Tourist attractions are dispersed across wide geographic areas even within the cities
making the data collection prohibitively expensive. For these reasons, information
on tourism destinations should be collected automatically. Recently, the collection
of particular data on destinations has become easier with the growing popularity of
location-based applications. Based on Google Popular Time (GPT), behavioral data are
collected to investigate the actual tourist behavior. The statistical analysis clearly
shows the presence of outliers in the collected data. Consequently, a regression model
based robust approach is used to study the tourists' processing time (i.e., the time
spent) at various tourism destinations in Budapest. Such spatial parameters are adopted
as car parking, public transport station, and location. The statistical outcomes present
that the availability of car parking or public transport stations significantly affects
the tourists' processing time at the tourism destinations. The findings demonstrate
the benefit of usingGPT and other online resources to analyze and predict individual
behavior. Furthermore, current study reveals that location-based services provide
a principal option for tourists during their journeys.