Decision Support System for Natural Disaster Response Process with Twitter Data

Abstract

In the natural disaster response process, the use of limited resources in place and on time is very important in limiting the loss of life and property. Disaster coordination centers are established in order to respond to the disaster in a timely manner and to manage the allocation of resources. During a disaster, individuals and institutions share live information on social media. Fast and accurate transmission of the shared information to the response teams will benefit the coordination of the effort. For this purpose, in this study, a decision support system that generates alerts via SMS and e-mail by processing the tweets published on Twitter with text mining has been introduced. By the decision support system, a content analysis was made for each tweet obtained from Twitter, and along with the location, date and time information, risk scores were calculated. With risk scores renewed every hour, warnings have been created for locations with high scores. In the study, the application of the decision support system was demonstrated with more than 120,000 tweets shared during the forest fires in Manavgat, Marmaris and Milas in July and August 2021. The application showed that high risk scores are created for places that were heavily affected by the fire, such as Marmaris Hisarönü and Milas Çökertme.

Keywords

• Natural Disaster Management
• Data Management
• Data Mining
• Decision Support Systems

Twitter Verisi İle Doğal Afet Müdahale Süreci İçin Karar Destek Uygulaması

Öz

Doğal afetlere müdahale sürecinde kısıtlı kaynakların yerinde ve zamanında kullanılması can ve mal kaybını sınırlamada çok önemlidir. Afete zamanında müdahale etmek ve kaynakları sevkini yönetmek amaçlarıyla afet koordinasyon merkezleri oluşturulur. Afet sırasında, bireyler ve kurumlar sosyal medya üzerinden anlık bilgi verici paylaşımlar yapılmaktadır. Paylaşılan bilginin hızlı ve doğru şekilde afet koordinasyon ekiplerine iletilmesi, ekiplerin yönetimine fayda sağlayacaktır. Bu amaçla, bu çalışmada Twitter üzerinden yapılan paylaşımları metin madenciliği ile işleyerek, SMS ve e-posta ile uyarı oluşturan bir karar destek sistemi tanıtılmıştır. Karar destek sistemi tarafından, Twitter’dan elde edilen her tweet için yer, tarih ve saat bilgisiyle birlikte, içerik analizi yapılmış ve risk puanı hesaplanmıştır. Her saat yenilenen risk puanlarıyla, kritik durumdaki lokasyonlar için uyarı oluşturulmuştur. Çalışmada, 2021 Temmuz ve Ağustos aylarında Manavgat, Marmaris ve Milas’ta çıkan orman yangınları sırasında paylaşılan 120,000’den fazla tweet ile karar destek sisteminin uygulaması gösterilmiştir. Uygulamada, Marmaris Hisarönü, Milas Çökertme gibi yangından çok etkilenen yerler için yüksek risk puanının oluşturulduğu görülmüştür.

Anahtar Kelimeler

• Doğal Afet Yönetimi
• Veri Yönetimi
• Veri Madenciliği
• Karar Destek Sistemleri

Kaynakça

1. Akkaş, S. (2022). Orman Yangınlarına Müdahalede Bir Yılda Neler Değişti?
2. Alam, F., Ofli, F., Imran, M., & Aupetit, M. (2018). A Twitter Tale of Three Hurricanes: Harvey, Irma, and Maria. Proceedings of the International ISCRAM Conference, 2018-May, 553-572. http://arxiv.org/abs/1805.05144
3. Ali Taha, V., Pencarelli, T., Škerháková, V., Fedorko, R., & Košíková, M. (2021). The Use of Social Media and Its Impact on Shopping Behavior of Slovak and Italian Consumers during COVID-19 Pandemic. Sustainability, 13(4), 1710. https://doi.org/10.3390/su13041710
4. Avcı, M., & Korkmaz, M. (2020). Türkiye’de orman yangını sorunu: Güncel bazı konular üzerine değerlendirmeler. Turkish Journal of Forestry | Türkiye Ormancılık Dergisi, 229-240. https://doi.org/10.18182/tjf.942706
5. Bai, X. (2011). Predicting consumer sentiments from online text. Decision Support Systems, 50(4), 732-742. https://doi.org/10.1016/j.dss.2010.08.024
6. Barzenji, H. (2021). Sentiment analysis of Twitter texts using Machine learning algorithms. Academic Platform Journal of Engineering and Science, 9(3), 460-471. https://doi.org/10.21541/apjes.939338
7. Beşkirli, A., Gülbandılar, E., & Dağ, İ. (2021). Metin Madenciliği Yöntemleri ile Twitter Verilerinden Bilgi Keşfi. Journal of ESTUDAM Information, 2(1), 21-25.
8. Bhardwaj, F., Arora, P., & Agrawal, G. (2021). Text Mining Using Twitter Data (ss. 29-49). https://doi.org/10.4018/978-1-7998-7728-8.ch002

