Revealing the relationship between spatio-temporal distribution of population and urban function with social media data

Li, Miaoyi; Shen, Zhenjiang; Xin-hua, Hao

doi:10.1007/s10708-016-9738-7

Cited by 46 publications

(37 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The time information in the check-in data indirectly reflects the relationship between the people and their facilities, such as temporarily shopping, permanently living, or regularly working. The relationship has been widely used to identify the city function zones and population mobility [74,75]. Hence, the adoption of check-in data acquired in different times may have different influences on the estimated accuracy.…”

Section: Influence Of the Acquisition Time Of Check-in Datamentioning

confidence: 99%

Fine-Resolution Population Mapping from International Space Station Nighttime Photography and Multisource Social Sensing Data Based on Similarity Matching

2019

View full text Add to dashboard Cite

Previous studies have attempted to disaggregate census data into fine resolution with multisource remote sensing data considering the importance of fine-resolution population distribution in urban planning, environmental protection, resource allocation, and social economy. However, the lack of direct human activity information invariably restricts the accuracy of population mapping and reduces the credibility of the mapping process even when external facility distribution information is adopted. To address these problems, the present study proposed a novel population mapping method by combining International Space Station (ISS) photography nighttime light data, point of interest (POI) data, and location-based social media data. A similarity matching model, consisting of semantic and distance matching models, was established to integrate POI and social media data. Effective information was extracted from the integrated data through principal component analysis and then used along with road density information to train the random forest (RF) model. A comparison with WordPop data proved that our method can generate fine-resolution population distribution with higher accuracy ( R 2 = 0.91 ) than those of previous studies ( R 2 = 0.55 ). To illustrate the advantages of our method, we highlighted the limitations of previous methods that ignore social media data in handling residential regions with similar light intensity. We also discussed the performance of our method in adopting social media data, considering their characteristics, with different volumes and acquisition times. Results showed that social media data acquired between 19:00 and 8:00 with a volume of approximately 300,000 will help our method realize high accuracy with low computation burden. This study showed the great potential of combining social sensing data for disaggregating fine-resolution population.

show abstract

Section: Influence Of the Acquisition Time Of Check-in Datamentioning

confidence: 99%

Fine-Resolution Population Mapping from International Space Station Nighttime Photography and Multisource Social Sensing Data Based on Similarity Matching

2019

View full text Add to dashboard Cite

show abstract

“…Others used geo‐tagged Flickr photos and their textual tags to detect urban areas of interest and their dynamics over time (Hu et al, ; Zhou, Xu, & Kimmons, ). Fourth, population distribution at a fine spatial scale (Yao et al, ) and its dynamics (Li, Shen, & Hao, ) can be estimated from social media data when paired with other socioeconomic covariates. Fifth, information on user interactions on social media can be used to infer spatial social networks and detect community boundaries (Shao, Zhang, & Li, ).…”

Section: Resultsmentioning

confidence: 99%

Big data‐enabled social sensing in spatial analysis: Potentials and pitfalls

Liao

Brown

Ding

et al. 2018

Transactions in GIS

View full text Add to dashboard Cite

Over the past decade, there has been an unprecedented boom in the application of big data derived from location‐aware technology in GIScience. However, reflections on data quality lead to concerns about inaccurate or even erroneous spatial analysis results. This article contributes a meta‐analysis of big data‐enabled social sensing in spatial analysis. Big data‐enabled research has substantially enhanced our understanding of human population distribution and dynamics, land use, travel behavior, movement patterns, and spatial social networks from city to country to global levels. However, the effectiveness of big data‐enabled social sensing can be undermined by five critical issues related to research design: data volume, spatial coverage, locational information quality, and representativeness across socioeconomic and demographic groups. We suggest a framework for addressing the inherent bias in spatial big data at multiple stages of the research lifecycle and applying them to appropriate topics and scales of applications.

show abstract

“…In traditional research, urban vitality is regarded as a part of urban planning research. It is considered as including the energy and power to promote urban development [35] and the basic elements for realizing the quality of urban life [36]. In recent years, there has been a growing number of studies on urban vitality.…”

Section: Evolution Of Scientific Activity: Prior Analysismentioning

confidence: 99%

“…On the hand, "growth" in this cluster means the patterns of growth of a city. For example, He used association rule analysis to explore the relationship between different urban growth patterns on urban vitality, and the results indicated that different forms of urban growth have different effects on urban vitality [36]. On the other hand, "growth" refers to the growth of urban trees [56,57].…”

Section: Abstract Co-occurrence Analysis: Main Topic Distribution Andmentioning

confidence: 99%

Visualization and Analysis of Mapping Knowledge Domain of Urban Vitality Research

Shi

Miao

2019

Sustainability

View full text Add to dashboard Cite

Mapping knowledge domain (MKD) is an important research technology in bibliometrics. It provides a visual perspective for researchers and helps researchers to clearly understand the general situations of specific research fields. Presently, MKD has been widely used in fields such as ecology and transportation safety. In this paper, we conduct a systematically bibliometric analysis of the development trend on urban vitality research by using VOSviewer software, and this work is based on the related articles published in the Science Citation Index Expanded (SCIE) and Social Sciences Citation Index (SSCI) between 1998 and 2018. In the implementation, we firstly introduce the annual numbers of articles, source journals, highly cited papers, and production countries relating to urban vitality research. Then, we adopt a keywords co-occurrence analysis to explore the topic distribution, research frontiers, and research trends of urban vitality research intuitively. Overall, the Mapped Knowledge Domain method has proved to be an effective way to assess research trends in specific disciplines and to contribute to researchers and governments with respect to management and decision-making on issues of science.

show abstract

Revealing the relationship between spatio-temporal distribution of population and urban function with social media data

Cited by 46 publications

References 12 publications

Fine-Resolution Population Mapping from International Space Station Nighttime Photography and Multisource Social Sensing Data Based on Similarity Matching

Fine-Resolution Population Mapping from International Space Station Nighttime Photography and Multisource Social Sensing Data Based on Similarity Matching

Big data‐enabled social sensing in spatial analysis: Potentials and pitfalls

Visualization and Analysis of Mapping Knowledge Domain of Urban Vitality Research

Contact Info

Product

Resources

About