Geo-Spatial Trend Detection Through Twitter Data Feed Mining

Conference paper
Part of the Lecture Notes in Business Information Processing book series (LNBIP, volume 226)


Present-day Social Networking Sites are steadily progressing towards becoming representative data providers. This paper proposes TweetPos, a versatile web-based tool that facilitates the analytical study of geographic tendencies in crowd-sourced Twitter data feeds. To accommodate the cognitive strengths of the human mind, TweetPos predominantly resorts to graphical data structures such as intensity maps and diagrams to visualize (geo-spatial) tweet metadata. The web service’s asset set encompasses a hybrid tweet compilation engine that allows for the investigation of both historic and real-time tweet posting attitudes, temporal trend highlighting via an integrated animation system, and a layered visualization scheme to support tweet topic differentiation. TweetPos ’ data mining features and the (geo-spatial) intelligence they can amount to are comprehensively demonstrated via the discussion of two representative use cases. Courtesy of its generic design, the TweetPos service might prove valuable to an interdisciplinary customer audience including social scientists and market analysts.


Twitter Social networking sites Social media Geographic trends Investigative tool Data mining TweetPos 


  1. 1.
    Sakaki, T., Okazaki, M., Matsuo, Y.: Earthquake shakes Twitter users: real-time event detection by social sensors. In: Proceedings of the WWW 2010, Raleigh, NC, USA, pp. 851–860 (2010)Google Scholar
  2. 2.
    Pinto, N., Majaj, N.J., Barhomi, Y., Solomon, E.A., Cox, D.D., DiCarlo, J.J.: Human versus machine: comparing visual object recognition systems on a level playing field. In: Proceedings of the Cosyne 2010, Salt Lake City, UT, USA (2010)Google Scholar
  3. 3.
    Twitter Developers: using the Twitter search API (2013).
  4. 4.
    140dev: 140dev streaming API framework (2013).
  5. 5.
    Google Developers: The Google Geocoding API (2013).
  6. 6.
    Google Developers: Google Maps JavaScript API v3 (2013).
  7. 7.
    Stefanidis, A., Crooks, A., Radzikowski, J.: Harvesting ambient geospatial information from social media feeds. GeoJournal 78, 319–338 (2013)CrossRefGoogle Scholar
  8. 8.
    Reips, U.D., Garaizar, P.: Mining Twitter: a source for psychological wisdom of the crowds. Behav. Res. Methods 43, 635–642 (2011)CrossRefGoogle Scholar
  9. 9.
    Boettcher, A., Lee, D.: EventRadar: a real-time local event detection scheme using Twitter stream. In: Proceedings of GreenCom 2012, Besançon, France, pp. 358–367 (2012)Google Scholar
  10. 10.
    Crooks, A., Croitoru, A., Stefanidis, A., Radzikowski, J.: #Earthquake: Twitter as a distributed sensor system. Trans. GIS 17, 124–147 (2013)CrossRefGoogle Scholar
  11. 11.
    Takahashi, T., Abe, S., Igata, N.: Can Twitter be an alternative of real-world sensors? In: Jacko, J.A. (ed.) Human-Computer Interaction, Part III, HCII 2011. LNCS, vol. 6763, pp. 240–249. Springer, Heidelberg (2011) Google Scholar
  12. 12.
    Singh, V.K., Gao, M., Jain, R.: Situation detection and control using spatio-temporal analysis of microblogs. In: Proceedings of WWW 2010, Raleigh, NC, USA, pp. 1181–1182 (2010)Google Scholar
  13. 13.
    Field, K., O’Brien, J.: Cartoblography: experiments in using and organising the spatial context of micro-blogging. Trans. GIS 14, 5–23 (2010)CrossRefGoogle Scholar
  14. 14.
    Oussalah, M., Bhat, F., Challis, K., Schnier, T.: A software architecture for twitter collection, search and geolocation services. Knowl.-Based Syst. 37, 105–120 (2013)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Expertise Centre for Digital MediaHasselt University – tUL – iMindsDiepenbeekBelgium

Personalised recommendations