Happiness and High-rise Living: Sentiment Analysis of Geo-Located Twitter Data in Hong Kong’s Housing Estates

Jianxiang Huang, Qingpeng ZHANG, Lishuai LI, Yiyang Yang, Alain CHIARADIA, Matthew Pryor, Chris Webster

    Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

    Abstract

    The high-rise housing, a largely unfavorable housing type in Western context (Turkington et al. 2004; Jacobs 1961), is considered a success in Asia (Castells et al. 1990). Researchers argue that a high-rise housing estate, if properly designed and managed, can be a satisfactory solution for high-density cities (Yeh 2000; Yuen et al. 2006); systematic evidence supportive of the above arguments are rare (Turkington et al. 2004). Questions remain as whether high-rise living promotes or degrades happiness? What are the physical attributes that are linked to occupant sentiment in high-rise housing estates? We used sentiment analysis of Twitter data as a measure of occupant satisfaction with the living environment. Data were collected between May and June 2016 within 487 major housing estates in Hong Kong, covering a variety of building forms, density, and other built environment attributes while controlling for demographic, social and economic profiles. Results show that the design of high-rise buildings matter: the Twin-Towers and T-shaped buildings, both were popular housing types in the 70s, correlated with negative sentiment tones. Density, measured in units/ha, showed positive correlation with happy sentiment. Property age, block size, loan-to-income ratio, employment, and occupation were also correlated with sentiment tones. Findings have implication for urban planning and design.
    Original languageEnglish
    Title of host publicationProceedings of the 52nd ISOCARP Congress
    Place of PublicationDurban, South Africa
    Pages380-387
    Publication statusPublished - Sept 2016

    Bibliographical note

    The conference paper does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

    Fingerprint

    Dive into the research topics of 'Happiness and High-rise Living: Sentiment Analysis of Geo-Located Twitter Data in Hong Kong’s Housing Estates'. Together they form a unique fingerprint.

    Cite this