CityPulse: A Platform Prototype for Smart City Social Data Mining

Cities experience radical shifts from conventional areas of fragmented services and interactions, to whole-of-service and end-to-end providers, while their citizens are empowered primarily via social networking applications with geotagging capabilities. This work is motivated by the fact that the exploitation of a (smart) city’s social networking and collective awareness can lead to improvements in the citizens’ daily life and assist city’s crowd-wise policy and decision making. This challenging objective requires appropriate platforms which will not only offer analytics of the city’s social networking data threads but also aggregation and visualization of these data for revealing and highlighting latent information in terms of the city’s emerging topics and trends. The proposed CityPulse is a modular platform for offering smart city services based on social data analysis in the context of a city. CityPulse is based on the main principle that a carefully designed backend system supports appropriate data storage, aggregation and analysis methodologies, while the derived results are exposed through Web service interfaces to ensure interoperability with various smart city applications that serve the needs of various city stakeholders. Here, we indicatively describe a generic mobile front end interface that demonstrates the functionalities that can be implemented based on CityPulse results derived by geolocated social data mining. We also demonstrate the results of CityPulse’s application on an representative smart city case study which indicate that it can effectively capture and summarize social media user activities within the city and deliver useful latent information to interested city communities in an comprehensive, flexible manner.

[1]  Mohammad Ali Abbasi,et al.  TweetTracker: An Analysis Tool for Humanitarian and Disaster Relief , 2011, ICWSM.

[2]  Leonidas G. Anthopoulos,et al.  Social networks in smart cities: Comparing evaluation models , 2015, 2015 IEEE First International Smart Cities Conference (ISC2).

[3]  Hirotoshi Iwasaki,et al.  BEIRA: A Geo-semantic Clustering Method for Area Summary , 2007, WISE.

[4]  Athena Vakali,et al.  Social networking trends and dynamics detection via a cloud-based framework design , 2012, WWW.

[5]  L. Anthopoulos,et al.  Defining Smart City Architecture for Sustainability , 2015 .

[6]  Ling Chen,et al.  Event detection from flickr data through wavelet-based spatial analysis , 2009, CIKM.

[7]  Theresa A. Pardo,et al.  Conceptualizing smart city with dimensions of technology, people, and institutions , 2011, dg.o '11.

[8]  T. Landauer,et al.  Indexing by Latent Semantic Analysis , 1990 .

[9]  Yiannis Kompatsiaris,et al.  ImproveMyCity: an open source platform for direct citizen-government communication , 2013, ACM Multimedia.

[10]  Kazufumi Watanabe,et al.  Jasmine: a real-time local-event detection system based on geolocation information propagated to microblogs , 2011, CIKM '11.

[11]  Cecilia Mascolo,et al.  The Call of the Crowd: Event Participation in Location-Based Social Services , 2014, ICWSM.

[12]  Denzil Ferreira,et al.  HotCity: enhancing ubiquitous maps with social context heatmaps , 2013, MUM.

[13]  R. Hollands Will the real smart city please stand up? , 2008, The Routledge Companion to Smart Cities.

[14]  Yutaka Matsuo,et al.  Earthquake shakes Twitter users: real-time event detection by social sensors , 2010, WWW '10.

[15]  Lefteris Angelis,et al.  Sensors talk and humans sense Towards a reciprocal collective awareness smart city framework , 2013, 2013 IEEE International Conference on Communications Workshops (ICC).

[16]  Yiannis Kompatsiaris,et al.  Cluster-Based Landmark and Event Detection for Tagged Photo Collections , 2011, IEEE MultiMedia.