The TweetBeat of the City: Microblogging Used for Discovering Behavioural Patterns during the MWC2012

  • Daniel Villatoro
  • Jetzabel Serna
  • Víctor Rodríguez
  • Marc Torrent-Moreno
Conference paper

DOI: 10.1007/978-3-642-36074-9_5

Part of the Lecture Notes in Computer Science book series (LNCS, volume 7685)
Cite this paper as:
Villatoro D., Serna J., Rodríguez V., Torrent-Moreno M. (2013) The TweetBeat of the City: Microblogging Used for Discovering Behavioural Patterns during the MWC2012. In: Nin J., Villatoro D. (eds) Citizen in Sensor Networks. Lecture Notes in Computer Science, vol 7685. Springer, Berlin, Heidelberg

Abstract

Twitter messages can be located in a city and take the pulse of the citizens’ activity. The temporal and spatial location of spots of high activity, the mobility patterns and the existence of unforeseen bursts constitute a certain Urban Chronotype, which is altered when a city-wide event happens, such as a world-class Congress. This paper proposes a Social Sensing Platform to track the Urban Chronotype, able to collect the Tweets, categorize their provenance and extract knowledge about them. The clustering algorithm DBScan is proposed to detect the hot spots, and a day to day analysis reveals the movement patterns. Having analyzed the Tweetbeat of Barcelona during the 2012 Mobile World Congress, results show that a easy-to-deploy social sensor based on Twitter is capable of representing the presence and interests of the attendees in the city and enables future practical applications. Initial empirical results haven shown a significant alteration in the behavioural patterns of users and clusters of activity within the city.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Daniel Villatoro
    • 1
  • Jetzabel Serna
    • 1
  • Víctor Rodríguez
    • 1
  • Marc Torrent-Moreno
    • 1
  1. 1.Barcelona Digital Technology CentreSpain

Personalised recommendations