Twitter Data Analysis: Izmir Earthquake Case

Abstract

Türkiye is located on a fault line; earthquakes often occur on a large and small scale. There is a need for effective solutions for gathering current information during disasters. We can use social media to get insight into public opinion. This insight can be used in public relations and disaster management. In this study, Twitter posts on İzmir Earthquake that took place on October 2020 are analyzed. We question if this analysis can be used to make social inferences on time. Data mining and natural language processing (NLP) methods are used for this analysis. NLP is used for sentiment analysis and topic modelling. The latent Dirichlet Allocation (LDA) algorithm is used for topic modelling. We used the Bidirectional Encoder Representations from Transformers (BERT) model working with Transformers architecture for sentiment analysis. It is shown that the users shared their goodwill wishes and aimed to contribute to the initiated aid activities after the earthquake. The users desired to make their voices heard by competent institutions and organizations. The proposed methods work effectively. Future studies are also discussed.

Keywords

• Exploratory Data Analysis
• Text Pre-Processing
• Disaster Management
• Natural Language Processing
• Social Media Analysis

References

1. A.C Yalciner, et al. "The 30 October 2020 (11: 51 UTC) Izmir-Samos earthquake and tsunami: post-tsunami field survey preliminary results", in Middle East Technical University, Ankara, Turkey, 2020.
2. A. Bovet, F. Morone and H. A. Makse, "Validation of Twitter opinion trends with national polling aggregates: Hillary Clinton vs Donald Trump", Scientific reports, 2018, 8(1): 1-16.
3. S. Gurajala, S Dhaniyala., and J. N. Matthews, "Understanding public response to air quality using tweet analysis", Social Media+ Society, 2019, 5(3).
4. N. Kankanamge, T. Yigitcanlar, A. Goonetilleke and M. Kamruzzaman, "Determining disaster severity through social media analysis: Testing the methodology with South East Queensland Flood tweets", International journal of disaster risk reduction 2020, 42: 101360.
5. N. Pourebrahim, S. Sultana, J. Edwards, A. Gochanour, and S. Mohanty, "Understanding communication dynamics on Twitter during natural disasters: A case study of Hurricane Sandy", International journal of disaster risk reduction, 2019, 37: 101176.
6. A. Ceron, L. Curini, S.M. Iacus and G. Porro, "Every tweet counts? How sentiment analysis of social media can improve our knowledge of citizens", political preferences with an application to Italy and France. New media and society, 2014, 16(2): 340-358.
7. V. Kharde and P. Sonawane, "Sentiment analysis of twitter data: a survey of techniques", arXiv preprint arXiv:1601.06971, 2016.
8. A. Shelar, C.Y. Huang, "Sentiment analysis of twitter data", In: 2018 International Conference on Computational Science and Computational Intelligence (CSCI). IEEE, 2018. p. 1301-1302.

9. M. Albayrak, K.topal and V. Altıntaş, "Sosyal medya üzerinde veri analizi: Twitter", Süleyman Demirel Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 2017, 22(Kayfor 15 Özel Sayısı): 1991-1998.
10. A. Karami, V. Shah, R. Vaezi and A. Bansal, "Twitter speaks: A case of national disaster situational awareness", Journal of Information Science, 2020, 46(3): 313-324.
11. K. Zahra, M. Imran, and F. O. Ostermann, "Automatic identification of eyewitness messages on twitter during disasters", Information processing management, 2020, 57(1): 102107.
12. F. Dalkılıç¸ , A. Çam, "Automatic Movie Rating by Using Twitter Sentiment Analysis and Monitoring Tool", Journal of Emerging Computer Technologies, 2021, 1(2): 55-60.
13. Ö. Ağralı, Ö. Aydın, "Tweet Classification and Sentiment Analysis on Metaverse Related Messages", Journal of Metaverse, 2021, 1(1): 25-30.
14. S. Yıldırım, savasy/bert-base-turkish-sentiment-cased · Hugging Face, 2020. [Online]. Available: https://huggingface.co/savasy/bert-baseturkish-sentiment-cased. [Accessed: 02- Nov- 2020].
15. B. Ayhan, winvoker/turkish-sentiment-analysisdataset Hugging Face, 2022. [Online]. Available: https://huggingface.co/datasets/winvoker/turkish-sentiment-analysisdataset. [Accessed: Nov- 2022].
16. "İşte birçok kişiye mezar olan Rıza Bey apartmanı", 2020. [Online]. Available: https://www.turkiyegazetesi.com.tr/gundem/742966.aspx. [Accessed: Oct. 30, 2020].
17. T. Albay, "İzmir’de deprem sonrası yıkılan Rıza Bey Apartmanı enkazındaki kurtarma çalışmasına ara verildi", 2020. [Online]. Available: https://www.aa.com.tr/tr/turkiye/izmirde-deprem-sonrasi-yikilan-rizabey-apartmani-enkazindaki-kurtarma-calismasina-ara-verildi-/2027207. [Accessed: 01- Nov- 2020].
18. T. Albay, "İzmir’deki depremden yaklaşık 58 saat sonra 14 yaşındaki İdil enkazdan yaralı çıkarıldı", 2020. [Online]. Available: https://www.aa.com.tr/tr/turkiye/izmirdeki-depremden-yaklasik-58-saatsonra-14-yasindaki-idil-enkazdan-yarali-cikarildi/2027463. [Accessed: 02- Nov- 2020].
19. "Son dakika: 3 yaşındaki Ayda bebek 91’inci saatte enkazdan çıkarıldı", 2020. [Online]. Available: https://www.haberturk.com/son-dakikahaberi-tunc-soyer-acikladi-ekipleri-bir-bebege-canli-ulasti-2857124. [Accessed: 03-Nov-2020].
20. "İzmir depremi: Arama kurtarma çalışmaları sona erdi, can kaybı 114’e yükseldi", 2020. [Online]. Available: https://www.bbc.com/turkce/haberler-turkiye-54810440. [Accessed:04- Nov- 2020].
21. L. İlhan "İzmir’de deprem", 2020. [Online]. Available: https://www.aa.com.tr/tr/pg/foto-galeri/izmir-de-deprem/0. [Accessed: 30- Oct- 2020].