9. Broersma, M., & Graham, T. (2013). TWITTER AS A NEWS SOURCE. Journalism Practice, 7(4), 446-464. https://doi.org/10.1080/17512786.2013.802481
10. Canbolat, Z. N., & Pinarbasi, F. (2020). Augmented Reality and Mobile Consumers: Mining Reviews of AR Applications for Consumer Perceptions. Içinde In Managerial Challenges and Social Impacts of Virtual and Augmented Reality (ss. 76-94). IGI Global.
11. Clement, J. (2022). Leading countries based on number of Twitter users as of October 2020. https://www.statista.com/statistics/242606/number-of-active-twitter-users-in-selected-countries/
12. Dastanwala, P. B., & Patel, V. (2016). A review on social audience identification on twitter using text mining methods. 2016 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET), 1917-1920. https://doi.org/10.1109/WiSPNET.2016.7566476
13. Eirinaki, M., Pisal, S., & Singh, J. (2012). Feature-based opinion mining and ranking. Journal of Computer and System Sciences, 78(4), 1175-1184. https://doi.org/10.1016/j.jcss.2011.10.007
14. Feinerer, I., & Hornik, K. (2020). tm: Text Mining Package. R package version 0.7-7. https://CRAN.R-project.org/package=tm
15. Ghazouani, D., Lancieri, L., Ounelli, H., & Jebari, C. (2019). Assessing Socioeconomic Status of Twitter Users: A Survey. Proceedings - Natural Language Processing in a Deep Learning World, 388-398. https://doi.org/10.26615/978-954-452-056-4_046
16. Guo, J., Xu, L. da, Xiao, G., & Gong, Z. (2012). Improving Multilingual Semantic Interoperation in Cross-Organizational Enterprise Systems Through Concept Disambiguation. IEEE Transactions on Industrial Informatics, 8(3), 647-658. https://doi.org/10.1109/TII.2012.2188899
17. Hung, J. (2012). Trends of e-learning research from 2000 to 2008: Use of text mining and bibliometrics. British Journal of Educational Technology, 43(1), 5-16. https://doi.org/10.1111/j.1467-8535.2010.01144.x
18. Ingvaldsen, J. E., & Gulla, J. A. (2012). Industrial application of semantic process mining. Enterprise Information Systems, 6(2), 139-163. https://doi.org/10.1080/17517575.2011.593103
19. Jahanbin, K., Rahmanian, F., & and, V. R.-G. H. (2019). Application of Twitter and web news mining in infectious disease surveillance systems and prospects for public health. GMS Hygiene and Infection Control, 14(19). https://doi.org/10.3205/dgkh000334
20. Jockers, M. L. (2021). Syuzhet: Extract Sentiment and Plot Arcs from Text. https://github.com/mjockers/syuzhet
21. Kapidzic, S., Neuberger, C., Frey, F., Stieglitz, S., & Mirbabaie, M. (2022). How News Websites Refer to Twitter: A Content Analysis of Twitter Sources in Journalism. Journalism Studies, 1-22. https://doi.org/10.1080/1461670X.2022.2078400
22. Kebabci, K., & Karsligil, M. E. (2015). High priority tweet detection and summarization in natural disasters. 2015 23nd Signal Processing and Communications Applications Conference (SIU), 1280-1283. https://doi.org/10.1109/SIU.2015.7130072
23. Khadjeh Nassirtoussi, A., Aghabozorgi, S., Ying Wah, T., & Ngo, D. C. L. (2014). Text mining for market prediction: A systematic review. Expert Systems with Applications, 41(16), 7653-7670. https://doi.org/10.1016/j.eswa.2014.06.009
24. Meystre, S. M., Savova, G. K., Kipper-Schuler, K. C., & Hurdle, J. F. (2008). Extracting Information from Textual Documents in the Electronic Health Record: A Review of Recent Research. Yearbook of Medical Informatics, 17(01), 128-144. https://doi.org/10.1055/s-0038-1638592
25. Murat Kırık, A. (2014). A Research on Social and Political Use of Social Media in Turkey. International Journal of Science Culture and Sport, 2(8), 49-49. https://doi.org/10.14486/IJSCS207
