Using multi-source data to assess livability in hong kong at the community-based level : a combined subjective-objective approach

Abstract

With the emergence of new types of data (e.g. social media data) and cutting-edge computer technology (e.g. Natural Language Processing), the shortcomings of traditional methods (subjective and objective ways) for detecting urban livability can be overcome by an integrated approach. This study aims to develop a comprehensive approach to measure urban livability based on statistic data, geo-data (e.g. points of interest), questionnaires survey, and social media data (Instagram), from both objective and subjective angles. Hong Kong, as a city with a high level of urbanization and contrasting urban environments, is chosen as the study area in this research. Through this study, the question which area of Hong Kong is more suitable for living is answered by the visualization of GIS-based analysis. Also, the correlation between livability scores and individuals' sentiment scores are explored. Specifically, the results show that central areas of Hong Kong with a higher level of urbanization are relatively more livable than suburban regions. However, through sentiment analysis, individuals who post Instagram in suburban areas of Hong Kong usually express more positive content and happier emotion than those who post Instagram in central urban areas. The study could offer useful information for the policy action of authorities as well as the residential location choices of citizens.