COVID-19 Aşıları için Türkçe Tweetlerle Duygu Analizi

Abstract

Zamanın ve teknolojinin gereksinimleri ile “Web” anlamsal ve akıllı teknolojilerle dönüşüme uğramış ve kullanıcıların aktif olarak içerik yaratabildiği, herhangi bir konuda görüşlerini ifade edebildiği çok yönlü sanal interaktif bir platform haline gelmiştir. Bu platformlardan biri olan sosyal medya sayesinde bilgi ve fikirlerin yayılması kolaylaşmıştır. Günümüzde sosyal medya platformlarında üretilen veriler metin madenciliği yöntemleri sayesinde basit, hızlı ve etkili bir şekilde analiz edilebilmektedir. Analiz sonuçları satış tahminleri, pazarlama, çevre, sağlık, toplumun duygu ve düşüncelerini saptama gibi birçok alanda kullanılmaktadır. Bu noktadan hareketle, bu çalışmada COVID-19 global hastalığı için geliştirilen Sinovac ve Biontech aşıları için Twitter kullanıcılarının paylaştıkları tweet’ler üzerine zamansal duygu analizi yapılmış ve sonuçlar karşılaştırılmıştır. Böylece aşıların insanlar üzerindeki olumlu ya da olumsuz etkileri ortaya çıkarılmıştır. Sonuçta aşı olan ya da olmayan insanların aşılara karşı duyguları ölçülmüş, aşıların olumlu ya da olumsuz etkilerinin değerlendirilmesi amaçlanmıştır. Analiz sonuçlarına göre, insanların çoğunlukla aşılardan memnun olduğu görülmektedir. Ancak nüfusun bir kısmının endişe ve korku duyması, aşıların insanlar üzerindeki etkisinin olumsuz taraflarını da yansıtmaktadır. Bu çalışma farklı aşı veya medikal tedavi türleri için de uyarlanıp insanlar için yol gösterici olabilir.

Keywords

• Metin madenciliği
• Tweet analizi
• Duygu analizi
• COVID-19 aşıları
• Pandemi

Sentiment Analysis with Turkish Tweets for COVID-19 Vaccines

Abstract

With the requirements of time and technology, the "Web" has been transformed by semantic and smart technologies and has become a versatile virtual interactive platform where users can actively create content and express their opinions on any subject. Thanks to social media, which is one of these platforms, the dissemination of information and ideas has become easier. Today, data produced on social media platforms can be analyzed simply, quickly and effectively thanks to text mining methods. Analysis results are used in many areas such as sales forecasts, marketing, environment, health, and determining the feelings and thoughts of the society. From this point of view, in this study, a temporal sentiment analysis was performed on the tweets shared by Twitter users for the Sinovac and Biontech vaccines developed for the COVID-19 global disease, and the results were compared. Thus, the positive or negative effects of vaccines on humans have been revealed. As a result, the feelings of people who have or have not been vaccinated against vaccines were measured, and it was aimed to evaluate the positive or negative effects of vaccines. According to the results of the analysis, it is seen that people are mostly satisfied with the vaccines. However, the anxiety and fear of a part of the population also reflects the negative aspects of the impact of vaccines on humans. This study can be adapted for different types of vaccines or medical treatments and may guide people.

Keywords

• Text mining
• Tweet analysis
• Sentiment analysis
• COVID-19 vaccines
• Pandemic

References

1. [1] “Instagram,” [Online]. Available: https://www.instagram.com/.
2. [2] “Facebook,” [Online]. Available: https://www.facebook.com/.
3. [3] “Twitter,” [Online]. Available: https://twitter.com/.
4. [4] R. Feldman and J. Sanger, “The Text Mining Handbook”, Advanced Approaches in Analyzing Unstructured Data, Cambridge University Press, 2006.
5. [5] R. Dehkharghani, Y. Saygin, B. Yanikoglu and K. Oflazer, “SentiTurkNet: a Turkish polarity lexicon for sentiment analysis”, Lang Resources & Evaluation, 50:667–685, 2016.
6. [6] S. Baccianella, A. Esuli, F. Sebastiani, “SENTIWORDNET 3.0: An Enhanced Lexical Resource for Sentiment Analysis and Opinion Mining”, Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), May, Valletta, Malta, 2010.
7. [7] E. Cambria, D. Olsher, D. Rajagopal, “VSenticNet 3: A Common and Common-Sense Knowledge Base for Cognition-Driven Sentiment Analysis”, July, Conference: AAAI, 2014.
8. [8] S. M. Mohammad and P. D. Turney, “Crowdsourcing a word-emotion association lexicon”, Computational Intelligence, 29(3), 436–465. 2013.

