K. Vishwakarma. 2020. A deep learning architecture of RADLNet for visual sentiment analysis. Multimedia Systems 26 (2020), 431–451.Google Scholar
Cross Ref
- A. Yadav and D. K. Vishwakarma. 2020. A unified framework of deep networks for genre classification using movie trailer. Applied Soft Computing 96, 106624.Google Scholar
Cross Ref
- C. Huang, W. Jiang, J. Wu, and G. Wang. 2020. Personalized review recommendation based on users’ aspect sentiment. ACM Transactions on Internet Technology (TOIT) 20, 4 (2020), 1–26.Google Scholar
Digital Library
Index Terms
A Language-independent Network to Analyze the Impact of COVID-19 on the World via Sentiment Analysis
Recommendations
Social sentiment sensor: a visualization system for topic detection and topic sentiment analysis on microblog
As a new form of social media, microblogging provides platform sharing, wherein users can share their feelings and ideas on certain topics. Bursty topics from microblogs are the results of the emerging issues that instantly attract more followers and ...
Sentiment analysis of COVID-19 cases in Greece using Twitter data
Abstract BackgroundSyndromic surveillance with the use of Internet data has been used to track and forecast epidemics for the last two decades, using different sources from social media to search engine records. More recently, ...
Effects of Microblog Comments on Chinese User's Sentiment with COVID-19 Epidemic Topics
Cross-Cultural Design. Applications in Business, Communication, Health, Well-being, and InclusivenessAbstractSocial media is one of the most significant sources of information in modern people’s life. Due to the large quantity of user base and public opinions, when people read a blog post, the different tendencies of comments may affect their views on ...






Comments