Veri Madenciliği Uygulamalarının Web Tabanlı Mekânsal Görsel Analitik Ortamda Sunumu: COVID-19 Aşı Tweet’leri Örneği

Mekânsal görsel analitik, mekânsal bilgilerin etkileşimli görsel ara yüzlerle ele alındığı analitik akıl yürütme bilimidir. Mekânsal görsel analitik sistemleri sayesinde, Twitter gibi sosyal medya platformlarındaki büyük veri setlerinden bir konu hakkında elde edilen veriler son kullanıcıya etkileşimli haritalama sistemleriyle sunulabilir. 11 Mart 2020’de Dünya Sağlık Örgütü’nün COVID-19 salgınını duyurmasının ardından Twitter veri trafiğinde de ciddi bir artış görülmüştür. Bu çalışmada, COVID-19 salgını döneminin önemli tartışmalarından biri olan COVID-19 aşıları hakkındaki tweet trafiğinin zamansal ve mekânsal gelişimi veri madenciliği teknikleriyle incelenmiş ve görsel analitik ortamda sunulmuştur. Bu çalışma ile twitter gibi sosyal medya platformlarının sahip olduğu büyük veri olarak kabul edilen veri setlerinin veri madenciliği yöntemleriyle analiz edilerek afet ve kriz yönetimi açısından önemli çıkarımlar yapılabileceği ortaya konmuştur.

Anahtar Kelimeler:

Mekânsal görsel analitik, Veri Madenciliği, Büyük Veri, Etkileşimli Haritalama, Sosyal Medya

Presentation of Data Mining Applications in Web Based Geovisual Analytical Environment: Example of COVID-19 Vaccine Tweets

Spatial visual analytics is the science of analytical reasoning in which spatial information is handled with interactive visual interfaces. Thanks to spatial visual analytics systems, data obtained from large data sets on social media platforms such as Twitter can be presented to the end user with interactive mapping systems. After the World Health Organization announced the COVID-19 outbreak on March 11, 2020, there has been a significant increase in Twitter data traffic. In this study, the temporal and spatial development of tweet traffic about COVID-19 vaccines, which is one of the important discussions of the COVID-19 epidemic period, was examined with data mining techniques and presented in a visual analytical environment. With this study, it has been revealed that important inferences can be made in terms of disaster and crisis management by analyzing the data sets, which are accepted as big data, of social media platforms such as twitter with data mining methods.

Keywords:

