Pattern mining in tourist attraction visits through association rule learning on Bluetooth tracking data: A case study of Ghent, Belgium

An empirical case study on the mining of association rules in tourist attraction visits, registered for 15 days by the Bluetooth tracking methodology is presented, finding interesting associations and identifying a tendency of visitors to rarely combine visits in the center with visits outside of the city center.

Abstract

The rapid evolution of information and positioning technologies, and their increasing adoption in tourism management practices allows for new and challenging research avenues. This paper presents an empirical case study on the mining of association rules in tourist attraction visits, registered for 15 days by the Bluetooth tracking methodology. This way, this paper aims to be a methodological contribution to the field of spatiotemporal tourism behavior research by demonstrating the potential of ad-hoc sensing networks in the non-participatory measurement of small-scale movements. An extensive filtering procedure is followed by an exploratory analysis, analyzing the discovered associations for different visitor segments and additionally visualizing them in ‘visit pattern maps’. Despite the limited duration of the tracking period, we were able to discover interesting associations and further identified a tendency of visitors to rarely combine visits in the center with visits outside of the city center. We conclude by discussing both the potential of the employed methodology as well as its further issues.