Inferring Urban Land Use Using Large-Scale Social Media Check-in Data

Emerging location-based services in social media tools such as Foursquare and Twitter are providing an unprecedented amount of public-generated data on human movements and activities. This novel data source contains valuable information (e.g., geo-location, time and date, type of places) on human ac...

Full description

Saved in:
Bibliographic Details
Published in:Networks and spatial economics Vol. 14; no. 3-4; pp. 647 - 667
Main Authors: Zhan, Xianyuan, Ukkusuri, Satish V., Zhu, Feng
Format: Journal Article
Language:English
Published: Boston Springer US 01.12.2014
Springer Nature B.V
Subjects:
Algorithms
Analysis
Cellular telephones
Civil Engineering
Data mining
Datasets
Digital media
Economics
Economics and Finance
Human
Inference
Land use
Learning
Location based services
Movements
Operations Research/Decision Theory
Regional/Spatial Science
Sensors
Smartphones
Social networks
Studies
Social media
Clustering algorithms
Geo-location data
Data mining
Land use
Foursquare
Supervised learning algorithms
ISSN:1566-113X, 1572-9427
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Emerging location-based services in social media tools such as Foursquare and Twitter are providing an unprecedented amount of public-generated data on human movements and activities. This novel data source contains valuable information (e.g., geo-location, time and date, type of places) on human activities. While the data is tremendously beneficial in modeling human activity patterns, it is also greatly useful in inferring planning related variables such as a city’s land use characteristics. This paper provides a comprehensive investigation on the possibility and validity of utilizing large-scale social media check-in data to infer land use types by applying the state-of-art data mining techniques. Two inference approaches are proposed and tested in this paper: the unsupervised clustering method and supervised learning method. The land use inference is conducted in a uniform grid level of 200 by 200 m. The methods are applied to a case study of New York City. The validation result confirms that the two approaches effectively infer different land use types given sufficient check-in data. The encouraging result demonstrates the potential of using social media check-in data in urban land use inference, and also reveals the hidden linkage between the human activity pattern and the underlying urban land use pattern.
Bibliography:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:1566-113X
1572-9427
DOI:10.1007/s11067-014-9264-4