Geovisual analytic, Data Mining, Big Data, Interactive Mapping, Social Media,

PDF

___

Aldenderfer, M.S., R.K. Blashfıeld, 1984. Cluster analysis, Beverly hills: Sage Publications.
Andrienko, G., Andrienko, N., Jankowski, P., Keim, D., Kraak, M. J., MacEachren, A. M., and Wrobel, S.,2007.
Geovisual analytics for spatial decision support: setting the research agenda. International Journal of Geographical Information Science, 21(8), 839-857.
Andrienko, G., Andrienko, N., Keim, D., MacEachren, A. and Wrobel, S., 2011. Challenging problems of geospatial visual analytics, Journal of Visual Languages and Computing, 22 (4), 251-256.
Atbaş, A.C.G., 2008. Kümeleme Analizinde Küme Sayısının Belirlenmesi Üzerine Bir Çalışma, Ankara Üniversitesi Fen Bilimleri Enstitüsü, Yüksek Lisans Tezi, Ankara.
Bennett, N.C., Millard, D.E., Martin, D., 2018. Assessing twitter geocoding resolution. In: Proceedings of the 10th ACM Conference on Web Science, 239–243.
Blashfield, R.K., Aldenferder, M.S., 1978. The literature on cluster analysis, Multivariate Behavioral Research, 13, 271-295.
Burton, S.H., Tanner, K.W., Giraud-Carrier,C.G., West, J.H., Barnes, M.D., 2012. ”right time, right place” health communication on twitter:value and accuracy of location information. Journal of Medical Internet Research, 14(6), 1-11.
Castillo, C., 2016. Big crisis data: Social media in disasters and time-critical situations. Cambridge University Press.
Dayan, S., 2021. COVID-19 ve Aşı, Dicle Tıp Dergisi / Dicle Medical Journal, 48 (Özel Sayı / Special Issue): 98-113.
Eligüzel, N., 2021. Using twitter for situational awareness after an earthquake: The roles of text categorization and location information, Doktora Tezi, Gaziantep Üniversitesi Fen Bilimleri Enstitüsü, Gaziantep.
Han, J., Kamber, M., 2001. “Data Mining Concepts and Techniques”, Morgan Kaufmann Publishers Inc. Hands, S., Everit, B., 1987. A Monte Carlo study of the recovery of cluster structure in binary data by hierarchical cluster techniques. Multivariate Behaviral Research, 22, 235-243.
Imran, M., Castillo, C., Diaz, F., Vieweg, S., 2015. Processing social media messages in mass emergency: A survey. ACM Computing Surveys (CSUR), 47(4), 1–38.
Imran,M., Mitra, P., Castillo, C., 2016.Twitter as a lifeline: Human annotated twitter corpora for nlp of crisis-related messages. In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016). European Language Resources Association (ELRA): Paris,France.
Imran, M., Ofli, F., Caragea, D., Torralba, A., 2020. Using ai and social media multimodal content for disaster response and management: Opportunities, challenges, and future directions. Information Processing & Management, 57, 1-9.
Kumar, P.,2020. Twitter, disaster and cultural heritage: A case study of the 2015 Nepal earthquake, Journal of Contingencies and Crisis Management, 28, 453–465.
Lei, T., Liang, X., Mascaro, G., Luo, W., White, D., Westerhoff, P., and Maciejewski R., 2015. An Interactive Web-Based Geovisual Analytics Tool to Explore Water Scarcity in Niger River Basin, Workshop on Visualisation in Environmental Sciences (EnvirVis).
Luo, W., Chang, Z., Kong, L.L., Link, R., Hejazi, M., Clarke, L., and Maciejewski, R., 2015. Web-Based Visualization of the Global Change Assessment Model. In: Proceedings of Visualization in Environmental Sciences (EnvirVis 2015), EuroVis 2015. Cagliari, Italy: May 25-26.
MacEachren, A.M., Jaiswal, A., Robinson, A. C., Pezanowski, S., Savelyev, A., Mitra, P., Zhang, X., and Blanford, J., 2011. SensePlace2: Geotwitter Analytics Support for Situation Awareness. 2nd IEEE Conference on Visual Analytics Science and Technology 2011, VAST 2011- Providence, RI, United States, Pages 181-190.
Moore, A., De Oliviera, M., Caminha, C., Furtado, V., Basso, V. and Ayres, L., 2013. Applying Geovisual Analytics to Volunteered Crime Data, Geospatial Visualisation, Lecture Notes in Geoinformation and Cartography, Springer-Verlag Berlin Heidelberg.
Murthy, B. and Longwell S.A., 2012. Twitter And Disasters, Information Communication&Society, 16(6), 1-19. Nair, M.R., Ramya, G.R.,Sivakumar, P.B., 2017. Usage and analysis of Twitter during 2015 Chennai flood towards, disaster management, Procedia Computer Science, 115 ,350–358.
Robinson, A.C., 2017. Geovisual Analytics, The Geographic Information Science&Technology Body of Knowledge (3rd Quarter 2017 Edition).
Robinson, A. C., Peuquet, D. J., Pezanowski, S., Hardisty, F. A., and Swedberg, B., 2016. Design and evaluation of a geovisual analytics system for uncovering patterns in spatio-temporal event data. Cartography and Geographic Information Science, 1-13.
Romesburg, H.C., 1984. Cluster Analysis for Researchers, Belmont, CA: Lifetime Learning Publications. Selvi, H.Z., Çağlar, B., 2017. Çok Değişkenli Haritalama İçin Kümeleme Yöntemlerinin Kullanılması, Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, 6(2), 415-429.
Silahtaroğlu, G., 2013. Veri Madenciliği (Kavram ve Algoritmaları), Papatya Yayıncılık, İstanbul. Tatlıdil, H., 1996. Uygulamalı Çok Değişkenli İstatistiksel Analiz, Hacettepe Taş. Yayınları, Ankara.
Thomas, J. and Cook, K., 2005. Illuminating the Path: Research and Development Agenda for Visual Analytics, IEEE Press, 194 p.
1- https://covid19.who.int/ (31.10.2022) 2- https://www.kaggle.com/datasets/gpreda/all-covid19-vaccines-tweets (06.10.2021) 3- https://ec.europa.eu/eurostat/web/gisco/geodata/reference-data/administrative-units-statistical-units/countries (01.03.2021) 4- https://colorbrewer2.org/ (20.03.2021) 5- https://www.statista.com/statistics/242606/number-of-active-twitter-users-in-selected-countries/ (31.10.2022) 6- https://en.wikipedia.org/wiki/COVID-19_vaccination_in_Canada (31.10.2022) 7- https://en.wikipedia.org/wiki/COVID-19_vaccination_in_Japan (31.10.2022)