Retail geography, Spatial analysis, Big data, Quantitative modeling
Harnessing Social Media Data to Explore Tourist Shopping Patterns in London
For global tourism destinations such as London, retail demand can be rather complicated. The complex mosaic of microgeographies in London results in mixed retail demand which is generated by not only residents but also other non-residential populations, including daily commuters, students, tourists etc. The spatial and temporal patterns of these non-residential demand types can influence retail centre and retail store trading characteristics, including store revenues. Whilst existing research has started to consider retail demand from workplaces (Berry et al., 2016) and domestic tourists (Newing et al., 2013) , the demand originating from overseas tourists has been the subject of limited research. The academic community and tourism sector have attempted to estimate inbound tourist expenditure for shopping as well as other disparate sectors, but such efforts have been deficient from a geographical perspective due to the data accessed from official surveys and research questionnaires often having little spatial detail below the regional level. Emerging georeferenced big data could provide new opportunities to capture information on tourist behaviours and expenditures at a more localised spatial scale. Birkin et al. (2017) exemplified the potential of social media data in informing the daily movement pattern and demographic fluctuations related to shopping activity and also suggested the possibility of these data for determining the global movement of travellers. Therefore, the purpose of this research is to use location-based social network (LBSN) data to explore the mobility patterns and potential retail demand of inbound tourist in the UK at a small area level focusing specifically on London.
In light of this, this research has the following aims:
- Review the potential of different kinds of LBSN data (Twitter, Flickr, Foursquare and Weibo) to obtain a richer insight into inbound international tourist mobility behaviours.
- Discuss the practical possibilities and evaluate the challenges of using multisource LBSN data in retail location analysis, in particular related to tourist retail demand.
- Generate a prototype tourist retail demand layer at the small-area level in London.
- 2006-2009: Msc Cartography and Geographical Information Engineering, China University of Geosciences (Wuhan
Dissertation: The Research and Realization of Parallel Spatial Operations in Simple Feature Model
- 2002-2006: BSc Geographic Information Systems (GIS), China University of Geosciences (Wuhan)
Dissertation: The Application of Mathematical Morphology and Pattern Recognition to Building Polygon generalization
- 2011-2017: Shandong Provincial Institute of Land Surveying and Mapping
- Research engineer / Public relations
- 2009-2011: Tencent, Inc.
- Back-end developer / E-commerce channel operation
Research groups and institutes
- Centre for Spatial Analysis and Policy