Exploring Group Movement Pattern through Cellular Data: A Case Study of Tourists in Hainan

Abstract

Identifying group movement patterns of crowds and understanding group behaviors are valuable for urban planners, especially when the groups are special such as tourist groups. In this paper, we present a framework to discover tourist groups and investigate the tourist behaviors using mobile phone call detail records (CDRs). Unlike GPS data, CDRs are relatively poor in spatial resolution with low sampling rates, which makes it a big challenge to identify group members from thousands of tourists. Moreover, since touristic trips are not on a regular basis, no historical data of the specific group can be used to reduce the uncertainty of trajectories. To address such challenges, we propose a method called group movement pattern mining based on similarity (GMPMS) to discover tourist groups. To avoid large amounts of trajectory similarity measurements, snapshots of the trajectories are firstly generated to extract candidate groups containing co-occurring tourists. Then, considering that different groups may follow the same itineraries, additional traveling behavioral features are defined to identify the group members. Finally, with Hainan province as an example, we provide a number of interesting insights of travel behaviors of group tours as well as individual tours, which will be helpful for tourism planning and management.

Multi-Objective Optimal Travel Route Recommendation for Tourists by Improved Ant Colony Optimization Algorithm

“…However, there are two major shortcomings of these data types: (1) the rarefaction of the sample results in a fragmentary and improper description of the travel recommendation; (2) the completeness and precision of the travel blogs may also mislead the consequences of the analysis because the travel notes are usually written by memory from the tourists after their trip [39]. On the contrary, mobile phone signaling data can be collected for a large number of samples at a lower cost; meanwhile, it contains the accurate time and location information of the users [3]. erefore, in this research, we proposed a novel framework that preprocesses the mobile signaling data to transform raw trajectories into tourists' travel sequence and finds the popular attractions and the frequent travel sequences.…”

“…With the development of location acquisition technology, GPS, the cellular networks, social networks, and location-based services can acquire large amounts of spatiotemporal data in the shape of locus [3][4][5].…”

Measuring the Degree of Balance between Urban and Tourism Development: An Analytical Approach Using Cellular Data

“…Its unique random phone ID enables researchers to recognize different group interactions through their peculiar pattern of trip frequency and origin-destination [30], which enables a capability of identifying different profiles of local residents from temporary population such as commuters and visitors [31]. In this context, cellular data has been applied to optimize tourism development via identifying tourists' group movement patterns [32], measuring tourists' spatiotemporal preference on destination visiting [33]. It is also interesting to apply cellular data to identify the effect of tourists' party size on their tourism behavior [34].…”

Enhancing impersonation fraud detection on smart buildings physical access control systems: an anomaly-based approach using social groups trajectories data.

“…In (ZHU et al, 2019), the authors aimed to find groups of tourists from phone call detail records (CDRs). Trajectory similarity was one of the features used to accomplish this task, along with the province of origin of the phone.…”

“…Other application domains, such as credit cards (TRIPATHI; PAVASKAR, 2012), have much more data to work with, for example: users' home addresses, delivery address, network IP address, and amount of purchasing. The work (ZHU et al, 2019) uses call duration, origin and destination provinces. In order to make possible the use of groups in the presented model, some preprocessing steps are taken to build new features: checkpoints and clusters.…”