26. Netzer, O., Feldman, R., Goldenberg, J., & Fresko, M. (2012). Mine Your Own Business: Market-Structure Surveillance Through Text Mining. Marketing Science, 31(3), 521-543. https://doi.org/10.1287/mksc.1120.0713
27. Porter, M. F. (1980). An algorithm for suffix stripping. Program, 14(3), 130-137. https://doi.org/10.1108/eb046814
28. Quadri, G. O., & Adebayo Idowu, O. (2016). Social Media Use by Librarians for Information Dissemination in Three Federal University Libraries in Southwest Nigeria. Journal of Library & Information Services in Distance Learning, 10(1-2), 30-40. https://doi.org/10.1080/1533290X.2016.1156597
29. Ravindran, S., & Garg, V. (2015). Mastering social media mining with R. Packt Publishing.
30. Reategui, E., Epstein, D., Lorenzatti, A., & Klemann, M. (2011). Sobek: a Text Mining Tool for Educational Applications. Proceedings International Conference on Data Mining (DMIN, 59-64.
31. Romero, C., & Ventura, S. (2007). Educational data mining: A survey from 1995 to 2005. Expert Systems with Applications, 33(1), 135-146. https://doi.org/10.1016/j.eswa.2006.04.005
32. Shin, N., Maruya, Y., Saitoh, T. M., & Tsutsumida, N. (2021). Usefulness of Social Sensing Using Text Mining of Tweets for Detection of Autumn Phenology. Frontiers in Forests and Global Change, 4. https://doi.org/10.3389/ffgc.2021.659910
33. Silahtaroğlu, G., Baykal, E., & Canbolat, Z. N. (2020). Covıd-19 Salgınında Yaşanan Haftalık Duygusal Değişimler: Türkiye Örneği. Ekonomi İşletme ve Maliye Araştırmaları Dergisi, 280-304. https://doi.org/10.38009/ekimad.825285
34. Silge, J., & Robinson, D. (2016). tidytext: Text Mining and Analysis Using Tidy Data Principles in R. The Journal of Open Source Software, 1(3), 37. https://doi.org/10.21105/joss.00037
35. Temizhan, E., & Mendeş, M. (2021). Evaluation of Twitter Messages Related to COVID-19 Pandemic Using Text Mining Technique. Turkiye Klinikleri Journal of Biostatistics, 13(2), 185-200. https://doi.org/10.5336/biostatic.2020-79992
36. Tsantis, L., & Castellani, J. (2001). Enhancing Learning Environments through Solution-Based Knowledge Discovery Tools: Forecasting for Self-perpetuating Systemic Reform. Journal of Special Education Technology, 16(4), 39-52. https://doi.org/10.1177/016264340101600406
37. Twitter API. (2022). https://developer.twitter.com/en/docs/twitter-api
38. Wetzstein, B., Leitner, P., Rosenberg, F., Dustdar, S., & Leymann, F. (2011). Identifying influential factors of business process performance using dependency analysis. Enterprise Information Systems, 5(1), 79-98. https://doi.org/10.1080/17517575.2010.493956
39. Wickham, H., François, R., Henry, L., & Müller, K. (2022). dplyr: A Grammar of Data Manipulation. R package version 1.0.2. https://CRAN.R-project.org/package=dplyr
40. Williams, M. L., Burnap, P., & Sloan, L. (2017). Towards an Ethical Framework for Publishing Twitter Data in Social Research: Taking into Account Users’ Views, Online Context and Algorithmic Estimation. Sociology, 51(6), 1149-1168. https://doi.org/10.1177/0038038517708140
41. Yang, S., & Zhang, haiyi. (2018). Text Mining of Twitter Data Using a Latent Dirichlet Allocation Topic Model and Sentiment Analysis.
42. Yeşilyurt, A., & Şeker, S. E. (2017). Metin Madenciliği Yöntemleri ile Twitter Duygu Analizi. YBS Ansiklopedisi, 4(2).
43. Zhu, F., Patumcharoenpol, P., Zhang, C., Yang, Y., Chan, J., Meechai, A., Vongsangnak, W., & Shen, B. (2013). Biomedical text mining and its applications in cancer research. Journal of Biomedical Informatics, 46(2), 200-211. https://doi.org/10.1016/j.jbi.2012.10.007
44. Zou, L., Lam, N. S. N., Cai, H., & Qiang, Y. (2018). Mining Twitter Data for Improved Understanding of Disaster Resilience. Annals of the American Association of Geographers, 108(5), 1422-1441. https://doi.org/10.1080/24694452.2017.1421897