Presentation by Karima Kourtit and Peter Nijkamp Advanced Brainstorm Carrefour (ABC): ‘Urban Empires - Cities as Global Rulers in the New Urban World’ Adam Mickiewicz University, Poznan, Poland (August, 2016)

1. Social Media Based Management ToolsSocial Media Based Management Tools
for Intelligent Citiesfor Intelligent Cities
Karima KourtitKarima Kourtit
Peter NijkampPeter Nijkamp

2. Aims and scopeAims and scope
Megatrends:
Emergence of smart / intelligent cities
Rapid penetration of social media in a digital
world
Aims:
to demonstrate the strategic importance of
digital technology for intelligent cities
to illustrate and to model the use of social
media as a buzz factor for spatial behaviour in
the city

3.  Kourtit, K., Nijkamp, P., and Steenbruggen, J. (2015),
The Significance of Cyber Space for Urban
Agglomerations: A Review of Impacts of Digital Data
Systems on Smart Cities, Socio-Economic Planning
Sciences (forthcoming).

4. Smart Cities - conceptsSmart Cities - concepts
 Wired cities (Dutton, 1987)
 Techno cities (Downey and McGuigan, 1999)
 Cyber cities (Graham and Marvin, 1999)
 Creative cities (Florida, 2005)
 Knowledge-based cities (Carrillo, 2006)
 Real-time city (Townsend, 2000)
 WIKI cities (Calabrese et al., 2007; Ratti et al., 2007)
 Digital cities (Komninos, 2008)
 Live City (Resch et al., 2012)
 Networked cities (Castells, 1996)
 Sentient cities (Shepard, 2011)
 Computable city
 Ubiquitous city
 Sustainable / resilient city
 Green city
 Open city……
 Latest (most used) concepts:
 Intelligent city (Komninos, 2006, 2008; Sassen, 2011).
 Smart city (Mitchell, 2006; Giffinger et al., 2007)
 Incredible cities (Kourtit et al. 2010)

5. • Each of these concepts are used in a particular way to
conceptualise the relationship between ICT and contemporary
urbanism, however, they share a common focus on the effects of
ICT on urban developments.
Key characteristics:
• networked (community and space-economy),
• wired
• digital
• innovation
• knowledge (creation)
• learning (capacity)
• smart, intelligent,
• creativity, productivity,
• competitive and participation.
Smart Cities – key characteristics

6. Some elements of Smart CitiesSome elements of Smart Cities
Main focus on soft infrastructure (i.e. ICT
networks, fast internet connections etc.)
Specific papers focus rather on:
– Human capital (Glaeser and Berry 2005,
2006)
– Urban amenities (Shapiro 2008)
– Creative class (Florida 2002)

7. • Technological innovation perspective (Komninos, 2006): “territories with high
capacity for learning and innovation, which is built-in the creativity of their
population, their institutions of knowledge creation, and their digital
infrastructure for communication and knowledge management”.
• Economic perspective (Nijkamp, 2011; Caragliu 2011; Kourtit an Nijkamp
2016): “investments in human and social capital and traditional (transport)
and modern (ICT) communication infrastructure to fuel sustainable
economic growth and a high quality of life, with a wise management of
natural resources, through participatory governance”.
• Monitoring perspective based on sensors (Giffinger et al., 2007): “a city
functions in a sustainable and intelligent way, by integrating all its
infrastructures and services into a cohesive whole and using intelligent
devices for monitoring and control, to ensure sustainability and efficiency”.
• Networked perspective (Nijkamp, 2008): “geographical hubs (virtual and
real) in a modern networked space-economy and will continue to be engines
of economic growth, creativity and innovativeness”.
Smart Cities - definitions

8. A new definion of Smart CitiesA new definion of Smart Cities
A city is smart when investments in human and
social capital and traditional (transport) and
modern (ICT) communication infrastructure fuel
sustainable economic growth and a high quality of
life, with a wise management of natural resources,
through participatory governance (Caragliu et al.
2009).

