The Classification of Space-Time Behaviour Patterns in a British City from Crowd-Sourced Data

  • Mark Birkin
  • Kirk Harland
  • Nicolas Malleson
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7974)


The use of social messaging as a means to represent activity and behaviour patterns across small geographical areas is explored. A large corpus of messages provides the source from which a range of interesting marker words are identified. Profiles of the variations in language across neighbourhoods can then be constructed. Areas are classified on the basis of the types of messages which they tend to generate. The resulting patterns are interpreted as suggesting that variations in behaviour and activity over time within an urban area are an important adjunct to well-established spatial variations. It is asserted that further elaboration of these promising investigations within appropriate analytic frameworks could extend our understanding of movement and behaviour patterns in cities in important ways.


Geodemographics social messaging crowd-sourced data cluster activity movement pattern 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Thelwall, M., Buckley, K., Paltoglou, G.: Sentiment in twitter events. Journal of the American Society for Information and Technology 62, 406–418 (2011)CrossRefGoogle Scholar
  2. 2.
    Kawamoto, T.: A Stochastic Model of Tweet Diffusion on the Twitter Network. Physica A: Statistical Mechanics and Its Applications (in press),
  3. 3.
    Xiong, F., Liu, Y., Zhang, Z., Zhu, J., Zhang, Y.: An Information Diffusion Model Based on Retweeting Mechanism for Online Social Media. Physics Letters A 376, 2103–2108 (2012)CrossRefGoogle Scholar
  4. 4.
    Tumasjan, A., Sprenger, T.O., Sandner, P.G., Welpe, I.M.: Election Forecasts With Twitter: How 140 Characters Reflect the Political Landscape. Social Science Computer Review 29, 402–418 (2011)CrossRefGoogle Scholar
  5. 5.
    Sobkowicz, P., Kaschesky, M., Bouchard, G.: Opinion Mining in Social Media: Modeling, Simulating, and Forecasting Political Opinions in the Web. Government Information Quarterly 29, 470–479 (2012), doi:10.1016/j.giq.2012.06.005.CrossRefGoogle Scholar
  6. 6.
    Cheng, Z., Caverlee, J., Lee, K., Sui, D.: Exploring Millions of Footprints in Location Sharing Services. In: Proceedings of the International AAAI Conference on Weblogs and Social Media (ICWSM) (2011)Google Scholar
  7. 7.
    Longley, P.: Geographical Information Systems: a renaissance of geodemographics for public service delivery. Progress in Human Geography 29, 57–63 (2005)CrossRefGoogle Scholar
  8. 8.
    Harris, R., Sleight, P., Webber, R.: Geodemographics, GIS, and neighbourhood targeting. Wiley, Chichester (2005)Google Scholar
  9. 9.
    Farr, M., Webber, R.: MOSAIC: From an area classification to individual classification. Journal of Targeting, Measurement and Analysis for Marketing 87, 681–699 (2001)Google Scholar
  10. 10.
    Humby, C., Hunt, T.: Scoring Points: How Tesco is Winning the Battle for Customer Loyalty. Kogan-Page (2003)Google Scholar
  11. 11.
    Everitt, B.: Cluster Analysis, 5th edn. John Wiley, Chichester (2011)zbMATHCrossRefGoogle Scholar
  12. 12.
    Vickers, D.: Multi-Level Integrated Classifications Based on the 2001 Census. PhD thesis University of Leeds (2006)Google Scholar
  13. 13.
    Cathelat, B.: Socio-Styles. Kogan Page, English London (1990)Google Scholar
  14. 14.
    Malleson, N., Birkin, M.: Estimating Individual Behaviour from Massive Social Data for An Urban Agent-Based Model. In: Modelling Social Phenomena in a Spatial Context GeoSimulation. LIT Verlag, Berlin (2012)Google Scholar
  15. 15.
    Hagerstrand, T.: Innovation Diffusion as a Spatial Process. Chicago University Press, Chicago (1967)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Mark Birkin
    • 1
  • Kirk Harland
    • 1
  • Nicolas Malleson
    • 1
  1. 1.School of GeographyUniversity of LeedsLeedsUK

Personalised recommendations