Estimating mobility of tourists. New Twitter-based procedure

Area of Science:

• Social media analytics
• Geospatial data science
• Human mobility studies

Background:

• Twitter is frequently used as a proxy for human mobility research.
• Tweets can possess explicit geographical metadata or lack it entirely.
• Identifying the origin and movement of individuals is crucial for understanding mobility patterns.

Purpose of the Study:

• To develop and present a novel methodology for estimating geographical coordinates of tweets.
• To determine the origin and travel routes of tourists using Twitter data, even when explicit location data is absent.
• To enhance the utility of social media data for human mobility research.

Main Methods:

• An algorithm was developed to estimate geographical coordinates for tweets lacking explicit metadata.
• Geographical searches were performed within defined areas to locate relevant tweets.
• An iterative approach with a decreasing search radius was employed to pinpoint tweet locations.
• The methodology was tested in tourist locations in Madrid, Spain, and a Canadian city.

Main Results:

• A set of tweets without geographical coordinates were identified in the studied areas.
• The developed algorithm successfully estimated the geographical coordinates for a subset of these tweets.
• The methodology demonstrated effectiveness in inferring location data for anonymized tweets.

Conclusions:

• The proposed algorithm offers a viable solution for geolocating tweets with missing metadata.
• This approach can significantly improve the accuracy of human mobility studies using social media data.
• The findings contribute to a better understanding of tourist movements and behavior through enhanced geospatial analysis.