Advertisement

On the Volume of Geo-referenced Tweets and Their Relationship to Events Relevant for Migration Tracking

  • Georg Neubauer
  • Hermann Huber
  • Armin Vogl
  • Bettina Jager
  • Alexander Preinerstorfer
  • Stefan Schirnhofer
  • Gerald Schimak
  • Denis Havlik
Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT, volume 448)

Abstract

Migration is a major challenge for the European Union, resulting in early preparedness being an imperative for target states and their stakeholders such as border police forces. This preparedness is necessary for multiple reasons, including the provision of adequate search and rescue measures. To support preparedness, there is a need for early indicators for detection of developing migratory push-factors related to imminent migration flows. To address this need, we have investigated the daily number of geo-referenced Tweets in three regions of Ukraine and the whole of Japan from August 2014 until October 2014. This analysis was done by using the data handling tool Ubicity. Additionally, we have identified days when relevant natural, civil or political events took place in order to identify possible event triggered changes of the daily number of Tweets. In all the examined Ukrainian regions a considerable increase in the number of daily Tweets was observed for the election day of a new parliament. Furthermore, we identified a significant decrease in the number of daily Tweets for the Crimea for the whole examined period which could be related to the political changes that took place. The natural disasters identified in Japan do not show a clear relationship with the changes in the degree of use of the social media tool Twitter. The results are a good basis to use communication patterns as future key indicator for migration analysis.

Keywords

migration tweets geolocation early indicator push factor 

References

  1. 1.
    Starbird, K.: Crowdwork, Crisis and Convergence: How the Connected Crowd Organizes Information during Mass Disruption Events. Colorado (2012)Google Scholar
  2. 2.
    Stefanidis, A., Crooks, A., Radzikowski, J.: Harvesting ambient geospatial information from social media feeds. GeoJournal 78(2), 319–338 (2011)CrossRefGoogle Scholar
  3. 3.
    Zagheni, E.G.V., Weber, I.: Inferring international and internal migration patterns from Twitter data. In: Proceedings of the Companion Publication of the 23rd International Conference on World Wide Web Companion, Geneva, Switzerland (2014)Google Scholar
  4. 4.
    Neubauer, G., Huber, H., Jager, B., Vogl, A.: Detecting Events in Egypt Based on Geo-Referenced Tweets. In: 22nd Proceedings of IDIMT-2014. Networking Societies – Cooperation and Conflict, Czech Republic, Poděbrady (2014)Google Scholar
  5. 5.
    Khanwalkar, S., Seldin, M., Srivastava, A., Kumar, A., Colbath, S.: Content-Based Geo-Location Detection for Placing Tweets Pertaining To Trending News on Map. In: The Fourth International Workshop on Mining Ubiquitous and Social Environments (MUSE 2013), Prague, Czech Republic (2013)Google Scholar
  6. 6.
    Ifrim, G., Shi, B., Brigadir, I.: Event Detection in Twitter using Aggressive Filtering and Hierarchical Tweet Clustering. In: Proceedings of the SNOW 2014 Data Challenge, Seoul, Korea (2014)Google Scholar
  7. 7.
    Office of the United Nations High Commissioner for Human Rights, Report on the human rights situation in Ukraine (2014)Google Scholar
  8. 8.
  9. 9.
  10. 10.
    United Nations University-Institute for Environment and Human Security, World Risk Report 2014, Bonn, Germany (2014)Google Scholar
  11. 11.
    Glidenumber, http://glidenumber.net/glide/public/search/search.jsp (accessed November 5, 2014)
  12. 12.
    Washington Post, The main advantage is the independence in terms of language understanding. Advanced analysis might also take term frequency and co-occurrence as well as hashtags and network relations into account. We discovered the stability of the public twitter data de (accessed November 5, 2014) Google Scholar
  13. 13.
    Morstatter, F., Pfeffer, J., Liu, H., Carley, K.M.: Is the Sample Good Enough? Comparing Data from Twitter’s Streaming API and Twitter’s Firehose. In: Proceedings of ICWSM (2013)Google Scholar
  14. 14.
    Abdelhaq, H., Sengstock, C., Gertz, M.: EvenTweet: Online Localized Event Detection from Twitter. In: Proceedings of the VLDB Endowment, Riva del Garda, Trento, Italy (2013)Google Scholar
  15. 15.
    Kraft, T., Wang, D., Delawder, J., Dou, W., Li, Y., Ribarsky, W.: Less After-the-Fact: Investigative visual analysis of events from streaming twitter. In: IEEE Symposium on Large-Scale Data Analysis and Visualization, LDAV (2013)Google Scholar
  16. 16.
    Schaust, S., Walther, M., Kaisser, M.: Avalanche: Prepare, Manage, and Understand Crisis Situations Using Social Media Analytics. In: Proceedings of the 10th International ISCRAM Conference, Baden-Baden (2013)Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2015

Authors and Affiliations

  • Georg Neubauer
    • 1
  • Hermann Huber
    • 1
  • Armin Vogl
    • 2
  • Bettina Jager
    • 1
  • Alexander Preinerstorfer
    • 1
  • Stefan Schirnhofer
    • 1
  • Gerald Schimak
    • 1
  • Denis Havlik
    • 1
  1. 1.AIT Austrian Institute of Technology GmbH, ViennaAustria
  2. 2.Federal Ministry of InteriorViennaRepublic of Austria

Personalised recommendations