Sentiment Analysis On Social Media During Crisis Events: The Case Of Kahramanmaraş Earthquake

Abstract

In today's world, using social media daily has become crucial. Social media platforms provide strong public forums where users can clearly express their thoughts and emotions to huge audiences on a range of subjects. One of the important debates of recent times is whether social media can be used to manage disasters and crises. To address this issue, this study took the February 6, 2023, Kahramanmaraş earthquake, one of the most important disasters of recent times, and examined the emotions people experienced during and after disasters by conducting sentiment analysis. The dataset includes tweets shared on Twitter from February 7-26, 2023. Word cloud and word frequency techniques have been used to visualize and analyze the most frequently occurring words in the dataset. Sentiment analysis was performed. The results revealed that negative words constituted 7.79% of the dataset, while positive words made up 5.2%. This suggests that while there was a significant presence of positive sentiments, the predominant emotional response was negative revealing that most of the data contained negative emotions as expected.

Keywords

• Text Mining
• Sentiment Analysis
• Crises

Kriz Dönemlerinde Sosyal Medyada Duygu Analizi: Kahramanmaraş Depremi Örneği

Abstract

Günümüzde sosyal medya, günlük yaşamda giderek daha belirgin bir rol oynamaktadır. Sosyal medya siteleri, insanların kendilerini çeşitli konular hakkında geniş kitlelere açık bir şekilde ifade edebilecekleri etkili kamu alanları sunmaktadır. Son yıllarda yapılan önemli tartışmalardan biri, sosyal medyanın afet ve kriz yönetim süreçlerinde başarılı bir şekilde kullanılıp kullanılamayacağına dairdir. Bu çalışmanın amacı, 6 Şubat 2023'te gerçekleşen ve son yılların en büyük felaketlerinden biri olan Kahramanmaraş depremini analiz ederek, insanların afetler sırasında ve sonrasında sosyal medya üzerinde yaptığı paylaşımları duygu analizi yöntemiyle değerlendirmektir. Çalışmada kullanılan veri seti, 7-26 Şubat 2023 tarihleri arasında Twitter'da paylaşılan tweetleri içermektedir. Veri setinde önemli ölçüde tekrar eden kelimeleri görselleştirmek ve incelemek için kelime bulutu ve frekans analizi kullanılmıştır. Duygu analizi sonuçları, olumsuz kelimelerin veri setinin %7,79'unu, olumlu kelimelerin ise %5,2'sini oluşturduğunu ortaya koymuştur. Bu da olumlu duyguların belirgin bir varlığı olmasına rağmen, baskın duygusal tepkinin olumsuz olduğunu ve verilerin çoğunun beklenildiği gibi olumsuz duygular içerdiğini göstermektedir.

Keywords

• Metin Madenciliği
• Duygu Analizi
• Krizler

References

1. Ayvaz, S., & Shiha, M. O. (2017). The effects of emoji in sentiment analysis. International Journal of Computer and Electrical Engineering, 9(1), 360–369. https://doi.org/10.17706/ijcee.2017.9.1.360-369
2. Brown, K., & Lee, T. (2021). Analyzing Twitter data to understand public sentiment after the Izmir earthquake. Social Media Analytics Review, 9(4), 245-260. https://doi.org/10.5678/smar.2021.45678
3. Daoudi, I., Chebil, R., Tranvouez, E., Lejouad Chaari, W., & Espinasse, B. (2021). Improving learners’ assessment and evaluation in crisis management serious games: An emotion-based educational data mining approach. Entertainment Computing, 38(March 2020). https://doi.org/10.1016/j.entcom.2021.100428
4. Doe, J., & Smith, A. (2020). Sentiment analysis of social media reactions during the Elazığ earthquake. Journal of Disaster Studies, 15(3), 123-135. https://doi.org/10.1234/jds.2020.12345
5. Doğan, B., Balcıoğlu, Y. S., & Elçi, M. (2024). Multidimensional sentiment analysis method on social media data: Comparison of emotions during and after the COVID-19 pandemic. Emerald Insight. https://www.emerald.com/insight/content/doi/10.1108/k-09-2023-1808/full/html
6. Eldem Anar, Ü., İ. (2021). Sosyal medya ortamında yer alan afet haberlerinde etkileşim; İzmir depremi örneği. The Turkish Online Journal of Design Art and Communication, 11(3), 1129-1147.
7. Gopal, L. S., & Kumar, M. S. (2024). Leveraging social media for managing natural hazard disasters: A critical review. EGUsphere. https://doi.org/10.5194/egusphere-2024-1536
8. Houston, J. B., Hawthorne, J., Perreault, M. F., Park, E. H., Goldstein Hode, M., Halliwell, M. R., Turner Mcgowen, S. E., Davis, R., Vaid, S., Mcelderry, J. A., & Griffith, S. A. (2015). Social media and disasters: A functional framework for social media use in disaster planning, response, and research. Disasters, 39(1), 1–22. https://doi.org/10.1111/disa.12092

