Araştırma Makalesi
BibTex RIS Kaynak Göster

Using GDELT Estimation of Social Unrest: The Tunisia Example

Yıl 2019, , 589 - 600, 30.11.2019
https://doi.org/10.29249/selcuksbmyd.594233

Öz

Today, social unrest (protests, strikes, conflicts and occupation
events) plays an active role in shaping and changing the borders and political
structures of many countries. The proactive handling of social unrest, both in
democracies and in authoritarian regimes, is of great importance for government
and policy-makers. Thanks to the GDELT project developed today, social events
can now be monitored in real time, thus predicting the future processes of
countries. In this study, a computational approach is used to detect the
incidents of unrest related to the instability of countries. To do this, Google
BigQuery's Pearson correlation feature was used to identify similar patterns
(patterns) for a specific time period in a date (in a 30-day window). In the
study, what happened during the 30-day period of 25 July 2013 in Tunisia was
estimated by using various event data obtained from GDELT. A high correlation
coefficient of r = 0.725 was found when compared to the actual results in
Tunisia. This correlation coefficient shows that the estimations made for
Tunisia are reliable.

Kaynakça

  • Alikhani, E., (2014), “Computational Social Analysis: Social Unrest Prediction Using Textual Analysis of News”, State University of New York at Binghamton.
  • Cadena, J., Korkmaz, G., Kuhlman, C. J., Marathe, A., Ramakrishnan, N., & Vullikanti, A., (2015), “Forecasting social unrest using activity cascades”. PloS one, 10(6), e0128879.
  • Cellan-Jones, R., (2014), “Can computers replace historians?”, https://www.bbc.com/news/technology-28895098, Erişim Tarihi: 10.07.2019.
  • Fallahi, F., (2017), “Machine Learning on Big Data for Stock Market Prediction”, Master of Science Thesis, Southern Illinois University Carbondale.
  • GDELT, (2019), “The GDELT Project”, https://www.gdeltproject.org/data.html#googlebigquery, Erişim Tarihi: 18.01.2019.
  • Google Cloud Platform Blog, (2014), “World's largest event dataset now publicly available in BigQuery”, https://cloudplatform.googleblog.com/2014/05/worlds-largest-event-dataset-now-publicly-available-in-google-bigquery.html, Erişim Tarihi 15.03.2018.
  • Gürsakal, N., (2013), “Çıkarımsal istatistik: MINITAB-SPSS uygulamalı”, Dora Yayıncılık.
  • Hoffa, F., (2017), “What is BigQuery”, https://www.quora.com/What-is-BigQuery, Erişim Tarihi: 12.12.2018.
  • Hoffa, F., (2018), “GDELT correlations.jpynb”, https://nbviewer.jupyter.org/github/fhoffa/notebooks/blob/master/GDELT%20correlations.ipynb, Erişim Tarihi: 10.10.2018.
  • Kallus, N., (2014), “Predicting crowd behavior with big public data”, In Proceedings of the 23rd International Conference on World Wide Web (pp. 625-630). ACM.
  • Keneshloo, Y., Cadena, J., Korkmaz, G., & Ramakrishnan, N., (2014), “Detecting and forecasting domestic political crises: A graph-based approach”, In Proceedings of the 2014 ACM conference on Web science (pp. 192-196). ACM.
  • Korkmaz, G., Cadena, J., Kuhlman, C. J., Marathe, A., Vullikanti, A., & Ramakrishnan, N., (2015), “Combining heterogeneous data sources for civil unrest forecasting”, In Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2015 (pp. 258-265). ACM.
  • Köseoğlu, M., & Yamak, R., (2001), “Uygulamalı İstatistik ve Ekonometri”, Trabzon: Celepler. ss.275.
  • Leetaru, K., (2014), “Towards Psychohistory: Uncovering the Patterns of World History with Google BigQuery” , https://blog.gdeltproject.org/towards-psychohistory-uncovering-the-patterns-of-world-history-with-google-bigquery/, Erişim Tarihi: 10.02.2019.
  • Leetaru, K., Hoffa, F., (2015), “Analyzing the world’s news: Exploring the GDELT Project through Google BigQuery”, https://www.oreilly.com/ideas/analyzing-the-worlds_news_exploring_the_gdelt_project_through_google_bigquery, Erişim Tarihi: 16.11.2018.
  • Muthiah, S., Huang, B., Arredondo, J., Mares, D., Getoor, L., Katz, G., & Ramakrishnan, N., (2015), “Planned protest modeling in news and social media”, In Twenty-Seventh IAAI Conference.
  • Qiao, F., & Wang, H., (2015), “Computational approach to detecting and predicting occupy protest events”, In 2015 International Conference on Identification, Information, and Knowledge in the Internet of Things (IIKI) (pp. 94-97). IEEE.
  • Qiao, F., & Chen, K., (2016), “Predicting protest events with Hidden Markov models”, In 2016 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC) (pp. 109-114). IEEE.
  • Van der Aalst, W. M., Schonenberg, M. H., & Song, M., (2011), “Time prediction based on process mining”, Information systems, 36(2), 450-475.
  • Yonamine, J. E., (2013), “Predicting future levels of violence in afghanistan districts using gdelt”, Unpublished manuscript.