9. DIVERSITY OF SMART / INTELLIGENT CITIES
WHICH STRATEGY?

10. Competitiveness
Innovative spirit
Entrepreneurship
Productivity
Flexibility of labour
market
Local & global
interconnections
...
SMART ECONOMY
Human & social
capital
Qualifications &
creativity
Social & ethnic
plurality
Open mindedness
Participation in
public life
...
SMART PEOPLE
Sustainable &
innovative
transportation
Pervasive ICT
infrastructure
Multimodal
accessibility
...
SMART MOBILITY
Sustainable
management of
resources
Energy & Water
Pollution
Green urban
planning
...
SMART
ENVIRONMENT
Participation
E-Government
Transparency &
open data
Public & social
services
...
SMART
GOVERNANCE
Public health
Public safety
Education facilities
Housing
Culturally vibrant,
attractive & happy
Social cohesion
...
SMART LIVING
TOPICSINDICATIORS(examples)
R&D expenditure
in % of GDP
Self-employment
rate
GDP per Capita
Companies with
HQ in the city
...
Participation in
long life learning
Share of people
working in creative
industries
Share of foreigners
Immigration-
friendly
environment
...
City
representatives
per resident
Share of children in
day care
Satisfaction with
quality of school
...
Public transport
network per
inhabitant
Broadband
internet access in
households
Green mobility
share
Traffic safety ...
Summer smog /
air quality
Efficient use of
water / energy
Opinion on nature
protection
...
Hospitals per
inhabitant
Crime rate
Theatre
attendance per
inhabitant
Perception on
personal risk
poverty ...
• City performance can be assessed against various dimensions of smartness: this
framework is not unique, but has a growing acceptance
• Smart city is a complex system of connected smart subsystems
Smart Cities - frameworkSmart Cities - framework
DATA

11. GREEN CITY INDEX
Areas Indicators
CO2
CO2 emission
CO2 intensity
CO2 reduction strategy
Energy
Energy Consumption
Energy intensity
Renewable energy consumption
Clean & efficient energy policies
Buildings
Energy consumption of residential
buildings
Energy-efficient building standards
Energy-efficient build. initiatives
Transport
Use of non-car transport
Size of non-car transport network
Green transport promotion
Congestion reduction policies
Water
Water consumption
Water system leakages
Wastewater treatment
Water efficiency & treatment policies
Waste and Land
Use
Municipal waste production
Waste recycling
Waste reduction & policies
General land use policies
Air Quality
Nitrogen dioxide
Ozone
Particulate matter
Sulphur dioxide
Clean air policies
Environmental
Governance
Green action plan
Green management
Public participation in green policy
GLOBAL CITY
INDICATORS FACILITY
Groups Themes
City Profile
Indicators
People
Housing
Economy
Government
Geography & Climate
Performance: City
Services
Education
Finance
Recreation
Governance
Energy
Transportation
Wastewater
Fire & Emergency Response
Health
Safety
Solid Waste
Urban Planning
Performance:
Quality of life
Civic Engagement
Economy
Shelter
Culture
Environment
Social Equality
Technology & Innovation
MERCER QUALITY OF
LIVING
Catego
ries
Factors
Political & social
environment
Political stability
Crime
Law enforcement
Economic
Environment
Currency exchange regulations
Banking services
Socio-cultural
environment
Censorship
Limitations on personal freedom
Medical & health
considerations
Medical supplies and services
Infectious diseases
Sewage
Waste disposal
Air pollution
Schools & education
Standard and availability of
International schools
Public services &
transportation
Electricity
Water
Public transportation
Traffic congestion
Recreation
Restaurants,
Theatres, movie theatres,
Sports and leisure
Consumer goods
Availability of food/daily consumption
items, cars
Housing
Rental housing,
Household appliances
So far, most of city rankings have
been created based on traditional
statistical data sources, and census-
like indicators.
Smart Cities – ranking system
http://www.mercer.com/press-
releases/quality-of-living-report-2012 http://www.siemens.com/entry/cc/en/greencityindex.htmhttp://www.cityindicators.org

13. Hägerstrand’s Time-Space Model
currentcity.org
• Hägerstand (1970)
shows how people travel
and live through time and
space from birth to
death.
• People always have to
deal with decisions they
made earlier (historical
setting) and some
constraints (divided in 3
groups).
The concept of a space-time path is to illustrate how a
person navigates his or her way through the spatial-temporal
environment.

14. Time-SpacTime-Spacee CilinderCilinder

15. “the city itself is turning into a
constellation of computers” (Batty, 1995)
Networked cities are made up by flows of
people, vehicles, and information (Sheller, 2004).
Data about these flows are difficult to collect,
but are becoming increasingly available for
new social science research data and methods (Shoval, 2007).
This trend promptsThis trend prompts the questionthe question on the potential useon the potential use
of ‘of ‘big databig data’ in the digital world for effective and’ in the digital world for effective and
efficient planning, management, and research purposesefficient planning, management, and research purposes
This trend promptsThis trend prompts the questionthe question on the potential useon the potential use
of ‘of ‘big databig data’ in the digital world for effective and’ in the digital world for effective and
efficient planning, management, and research purposesefficient planning, management, and research purposes

16. • The use of mobile phone to support urban analytics
enables the research community to analyze
and model the dynamic pulse of
the city or heartbeat (Batty, 2010).
• The underlying assumption of space-time geography
methods is not a static canvas of urban zones or urban
morphology, but instead a dynamic understanding of the
urban environment, as manifested in numerous and
diverse individual urban life-styles.
– Space is not separated by time; the domain of such urban
analytics is the space-time continuum.
Urban analytics – Space and time