9. [9] M. Özcelik, N. B. Arıcan, Ö. Bakay, E. Sarmış, G. N. Bayazıt, Ö. Ergelen ve T. O. Yıldız, “HisNet: A Polarity Lexicon based on WordNet for Emotion Analysis”, In Proceedings of the 11th Global Wordnet Conference, pages 157–165, University of South Africa (UNISA). Global Wordnet Association, 2021.
10. [10] S. S. Sharma and G. Dutta, “SentiDraw: Using star ratings of reviews to develop domain specific sentiment lexicon for polarity determination”, Information Processing and Management 58 (2021) 102412, 2021.
11. [11] R. Dehkharghani, “SentiFars: A Persian Polarity Lexicon for Sentiment Analysis”, ACM Trans. Asian Low-Resour. Lang. Inf. Process. 19, 2, Article 21, 12 pages, September, 2019.
12. [12] “Emotion Ontology”, [Online]. Available: https://bioportal.bioontology.org/ontologies/MFOEM.
13. [13] M. Dragoni, S. Poria, E. Cambria, “OntoSenticNet: A Commonsense Ontology for Sentiment Analysis”, IEEE Intelligent Systems, May/June, p.77-85, 2018.
14. [14] B. Pang, L. Lee and S. Vaithyanathan, “Thumbs up? Sentiment classification using machine learning techniques”, In: Proceedings of the ACL-02 conference on empirical methods in natural language processing-Volume 10 (pp. 79–86), Association for Computational Linguistics, 2002.
15. [15] A. Xie. Agarwal, B. Vovsha, I. O. Rambow and R. Passonneau, “Sentiment analysis of Twitter data”, In: Proceedings of the workshop on languages in social media Association for Computational Linguistics, (pp. 30–38), 2011.
16. [16] S. M. Başarslan ve F. Kayaalp, “Sentiment Analysis with Machine Learning Methods on Social Media”, ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal Regular Issue, Vol. 9, N. 3 (2020), 5-15, 2020.
17. [17] F. Fang Yao, Y. Wang, “Domain-specific sentiment analysis for tweets during hurricanes (DSSA-H): A domain-adversarial neural-network-based approach”, Computers, Environment and Urban Systems 83 (2020) 101522, 2020.
18. [18] N. Mukhtar, A. M. Khan, N. Chiragh, “Lexicon-based approach outperforms Supervised Machine Learning approach for Urdu Sentiment Analysis in multiple domains”, Telematics and Informatics, 35 (2018) 2173–2183, 2018.
19. [19] D. Michailidis, N. Stylianou and I. Vlahavas, “Real Time Location Based Sentiment Analysis on Twitter - The AirSent System”, In SETN ’18: 10th Hellenic Conference on Artificial Intelligence, July 9–15, 2018, Rio Patras, Greece. ACM, New York, NY, USA, Article 4, 4 pages. https: //doi.org/10.1145/3200947.3201052, 2018.
20. [20] S. Saran, L. Singla & P. Singh, “Twitter analytics for integrated research in biodiversity”, Asian conference on remote sensing. In Proceedings of the 40th Asian Conference on Remote Sensing ACRS, 2019.
21. [21] M. Albayrak, K. Topal ve V. Altıntaş, “Sosyal Medya Üzerinde Veri Analizi: Twitter”, Süleyman Demirel Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, C.22, Kayfor 15 Özel Sayısı, s.1991-1998, 2017.
22. [22] M. G. Almatar, H. S. Alazmi, L. Li and E. A. Fox, “Applying GIS and Text Mining Methods to Twitter Data to Explore the Spatiotemporal Patterns of Topics of Interest in Kuwait”, ISPRS Int. J. Geo-Inf., 9, 702; 2020, doi:10.3390/ijgi9120702.
23. [23] Z Song and J. Xia, “Spatial and Temporal Sentiment Analysis of Twitter data”, In: Capineri, C, Haklay, M, Huang, H, Antoniou, V, Kettunen, J, Ostermann, F and Purves, R. (eds.) European Handbook of Crowdsourced Geographic Information, Pp. 205–221, 2016, London: Ubiquity Press. DOI: http://dx.doi.org/10.5334/bax.p. License: CC-BY 4.0
24. [24] M. Häberle, M. Wernerb and X. X. Zhua, “Geo-spatial text-mining from Twitter – a feature space analysis with a view toward building classification in urban regions”, European Journal of Remote Sensing 2019, Vol. 52, No. S2,2–11, https://doi.org/10.1080/22797254.2019.1586451, 2019.
25. [25] S. Alowaidi, M. Saleh, O. Abulnaja, “Semantic Sentiment Analysis of Arabic Texts”, (IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 8, No. 2. 2017.
26. [26] B. Resch, F. Usländer and C. Havas, “Combining machine learning topic models and spatiotemporal analysis of social media data for disaster footprint and damage assessment”, Cartography and Geographic Information Science, 45:4, 362-376, 2018, DOI: 10.1080/15230406.2017.1356242.
