A cross-analysis framework for multi-source volunteered, crowdsourced, and authoritative geographic information: The case study of volunteered personal traces analysis against transport network data

Abstract

The paper discusses the need of a high-level query language to allow analysts, geographers and, in general, non-programmers to easily cross-analyze multi-source VGI created by means of apps, crowd-sourced data from social networks and authoritative geo-referenced data, usually represented as JSON data sets (nowadays, the de facto standard for data exported by social networks). Since an easy to use high-level language for querying and manipulating collections of possibly geo-tagged JSON objects is still unavailable, we propose a truly declarative language, named J-CO-QL, that is based on a well-defined execution model. A plug-in for a GIS permits to visualize geo-tagged data sets stored in a NoSQL database such as MongoDB; furthermore, the same plug-in can be used to write and execute J-CO-QL queries on those databases. The paper introduces the language by exemplifying its operators within a real study case, the aim of which is to understand the mobility of people in the neighborhood of Bergamo city. Cross-analysis of data about transportation networks and VGI from travelers is performed, by means of J-CO-QL language, capable to manipulate and transform, combine and join possibly geo-tagged JSON objects, in order to produce new possibly geo-tagged JSON objects satisfying users’ needs.

Keywords:

• Cross-analysis framework
• comparing VGI
• crowd-sourced and authoritative geographical data
• JSON data-sets
• declarative query language
• heterogeneous data-sets

Notes

1 http://www.gbif.org/dataset/50c9509d-22c7-4a22-a47d-8c48425ef4a7.

2 http://ebird.org/content/ebird/.

3 https://apps.moves-app.com/.

4 MongoDB: https://www.mongodb.com/ CouchDB: http://docs.couchdb.org/en/2.0.0/.

5 www.couchbase.com/n1ql.

6 www.jsoniq.org.

7 The connection URL has the URI form mongodb://user:[email protected]/the_database?authMechanism=SCRAM-SHA-1.

8 In J-CO-QL, fields are referenced by a dot notation which starts with a dot. For Example, .location is a field in the root level of the object, .location.item.lat references a field lat contained in the upper object field item that, in turns, is contained in the root object field location. The “.” at the beginning means that we start from the root of the object, i.e. the most external level of the object.