17. Identification and location devices
Patient Children
Label Tag Car box
Patient Inmate Badge
AGPS phone Navigators
Camera WiFi tag

21. Measurement and Monitoring
Performance system: DASHBOARDS
• In general, space-time geography (data) form a
way to better understand the urban environment
and its dynamics and a HEALTH CHECK of
Smart Cities.
– Such data can serve to reveal how we as citizens
relate to our urban contexts
– Highlights the needs for strategic urban planning and
complex urban management issues.
• In this sense:
– data analysis (usually enabled by data visualizations)
can empower a city with smartness and intelligence
by helping us to identify patterns and relationships,
enabling citizens and decision bodies with tools that
support better decision making, discovery,
exploration, and explanation of the city.

22. 22
Examples of smart sub-performance indicators measure:
Geographic
ConcentrationJob Creation
Innovation
and
Entrepreneurhip
Availability venture
capital

23. Location-based Digital information

24. Penetration of Social MediaPenetration of Social Media
Facebook, 2004 Twitter, 2006 FourSquare, 2009
Flickr, 2004 Panoramio, 2005

25. Tourism
=> language diversity as an indicator (based on twitter)
http://irevolution.net/2013/06/09/mapping-global-twitter-heartbeat/

26. Amsterdam (4.02 ml. / 9 % - ranking 22) London (14.7 ml. / 3.5% - ranking 3)
Casablanca (??)Milan (1.9 ml. / 0.8% - ranking 65)
Tourism
=> Language comparison between cities (based on geo-located tweets)
Marocco (9.2 ml. Tourists in 2010)
Marrakech (2.02 ml. - Ranking 58)

27. Big Data
“Datasets whose size is beyond the ability of typical database
software tools to capture, store, manage, and analyze”
or
“Large volumes of high velocity, complex and variable data that
require advanced techniques and technologies to enable the
capture, storage, distribution, management and analysis of the
information”
or the four V’s
– Volume (huge data sets with terabytes or petabytes of information)
– Velocity (time sensitive)
– Variety (unstructured data of all varieties)
– Veracity (quality and provenance of received data)

28. Big Data
In other words:
• Big data consists of massive, dynamic, varied, detailed, inter-
related, low cost datasets that can be connected and utilised in
diverse ways (Kitchin, 2013).
• Bigger data are larger-sized datasets, often drawn from different
sources, with multidimensional structures and levels of many
characteristics and activities of a complex economic, social and
cultural nature produced by a multiplicity of actors and stakeholders
for new and sustainable urban development and advanced urban
competitiveness analysed with powerful tools. (Nijkamp and Kourtit
2016).

29. Mobile phone network data
• Data generated by the interaction between mobile
phone and the serving telecommunication network
• Triggered by
– Events (call/sms/Internet usage)
– Network • Periodic • Mobility-driven
• Different device location information is available at
different levels (interfaces) of the
telecommunication Network
– Cell tower
– Cell sector
– Triangulated position
• Data can be aggregated at different spatial and
temporal levels

30. • How many people are in that area?
• Where are traffic jams?
• Where are incidents or major events?
• What percentage of people have left the area?
• What is the current demand and supply of public
transportation?
• How much CO2 was emitted today?
• Is there a relation between energy consumption
and the presence of people
• What’s the hottest spot in town now?
• What is the most popular landmark?
• Where the tourist come from?
Smart / intelligent city and information needs
=> Growing interest in urban dynamics
Big Data ,Space-time geography and Dashboard
is a new way to support smart city vision, strategies and
its objectives

31. Central Station
Rembrandtplein
Jordaan
WTC
Museumplein

32. World Trade Center
Business area
00:00
Monday
Tuesday
Wednesday
Thursday
Friday
Saturday
Sunday
Aggregared call intensity
12:0006:00 18:00

33. Central station
Transportation hub
Monday
Tuesday
Wednesday
Thursday
Friday
Saturday
Sunday
Aggregared call intensity
00:00 12:0006:00 18:00

34. Amsterdam Arena
Footbal stadium
Monday
Tuesday
Wednesday
Thursday
Friday
Saturday
Sunday
00:00 12:0006:00 18:00
Aggregared call intensity

35. Rembrandtplein
Nightlife area
Monday
Tuesday
Wednesday
Thursday
Friday
Saturday
Sunday
00:00 12:0006:00 18:00
Aggregared call intensity

36. currentcity.org
queensday
King’s day

37. Calls+SMS
Rembrandt
WTC
`
30 April
Visualization – Queens day
Heartbeat of the city
Creating normality maps to detect anomalies

38. Presence of people

39. Where is the shopping action?

40. Telecom data for Traffic
Incident Management
Traffic Incident Management can be seen as a
special case of Emergency Management
Hurricane Rita I45N Freeway Gridloc

41.  Arribas-Bel, D., Kourtit, K., and Nijkamp, P. (2016), The
Sociocultural Sources of Urban Buzz, Environment and
Planning C, 34 (1), 188-204.

