The opportunities for the use of SMGI in spatial planning guide the design of a user-friendly suite of tools, called SPATEXT (SPAtial-Temporal-tEXtual Toolbox), which eases the extraction and management of information from multiple social media platforms and the contextual integration in a GIS environment for analysis. The SPATEXT suite is implemented as Python 2.7 add-in for the commercial software ESRI ArcGIS©, including a number of ad-hoc developed tools, which may be used to (1) retrieve SMGI from social networks (including Twitter, YouTube, Wikimapia, Instagram, Instagram Places, Foursquare and Panoramio); (2) geocode or georeference data; and carry out analyses on the (3) spatial, (4) temporal, (5) textual and (6) user dimension of SMGI. In addition, the analytical methods available in the tool include several clustering algorithms in order to enable user profiling, user movement analysis, user behavioral analysis and land use detection, to name a few. Indeed, the collection, management and geocoding functionalities may turn any social media content into a workable SMGI dataset, which may then be directly integrated with other spatial data and analyzed in a GIS environment with off-the-shelf instruments.
Social Media Geographic Information (SMGI): opportunities for spatial planning and governance. 61 SPATEXT takes advantage of the available social media APIs to perform queries directly from the GIS interface, enabling the collection of multimedia information regarding different topics, time periods and geographic areas. This way, the extension of traditional GIS tools with SPATEXT tools may ease the integration of SMGI with A-GI, in order to support analysis, design and decision-making in urban and regional planning.
The tools included in SPATEXT are developed in order to deal with the hurdles regarding access, management and analysis of ‘big data’ and may be consequently categorized in three different classes:
1) data collection;
2) data management;
3) data analysis.
The first class includes user-friendly tools that enable information harvesting from several social networks through spatial, temporal or textual queries. These tools can facilitate the direct access to social networks APIs avoiding programming efforts. The second class provides tools developed to ease the management, the integration and the successive analysis in GIS environment of SMGI extracted from different sources.
Finally, the third class contains tools designed for analyzing the spatial, temporal and user dimensions of this information, as well as, for enabling the investigation of embedded textual contents. An overview of the SPATEXT functionalities is presented in Table 2, where the main tools are classified and briefly described according to the specific class functionality, while the SPATEXT architecture is shown in Figure 4.
SPATEXT SUITE TOOLS CATEGORY ‘DATA COLLECTION’
query parameters
Tool Name Function space time keyword
Instagram extractor Extracts Instagram SMGI to shapefile
YouTube extractor Extracts YouTube SMGI to shapefile
Instagram Places extractor Extracts Instagram Places SMGI to shapefile
Twitter extractor Extracts Twitter SMGI to shapefile
WikiMapia extractor Extracts Wikimapia SMGI to shapefile
Foursquare extractor Extracts Foursquare SMGI to shapefile
Panoramio extractor Extracts Panoramio SMGI to shapefile
CATEGORY ‘DATA MANAGEMENT’
function activation
Tool Name Function Manual Automatic
Geocode address Geocoding place/address from string
Geocode table Batch-Geocoding place/address from table
Georeferencing Georeferencing SMGI coordinates
Decomposition tools Decompose SMGI shapefile in multiple shapefiles Google™ Static Maps Add Google Static Map URL in SMGI attribute fields
Social Media Geographic Information (SMGI): opportunities for spatial planning and governance. 62 CATEGORY ‘DATA ANALYSIS’
SPATIAL AND CLUSTERING ANALYSIS
Tool Name Function
DB-SCAN (Density-Based SCAN)
Run DB-SCAN algorithm (Ester et al., 1996) on SMGI feature class to detect density clusters and add the cluster group in a new field of SMGI feature class
Feature-Based DB-SCAN Run FB-DBSCAN algorithm (Ester et al., 1996) on SMGI feature class to detect density clusters for each group in SMGI feature class (e.g. User)
Advanced SQL maximum SQL selection on a SMGI feature class to detect maximum values for a specific group (e.g. User Cluster exposing max number of points)
TEXTUAL ANALYSIS
Tool Name Function
Attribute to string Creation of a text file from an attribute field in a SMGI feature class for textual analysis
Attribute to table Creation of a table from an attribute field in a SMGI feature class for textual analysis Attribute to tag-cloud Tag-clouding analysis from an attribute field in a SMGI feature class
Selection to tag-cloud Tag-clouding analysis from a spatial/attribute selection in a SMGI feature class Text to tag-cloud Tag-clouding analysis from a text file
TEMPORAL ANALYSIS
Tool Name Function
Identify
Month/Weekday/Day/hour
Add the Month/Weekday/Day/hour of creation in a new field of SMGI feature class
Trend Day/hour Creation of a 24h/60min time graph and statistic report from SMGI feature class Table 2. SPATEXT tools.
Figure 4. SPATEXT architecture design.
Social Media Geographic Information (SMGI): opportunities for spatial planning and governance. 63 The tools included in SPATEXT are designed and developed in order to supply user-friendly tools to planners easing the development of spatial planning analyses concerning the use of SMGI for practices. Planning and especially urban planning are generally based on technical sectors and share some methods and tools with social sciences (Goldstein and Garmin, 2006). The discipline concerns both policies and practices, including a scientific basis built upon sociology, economics, environmental, sciences, geography and GIS (Zanon, 2014). Any advance in these sectors requires a specific expertise that further delineates a planner’s toolbox (Zanon, ibidem).
Nevertheless, the SMGI nature and the methods and tools required for exploit this information in practice, usually overtake the traditional competencies of a planner, which should deal with issues concerning programming, database creation, management and query on ‘big data’. In this respect, the SPATEXT suite is developed to address these later issues supplying a set of tools that might be proficiently used in practices to solve several problems concerning the access and the management of SMGI, and to ease the development of analytical processes.