Human Data

tav_10_social_pattern     tav_10a_social_pattern+talenti

Tav. 10 Urban pattern from social networking activity

The representation returns the pattern in a regular grid of 50m of intensity activities derived from social networks (Twitter, Facebook and Foursquare).  A  greater number of “Tweet”, “Place” and “Tag” in a cell corresponds to  brownish colors, while a smaller number corresponds to a color tone of beige. This model, replicable in other urban contexts, is able to monitor the dynamics of use of these platforms in the city investigated not from the point of view of supply of static services, but also by the point of view of a dynamic use.
The latter being  more useful to the sustainable management of services provision, mobility or energy management.
(Data source: Twitter API, Facebook, Fousquare API)

tav_11a_tweet_ore_7_9  tav_11b_tweet_ore_9_11

tav_11c_tweet_ore_11_15  tav_11d_tweet_ore_15_18

tav_11e_tweet_ore_18_20    tav_11f_tweet_ore_20_22

tav_11g_tweet_#palermo_3d_13_03_2015   tav_11h_tweet_#palermo_3d_14_03_2015

tav_11i_tweet_#palermo_13_03_2015  tav_11l_tweet_#palermo_14_03_2015 tav_11m_tweet_3d_ore_11_15_2015_riverbero


Tav. 11 Distribution of social networks activity (Twitter) [Heat Map]
The representation returns the distribution of twitter activity with reference to different timeframes through the use of a concentration algorithm called “Heat Map”. The four representations show the streaming of human data that originate by Twitter. The social network has been chosen for the peculiarities in providing  in real-time information and space-time information that are  useful for example in the analysis of flows to and from work and/or leisure places.
The location of users is able to monitor the dynamics of the use of city functions, investigated not only  from the point of view of static services supply, but also by the point of view of a dynamic use. The latter being  more useful to the sustainable management of services provision, mobility or energy management. The same information was also represented through appropriate temporal filters and text. The elaborations show the Twitter activity filtered on two days (13 and 14 March),  with hashtag “Palermo” and chosen by the presence of an event (the match of the team of Palermo Soccer team) or a normal daily operation. Through Data Mining analysis, you can monitor the mutation of urban polarities according to the different “urban social metabolism”.
The same processing in 3d show even more clearly the information and, in the case of representation in contour lines, show that changes the urban “morphology” observed with the filter of social networks.
(Data source: Twitter API)

Licenza Creative Commons
Quest’opera è distribuita con Licenza Creative Commons Attribuzione – Non commerciale – Non opere derivate 4.0 Internazionale.

Leave a Reply

Your email address will not be published. Required fields are marked *