BIROn - Birkbeck Institutional Research Online

    Geo-referencing as a connector between user reviews and urban environment quality

    Ballatore, Andrea and Pang, A. and Pozzana, Iacopo and Prifti, Y. and Provetti, Alessandro (2019) Geo-referencing as a connector between user reviews and urban environment quality. In: 5th International Conference on Computational Social Science IC2S2, 17-20 Jul 2019, Amsterdam, The Netherlands. (Unpublished)

    [img]
    Preview
    Text
    2019-Ballatore_et_al-IC2S2-User_Reviews_Urban.pdf - Author's Accepted Manuscript

    Download (306kB) | Preview

    Abstract

    The primary objective of this research is to understand the relationship between the positivity of user-generated content, namely Airbnb reviews and the “attractiveness” of the neighbourhood of the listing. Focussing on London wards and their Airbnb listings, we could identify some features which consistently signal positive sentiment and used best-subset selection to identify an overall relationship. We identified the types of features most commonly associated with positive sentiment before discussing how this information be used to influence urban development. Whilst analysis of the Airbnb market has been a popular area of study lately, to the best of our knowledge this specific research question has not been considered.

    Metadata

    Item Type: Conference or Workshop Item (Paper)
    Keyword(s) / Subject(s): User reviews; Geo-referenced data; Sentiment analysis; Urban Data Science
    School: Birkbeck Faculties and Schools > Faculty of Science > School of Computing and Mathematical Sciences
    Birkbeck Faculties and Schools > Faculty of Humanities and Social Sciences > School of Social Sciences
    Research Centres and Institutes: Data Analytics, Birkbeck Institute for
    Depositing User: Andrea Ballatore
    Date Deposited: 03 Sep 2019 13:01
    Last Modified: 09 Aug 2023 12:46
    URI: https://eprints.bbk.ac.uk/id/eprint/27360

    Statistics

    Activity Overview
    6 month trend
    63Downloads
    6 month trend
    240Hits

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item