Characterizing traveling fans: a workflow for event-oriented travel pattern analysis using Twitter data

ABSTRACT

Characterizing event attendees’ travel patterns is key to understanding the dynamics of social events in cities. However, the scientific investigation of event travel patterns has been hindered by the difficulty in gathering travel diaries of participants. Geotagged microblogs provide new opportunities for studying event travel patterns by offering rich locational and semantic information of attendees. Here, we develop, implement, and apply a workflow to characterize travel behaviors of event attendees with geotagged Twitter data, using college football events as a case study. The workflow includes five steps: 1) filtering event attendees using real-time geotagged tweets, 2) identifying origins of the event attendees using historical timeline tweets, 3) identifying past sports-related activities at travel destinations using topic modeling, 4) computing user movement features using origin-destination travel flows, and 5) identifying atypical travel patterns to characterize event attendees. The travel patterns uncovered in the study offer insights into user interests and travel behaviors related to sporting event attendance. The findings demonstrate that our method holds promise in revealing long-term event travel patterns (not limited to sporting events) through the use of geotagged microblogs.

KEYWORDS:

• Event travel patterns
• movement analysis
• Twitter
• sports tourism

Acknowledgments

We want to thank all anonymous reviewers and the editors Dr. May Yuan and Dr. Martin Tomko, for their insightful comments. We would also like to express our gratitude to Dr. Clio Andris, Dr. Benjamin Shaby, Dr. Justine Blanford, Thomas Kent, and Di Chen, for their valuable discussions and suggestions. We want to thank Mohammed Asif for his constructive criticism of the manuscript.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data and code availability statement

The data and code that support the findings of this study are available in figshare.com with the identifier http://doi.org/10.6084/m9.figshare.11991357.

Supplemental data

Supplemental data for this article can be accessed here.

Notes

1. The geolocated tweets posted by 13 users in 2016 during Penn State football games no longer existed in their timeline tweets when we downloaded the data.

2. Open Calais API. http://www.opencalais.com/.

3. The major sports venues dataset was downloaded in March 2019. https://hifld-geoplatform.opendata.arcgis.com/datasets/major-sport-venues.

Additional information

Notes on contributors

Yanan Xin

Yanan Xin is a Ph.D. candidate in Geography at the Pennsylvania State University. Her research interests are computational movement analysis, geovisual analytics, machine learning and deep learning, anomaly detection, and spatial statistics. More information is available at: https://www.geog.psu.edu/directory/yanan-xin

Alan M. MacEachren

Alan M. MacEachren is a Professor of Geography and Information Sciences & Technology at the Pennsylvania State University and is a Faculty Associate of the Institute for Computational Data Sciences. His research interests include geovisual analytics, geovisualization, exploratory spatial data analysis, place and big data, geosemantics, and geographical information retrieval. More information is available at: https://sites.psu.edu/ammaceachren/