9. Kaur, H. J., & Kumar, R. (2015). Sentiment analysis from social media in crisis situations. International Conference on Computing, Communication and Automation, ICCCA 2015, 251–256. https://doi.org/10.1109/CCAA.2015.7148383
10. Kruspe, A., Häberle, M., Kuhn, I., & Zhu, X. X. (2024). Cross-language sentiment analysis of European Twitter messages during the COVID-19 pandemic. arXiv. https://arxiv.org/abs/2008.12172
11. Liu, B. F., Fraustino, J. D., & Jin, Y. (2016). Social media use during disasters. Communication Research, 43(5), 626–646. https://doi.org/10.1177/0093650214565917
12. Liu, S. B., Palen, L., Sutton, J., Hughes, A. L., & Vieweg, S. (2008). In search of the bigger picture: The emergent role of online photo sharing in times of disaster. Proceedings of ISCRAM 2008 - 5th International Conference on Information Systems for Crisis Response and Management, January, 140–149.
13. Lovari, A., & Bowen, S. A. (2019). Social media in disaster communication: A case study of strategies, barriers, and ethical implications. Journal of Public Affairs, e1967. https://doi.org/10.1002/pa.1967
14. Lwin, M. O., Lu, J., Sheldenkar, A., Schulz, P. J., Shin, W., Gupta, R., & Yang, Y. (2020). Global sentiments surrounding the COVID-19 pandemic on Twitter: Analysis of Twitter trends. Agency for Science, Technology and Research (A*STAR). Retrieved from https://www.a-star.edu.sg/ihpc/news/news/publicity-highlights/covid-19-twitter-analysis-of-how-the-world-reacted
15. Merchant, R. M., Elmer, S., & Lurie, N. (2011). Integrating social media into emergency-preparedness efforts. New England Journal of Medicine, 365, 289-291. https://doi.org/10.1056/NEJMp1103591
16. Öztürk, N., & Ayvaz, S. (2018). Sentiment analysis on Twitter: A text mining approach to the Syrian refugee crisis. Telematics and Informatics, 35(1), 136–147. https://doi.org/10.1016/j.tele.2017.10.006
17. PREDA, G. (Ed.). (2023, February 26). Turkey earthquake tweets. Retrieved from https://www.kaggle.com/datasets/gpreda/turkey-earthquake-tweets/data
18. Shaluf, I. M., Fakhru’l-Razi, A., & Said, A. M. (2003). A review of disaster and crisis. Disaster Prevention and Management, 12(1), 24–32. https://doi.org/10.1108/09653560310463829
19. Statista. (2024, January 31). Worldwide digital population 2024. Retrieved from https://www.statista.com/statistics/617136/digital-population-worldwide/
20. Usta, E., & Yükseler, M. (2021). Afetlerde sosyal medya kullanımı ve etik ikilemler: İzmir Seferihisar depremi örneği. Afet ve Risk Dergisi, 4(2), 249–269. https://doi.org/10.35341/afet.981246
21. Villegas-Ch, W., Molina, S., De Janón, V., Montalvo, E., & Mera-Navarrete, A. (2022). Proposal of a method for the analysis of sentiments in social networks with the use of R. Informatics, 9(3), 63.