Mining trips from location-based social networks for clustering travelers and destinations
- PDF / 3,278,105 Bytes
- 36 Pages / 439.37 x 666.142 pts Page_size
- 79 Downloads / 188 Views
Mining trips from location‑based social networks for clustering travelers and destinations Linus W. Dietz1 · Avradip Sen1 · Rinita Roy1 · Wolfgang Wörndl1 Received: 23 June 2019 / Revised: 3 January 2020 / Accepted: 21 January 2020 / Published online: 29 January 2020 © The Author(s) 2020
Abstract It is important to learn the characteristics of travelers and touristic regions when trying to generate recommendations for destinations to users. In this work, we first present a data-driven method to mine trips from location-based social networks to understand how tourists travel the world. These trips are quantified using a number of metrics to capture the underlying mobility patterns. We then present two applications that utilize the mined trips. The first one is an approach for clustering travelers in two case studies, one of Twitter and another of Foursquare, where the pure mobility metrics are enriched with social aspects, i.e., the kinds of venues into which the users checked-in. Clustering 133,614 trips from Twitter, we obtain three distinct clusters. In the Foursquare data set, however, six clusters can be determined. The second application area is the spatial clustering of destinations around the world. These discovered regions are solely formed by the mobility patterns of the trips and are, thus, independent of administrative regions such as countries. We identify 942 regions as destinations that can be directly used as a region model of a destination recommender system. This paper is the extended version of the conference article “Characterisation of Traveller Types Using Check-in Data from Location-Based Social Networks” presented at the 26th Annual ENTER eTourism Conference held from January 19 to February 1, 2019 in Nicosia, Cyprus. Keywords Mobility modeling · Cluster analysis · Spatial clustering · Recommender systems
1 Introduction Analyzing the mobility of travelers reveals a lot of information about their behavior, preferences, and the destinations they visit. This is interesting for a number of different purposes. Municipalities can obtain information about the popularity of destinations * Linus W. Dietz [email protected] 1
Technical University of Munich, Boltzmannstr. 3, 85748 Garching, Germany
13
Vol.:(0123456789)
132
L. W. Dietz et al.
within their district to build infrastructure and provide services in an informed way. Destination marketers can learn more about the context of their prospective guests and make improved offers to attract more visitors. Tourist agencies or travel recommender systems can characterize their clients and suggest serendipitous, yet accurate destinations to visit. Finally, prospective travelers can benefit from useful recommendations when planning their trips. Tourist mobility can be observed in different ways. Analyzing the number of accommodation bookings in a city, tracking ticket sales of flights or trains, or analyzing the congestion of highway connections only captures aggregate travel patterns of one destination or the connections between them. To pro
Data Loading...
