Extraction and analysis of city's tourism districts based on social media data

Through the perspective of tourism, a city as a tourist destination usually consists of multiple tourist attractions such as natural or cultural scenic spots. These attractions scatter in city spaces following some specific forms: clustered in some regions and dispersed in others. It is known that u...

Full description

Saved in:
Bibliographic Details
Published in:Computers, environment and urban systems environment and urban systems, 2017-09, Vol.65, p.66-78
Main Authors: Shao, Hu, Zhang, Yi, Li, Wenwen
Format: Article
Language:English
Subjects:
Cities
Costs
Digital media
Districts
Division
Experiments
Mass media
Social media
Social networks
Spatial-temporal behavior
Tourism
Tourism district
Tourist attractions
Urban planning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Through the perspective of tourism, a city as a tourist destination usually consists of multiple tourist attractions such as natural or cultural scenic spots. These attractions scatter in city spaces following some specific forms: clustered in some regions and dispersed in others. It is known that users organize their tours in a city not only according to the distance between different attractions but also according to other factors such as time constraints, expenses, interests, and the similarities between different attractions. Hence, users' travel tours can help us gain a better understanding about the relationships among different attractions at the city scale. In this paper, a methodological framework is developed to detect tourists' spatial-temporal behaviors from social media data, and then such information is used to extract and analyze city's tourism districts. We believe that this city space division will make significant contributions to the fields of urban planning, tourism facility providing, and scenery area constructing. A typical tourism city in China—Huangshan—is selected as our study area for experiments. •Introduced social media data to tourism study.•Developed a novel data-driven method to extract city's tourism districts through mining tourist's spatiotemporal behaviors.•Extracted six core tourism districts of Huangshan City in China and analyzed their spatial distribution patterns.•Our methodology can be used for long-term monitoring of city tourism districts' developing and reshaping process.
ISSN:0198-9715
1873-7587
DOI:10.1016/j.compenvurbsys.2017.04.010