GDELT Kullanarak Toplumsal Huzursuzlukların Tahmin Edilmesi: Tunus Örneği

Yıl 2019, , 589 - 600, 30.11.2019
https://doi.org/10.29249/selcuksbmyd.594233

Öz

Günümüzde, toplumsal huzursuzluklar (protestolar, grevler,
çatışmalar ve işgal olayları) birçok ülkenin sınırlarının ve siyasal
yapılarının şekillenmesinde ve değişmesinde etkin bir rol almaktadır. Gerek
demokrasilerde ve gerek otoriter rejimlerde toplumsal huzursuzlukların proaktif
olarak ele alınması hükümet ve politika yapıcılar için büyük öneme sahiptir.
Bugün geliştirilen GDELT projesi sayesinde artık toplumsal olaylar gerçek
zamanlı izlenebilmekte ve bu sayede ülkelerin gelecekte yaşaması muhtemel
süreçler tahmin edilebilmektedir. Bu çalışmada, ülkelerin istikrarsızlıkları
ile ilgili huzursuzluk olaylarını tespit etmek için hesaplamalı bir yaklaşım
kullanılmıştır. Bunun için tarihteki belli bir zaman aralığın da (30 günlük bir
pencerede) benzer kalıpları (desenleri) tespit etmek için Google BigQuery’nin
Pearson korelasyon özelliği kullanılmıştır. Çalışmada, Tunus’un 25 Temmuz 2013
sorasındaki 30 günlük süreçte yaşananlar, GDELT’ten elde edilen çeşitli olay
verileri kullanılarak tahmin edilmiştir. Tunus’ta gerçekte yaşananlar tahmin
sonuçları ile karşılaştırıldığında r=0.725 gibi yüksek bir korelasyon katsayısı
bulunmuştur. Elde edilen bu korelasyon katsayısı Tunus için yapılan tahminlerin
doğruluğunun güvenilir olduğunu göstermektedir.  

