Mining point-of-interest data from social networks for urban land use classification and disaggregation (original) (raw)
Related papers
Inferring Urban Land Use Using Large-Scale Social Media Check-in Data
Networks and Spatial Economics, 2014
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.
Understanding the dynamics of urban areas of interest through volunteered geographic information
Journal of Geographical Systems
Obtaining insights about the dynamics of urban structure is crucial to the framing of the context within the smart city. This paper focuses on urban areas of interest (UAOI), a concept that provides functional definitions of a city's spatial structure. Traditional sources of social data can rarely capture these aspects at scale while spatial information on the city alone does not capture how the population values different parts of the city and in different ways. Hence, we leverage volunteered geographic information (VGI) to overcome some of the limits of traditional sources in providing urban structural and functional insights. We use a special type of VGImetadata from geotagged Flickr images-to identify UAOIs and exploit their temporal and spatial attributes. To do this, we propose a methodological strategy that combines hierarchical density-based spatial clustering for applications with noise and the 'α-shape' algorithm to quantify the dynamics of UAOIs in Inner London for a period 2013-2015 and develop an innovative visualisation of UAOI profiles from which UAOI dynamics can be explored. Our results expand and improve upon the previous literature on this topic and provide a useful reference for urban practitioners who might wish to include more timely information when making decisions.
Sustainability
In fast-growing cities, especially large cities in developing countries, land use types are changing rapidly, and different types of land use are mixed together. It is difficult to assess the land use types in these fast-growing cities in a timely and accurate way. To address this problem, this paper presents a multi-source data mining approach to study dynamic urban land use patterns. Spatiotemporal social media data reveal human activity patterns in different areas, social media text data reflects the topics discussed in different areas, and Points of Interest (POI) reflect the distribution of urban facilities in different regions. Human activity patterns, topics of discussion on social media, and the distribution of urban facilities in different regions were combined and analyzed to infer urban land use patterns. We collected 9.5 million geo-tagged Chinese social media (Sina-Weibo) messages from January 2014 to July 2014 in the urban core areas of Beijing and compared them with 385,792 commercial Points of Interest (POI) from Datatang (a Chinese digital data content provider). To estimate urban land use types and patterns in Beijing, a regular grid of 400 m × 400 m was created to divide the urban core areas into 18,492 cells. By analyzing the temporal frequency trends of social media messages within each cell using K-means clustering algorithm, we identified seven types of land use clusters in Beijing: residential areas, university dormitories, commercial areas, work areas, transportation hubs, and two types of mixed land use areas. Text mining, word clouds, and the distribution analysis of POI were used to verify the estimated land use types successfully. This study can help urban planners create up-to-date land use patterns in an economic way and help us better understand dynamic human activity patterns in a city.
Social Sensing for Urban Land Use Identification
ISPRS International Journal of Geo-Information
The utilization of urban land use maps can reveal the patterns of human behavior through the extraction of the socioeconomic and demographic characteristics of urban land use. Remote sensing that holds detailed and abundant information on spectral, textual, contextual, and spatial configurations is crucial to obtaining land use maps that reveal changes in the urban environment. However, social sensing is essential to revealing the socioeconomic and demographic characteristics of urban land use. This data mining approach is related to data cleaning/outlier removal and machine learning, and is used to achieve land use classification from remote and social sensing data. In bicycle and taxi density maps, the daytime destination and nighttime origin density reflects work-related land uses, including commercial and industrial areas. By contrast, the nighttime destination and daytime origin density pattern captures the pattern of residential areas. The accuracy assessment of land use class...
The global spread of internet access and the ubiquity of internet capable devices has lead to an increased online presence on the behalf of companies and businesses, namely in collaborative platforms called local directories, where Points-of-Interest (POIs) are usually classified with a set of categories and tags. Such information can be extremely useful, especially if aggregated under a common (shared) taxonomy. This article proposes a complete framework for the urban planning task of disaggregated employment size estimation based on collaborative online POI data, collected using web mining techniques. In order to make the analysis possible, we present a machine learning approach to automatically classify POIs to a common taxonomy-the North American Industry Classification System. This hierarchical taxonomy is applied in many areas, particularly in urban planning, since it allows for a proper analysis of the data at different levels of detail, depending on the practical application at hand. The classified POIs are then used to estimate disaggregated employment size, at a finer level than previously possible, using a maximum likelihood estimator. We empirically show that the automatically-classified online POIs are competitive with proprietary gold-standard POI data. This fact is then supported through a set of new visualizations that allow us to understand the spatial distribution of the classification error and its relation with employment size error.
Could Data from Location-Based Social Networks Be Used to Support Urban Planning
A great quantity of information is required to support urban planning. Usually there are many (not integrated) data sources, originating from different government bodies, in distinct formats and variable properties (e.g. reliability, completeness). The effort to handle these data, integrate and analyze them is high, taking to much time for the information to be available to help decision making. We argue that data from location-based social networks (LBSN) could be used to provide useful information in reasonable time, despite several limitations they have. To asses this, as a case study, we used data from different LBSN to calculate the Local Availability Index (IOL) for a Brazilian city. This index is part of a methodology to estimate quality of urban life inside cities and is used to support urban planning. The results suggest that data from LBSN are useful and could be used to provide insights for local governments.
Journal of Transport and Land Use, 2019
Location-based social networks (LBSN) are social media sites where users check-in at venues and share content linked to their geo-locations. LBSN, considered to be a novel data source, contain valuable information for urban planners and researchers. While earlier research efforts focused either on disaggregate patterns or aggregate analysis of social and temporal attributes, no attempt has been made to relate the data to transportation planning outcomes. To that extent, the current study employs LBSN service-based data for an aggregate-level transportation planning exercise by developing land-use planning models. Specifically, we employ check-in data aggregated at the census tract level to develop a quantitative model for activity intensity as a function of land use and built-environment attributes for the New York City (NYC) region. A statistical exercise based on clustering of census tracts and negative binomial regression analyses are adopted to analyze the aggregated data. We de...