Using social media user profiles to identify visitor demographics and origins in Yellowstone national park

Yun Liang, Junjun Yin, Soyoung Park, Bing Pan, Guangqing Chi, Zachary Miller

Research output: Contribution to journalArticlepeer-review

4 Scopus citations


Despite the growing body of studies on mining visitor perceptions and attitudes of national park visitors using social media data, few research investigated user demographics and its representative issues. This study assessed visitor demographics, including gender, age, racial groups, and origins of visitors in a U.S. national park through their Twitter user profiles, and compared the results to a traditional visitor survey. The results showed similar percentages of gender groups between Twitter user profiles and the traditional survey. However, significant differences existed across all age groups and all racial groups between the two data sources. Compared to the survey, the visitors identified from social media data were younger and from more diverse race groups. The lists of the top 10 states and countries of residency of visitors from the two data sources overlapped but had different orders. The findings indicated that social media data could only be a complementary data source due to its representative issues. The results allow researchers to explore social media users’ demographics by advanced social data analytics. However, this study suggests that analyzing Twitter profile information, such as self-reported names and profile photos, requires special attention from researchers even if the data were publicly available. The authors recommend that future research should attend to the representative and private issues of social media data. Management implications: • Social media user profiles can be utilized for predicting users’ demographics, such as gender, age, and racial groups. • Social media data can only be a conplementary data source to understand visitor demographics in future research. • The ethical issues of social media data, including private domain and machine learning algorithms, need further discussion.

Original languageEnglish (US)
Article number100620
JournalJournal of Outdoor Recreation and Tourism
StatePublished - Dec 2023

All Science Journal Classification (ASJC) codes

  • Tourism, Leisure and Hospitality Management

Cite this