Kaynakça

  • Alikhani, E., (2014), “Computational Social Analysis: Social Unrest Prediction Using Textual Analysis of News”, State University of New York at Binghamton.
  • Cadena, J., Korkmaz, G., Kuhlman, C. J., Marathe, A., Ramakrishnan, N., & Vullikanti, A., (2015), “Forecasting social unrest using activity cascades”. PloS one, 10(6), e0128879.
  • Cellan-Jones, R., (2014), “Can computers replace historians?”, https://www.bbc.com/news/technology-28895098, Erişim Tarihi: 10.07.2019.
  • Fallahi, F., (2017), “Machine Learning on Big Data for Stock Market Prediction”, Master of Science Thesis, Southern Illinois University Carbondale.
  • GDELT, (2019), “The GDELT Project”, https://www.gdeltproject.org/data.html#googlebigquery, Erişim Tarihi: 18.01.2019.
  • Google Cloud Platform Blog, (2014), “World's largest event dataset now publicly available in BigQuery”, https://cloudplatform.googleblog.com/2014/05/worlds-largest-event-dataset-now-publicly-available-in-google-bigquery.html, Erişim Tarihi 15.03.2018.
  • Gürsakal, N., (2013), “Çıkarımsal istatistik: MINITAB-SPSS uygulamalı”, Dora Yayıncılık.
  • Hoffa, F., (2017), “What is BigQuery”, https://www.quora.com/What-is-BigQuery, Erişim Tarihi: 12.12.2018.
  • Hoffa, F., (2018), “GDELT correlations.jpynb”, https://nbviewer.jupyter.org/github/fhoffa/notebooks/blob/master/GDELT%20correlations.ipynb, Erişim Tarihi: 10.10.2018.
  • Kallus, N., (2014), “Predicting crowd behavior with big public data”, In Proceedings of the 23rd International Conference on World Wide Web (pp. 625-630). ACM.
  • Keneshloo, Y., Cadena, J., Korkmaz, G., & Ramakrishnan, N., (2014), “Detecting and forecasting domestic political crises: A graph-based approach”, In Proceedings of the 2014 ACM conference on Web science (pp. 192-196). ACM.
  • Korkmaz, G., Cadena, J., Kuhlman, C. J., Marathe, A., Vullikanti, A., & Ramakrishnan, N., (2015), “Combining heterogeneous data sources for civil unrest forecasting”, In Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2015 (pp. 258-265). ACM.
  • Köseoğlu, M., & Yamak, R., (2001), “Uygulamalı İstatistik ve Ekonometri”, Trabzon: Celepler. ss.275.
  • Leetaru, K., (2014), “Towards Psychohistory: Uncovering the Patterns of World History with Google BigQuery” , https://blog.gdeltproject.org/towards-psychohistory-uncovering-the-patterns-of-world-history-with-google-bigquery/, Erişim Tarihi: 10.02.2019.
  • Leetaru, K., Hoffa, F., (2015), “Analyzing the world’s news: Exploring the GDELT Project through Google BigQuery”, https://www.oreilly.com/ideas/analyzing-the-worlds_news_exploring_the_gdelt_project_through_google_bigquery, Erişim Tarihi: 16.11.2018.
  • Muthiah, S., Huang, B., Arredondo, J., Mares, D., Getoor, L., Katz, G., & Ramakrishnan, N., (2015), “Planned protest modeling in news and social media”, In Twenty-Seventh IAAI Conference.
  • Qiao, F., & Wang, H., (2015), “Computational approach to detecting and predicting occupy protest events”, In 2015 International Conference on Identification, Information, and Knowledge in the Internet of Things (IIKI) (pp. 94-97). IEEE.
  • Qiao, F., & Chen, K., (2016), “Predicting protest events with Hidden Markov models”, In 2016 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC) (pp. 109-114). IEEE.
  • Van der Aalst, W. M., Schonenberg, M. H., & Song, M., (2011), “Time prediction based on process mining”, Information systems, 36(2), 450-475.
  • Yonamine, J. E., (2013), “Predicting future levels of violence in afghanistan districts using gdelt”, Unpublished manuscript.
Toplam 20 adet kaynakça vardır.

Ayrıntılar

Birincil Dil Türkçe
Bölüm Araştırma Makalesi
Yazarlar

Sadullah Çelik 0000-0001-5468-475X

Yayımlanma Tarihi 30 Kasım 2019
Gönderilme Tarihi 19 Temmuz 2019
Yayımlandığı Sayı Yıl 2019

Kaynak Göster

APA Çelik, S. (2019). GDELT Kullanarak Toplumsal Huzursuzlukların Tahmin Edilmesi: Tunus Örneği. Selçuk Üniversitesi Sosyal Bilimler Meslek Yüksekokulu Dergisi, 22(2), 589-600. https://doi.org/10.29249/selcuksbmyd.594233

Selçuk Üniversitesi Sosyal Bilimler Meslek Yüksekokulu Dergisi Creative Commons Atıf-GayriTicari 4.0 Uluslararası Lisansı (CC BY NC) ile lisanslanmıştır.