42. EMPIRICAL ILLUSTRATION:EMPIRICAL ILLUSTRATION:
SOCIAL MEDIA, BIG DATA AND URBAN
BUZZ:
Explanatory Analysis
 Aim: trace the origin and impact of urban
buzz
 Relationship: Urban buzz and cultural
diversity
 Methodological strategy
 Data
- Urban buzz and location-sharing services
- Other data
 Results

43. Buzz
“A low, continuous humming or murmuring
sound”
Urban buzz
 Cities as human agglomerations (geographical
spikes)
 But, intra-urban landscapes are also ‘spiky’:
agents and activities are unevenly distributed
both in space and time
 Volume of activities and interactions in
neighbourhood , the traditional piazza
B = f (economic function, time…)
43

44. Methodological strategy
The city of Amsterdam
 Amsterdam: ‘perfect’ candidate (open and high-tech)
 Neighbourhood (buurt) → n = 96
Empirical equations
 Baseline
 Spatial lag
(expresses the value of the dependent variable
in the surrounding neighbourhood)
44
• Bi: the level of buzz in neighbourhood i,
• α: a constant term,
• Fi : a set of variables relating to the amount of
possibilities for buzz to occur in i,
• Ei : a group of variables describing different
characteristics of the urban form in i,
• Divi : the level of cultural diversity that
characterizes i,
• εi : a well-behaved error term

45. Location-sharing services and urban buzz
Location-sharing services (Foursquare)
 Online applications (services)
 Users, empowered by a location-aware device
connected to the internet such as a smartphone or
tablet, can share their geographical position at a given
point in time with their friends and broadcast it to the
internet
 Data from Fourquare (mostly)
Urban buzz
 The closest we can get to know where people are when
→ good measure of urban buzz
 Spatially and temporally (very) granular
45

46. Foursquare is popular
46
2010:
• 1,000,000 posts per day
• an increase of 3400%
• 381,576,305 posts in every single country (and one from
space!)
For more facts see: http: //blog/foursquare.com/2011/01/24/2010infographic

47. Anatomy of a checkin
47

48. Foursquare checkins in Amsterdam
Dataset
 Chen et al. (2011)
 ≈ 70,000 geo-located tweets posted from February
2010 to January 2011
 Within the boundaries of the municipality of
Amsterdam
48

49. Other data
Cultural diversity
Index of fractionalization
Control variables
 Foursquare categories
- Arts and Entertainment, College & University, Food, Other,
Outdoor & Recreation, Professional, Travel & Transport
 Land-use
-Industrial, office, sports, retail
Size
 Number of Foursquare venues and building units
49
• divr : diversity index in area r,
• M: the total number of different
cultural origins,
•C oBr: share of the population
with cultural origin i in area r.

50. Main results
50
The presence of office and of retail spacepresence of office and of retail space,
both functions that attract day-timeattract day-time
activityactivity, significantly increases the number
of check-ins an area receives
The strongest effect, unsurprisingly, comes
from the presence of venues in the
category ‘arts and entertainment’, in
which most cultural amenities, such as
museums and cinemas, are included as well
as some bars. This is in line with the
consumption amenity nature of
Foursquare check-in data and reinforces
the argument that they constitute a good
index of urban buzz.

51. Effect over different times of the weekEffect over different times of the week
The effect is lowest on a weekday morning and grows over the day to
reach its peak during the night of a weekday. Over the weekend, the
effect decreases a little in the morning but picks up again during the
evening and night. Except for the weekday mornings.
Users particularly prefer diverse neighbourhoods for the activities they
engage in at the end of the day or during the weekend
51

52. The management and policy uses of such massive data
call for intelligent data analysis; a compact
representation of ‘big data’ in cities may be helpful for:
 pattern recognitionpattern recognition of stocks and flows (eg, people, real estate,
infrastructure);
 provision of public servicesprovision of public services in urban hotspots (eg, ambulances,
police);
 monitoring of urban developmentsmonitoring of urban developments (eg, office developments,
commuting patterns, shopping behaviour, public transport use);
 identification of problem situationsidentification of problem situations or bottlenecks (eg, transport
management, crowd management);
 projection of future developmentsprojection of future developments (eg, accessibility,
congestion).

53. Summary
 Using a novel source of data that allows for very detailed spatial
identification, we study the effect of a diverse environment in the
levels of urban buzz
 We find a positive effect of cultural diversity on the levels of activity in
an area of the city
 This effect is stronger in times of the week with a high presence of
leisure in the time allocation
 Individuals positively value diverse environments → policy implications
to protect such characteristics
53

54. Thanks for your attentionThank You!Thank You!