27. [27] L. Tavoschi, F. Quattrone, E. D’Andrea, P. Ducange, M. Vabanesi, F. Marcelloni and L. P. Lopalco, “Twitter as a sentinel tool to monitor public opinion on vaccination: an opinion mining analysis from September 2016 to August 2017 in Italy”, Human Vaccines & Immunotherapeutics, 16:5, 1062-1069, 2020, DOI: 10.1080/21645515.2020.1714311.
28. [28] L. Nemes and A. Kiss, “Social media sentiment analysis based on COVID-19”, Journal of Information and Telecommunication”, 5:1, 1-15, DOI: 10.1080/24751839.2020.1790793, 2021.
29. [29] A. Beşkirli, E. Gülbandılar ve E. Dağ, “Metin Madenciliği Yöntemleri ile Twitter Verilerinden Bilgi Keşfi”, ESTUDAM Bilişim Dergisi, Cilt 2, Sayı 1, 21-25, 2021.
30. [30] Çakmak, E. T., & Oğuzlar, A. (2022). Sosyal Medyada Duygu Analizi: COVID-19 Sürecinde 5G Algısı. International Journal of Social Inquiry, 15(1), 55-68.
31. [31] Aygün, I., Kaya, B., & Kaya, M. (2021). Aspect based twitter sentiment analysis on vaccination and vaccine types in covid-19 pandemic with deep learning. IEEE Journal of Biomedical and Health Informatics, 26(5), 2360-2369.
32. [32] C. J. Lyu, L. E. Han, K. G. Luli, “COVID-19 Vaccine–Related Discussion on Twitter: Topic Modeling and Sentiment Analysis”, J Med Internet Res 2021, 23(6), e24435, 2021.
33. [33] S. Liu and J. Liu, “Public attitudes toward COVID-19 vaccines on English-language Twitter: A sentiment analysis”, Vaccine 39 (2021) 5499–5505, 2021.
34. [34] Marcec, R., & Likic, R. (2022). Using twitter for sentiment analysis towards AstraZeneca/Oxford, Pfizer/BioNTech and Moderna COVID-19 vaccines. Postgraduate medical journal, 98(1161), 544-550.
35. [35] Å. F. Nielsen, “A new anew: evaluation of a word list for sentiment analysis in microblogs”, CEUR Workshop Proc 2011;718:93–8, 2011.
36. [36] C. Villavicencio, J. J. X. Macrohon, X. A. Inbaraj, J. H. Jeng, J. G. Hsieh, “Twitter Sentiment Analysis towards COVID-19 Vaccines in the Philippines Using Naïve Bayes”, Information, 12, 204, 2021, https://doi.org/10.3390/info12050204.
37. [37] Ansari, M. T. J., & Khan, N. A. (2021). Worldwide COVID-19 Vaccines Sentiment Analysis Through Twitter Content. Electronic Journal of General Medicine, 18(6).
38. [38] Çılgın, C., Gökçen, H., & Gökşen, Y. (2022). Twitter’da COVID-19 aşılarına karşı kamu duyarlılığının çoğunluk oylama sınıflandırıcısı temelli makine öğrenmesi ile duygu analizi. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, 38(2), 1093-1104.
39. [39] Aslan, S. (2022). BiGRU-CNN Tabanlı Derin Öğrenme Modeliyle Türkiye’deki Covid-19 Aşılarına Yönelik Twitter Duygu Analizi. International Journal of Pure and Applied Sciences, 8(2), 312-330.
40. [40] Mermer, G., & Özsezer, G. (2023). Discussions About COVID-19 Vaccination on Twitter in Turkey: Sentiment Analysis. Disaster Medicine and Public Health Preparedness, 17, e266.
41. [41] “Covid19,” [Online]. Available: https://covid19.saglik.gov.tr/.
42. [42] “WHO,” [Online]. Available: https://www.who.int/publications/m/item/weekly-epidemiological-update-on-covid-19---1-september-2023
43. [43] T. Jo, “Text Mining Concepts, Implementation, and Big Data Challenge”, Studies in Big Data, Springer, Volume 45, ISBN 978-3-319-91814-3, https://doi.org/10.1007/978-3-319-91815-0. 2019.
44. [44] X. Wu, X. Zhu, G. Wu and W. Ding, “Data Mining with Big Data”, IEEE Transactions On Knowledge And Data Engineering, Vol. 26, No. 1, 2014.
45. [45] G. Salton, C.S. Yang, “On the specification of term values in automatic indexing”. J. Doc. 29, 351–372, 1973.
46. [46] “Wordnet,” [Online]. Available: https://wordnet.princeton.edu/.
47. [47] “Orange,” [Online]. Available: https://orangedatamining.com/.
48. [48] J. Demšar and B. Zupan, “Orange: Data Mining Fruitful And Fun”, Proceedings of the 15th International Multiconference, Informatıon Socıety-IS, Volume A, 2012.
49. [49] M. Hu and B. Liu, “Mining and Summarizing Customer Reviews”, KDD’04, August 22–25, Seattle, Washington, USA, 2004.
50. [50] C. J. Hutto, E. Gilbert, “VADER: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text”, Proceedings of the Eighth International AAAI Conference on Weblogs and Social Media, Michigan, USA, June 1–4, 2014.