Understanding travellers’ spatial preferences based on mobile internet usage data

New mobility data sources like mobile phone traces are able to reveal individuals’ movements in space and time. However, socioeconomic attributes of travellers are missing in those data for privacy reasons. Consequently, it is difficult to explain the difference between travel behavior of different kinds of people. This study proposed to use mobile internet usage, including one’s favorite type of websites and apps as well as the intensity level of mobile internet usage, to distinguish different population segments and further explain behavioral heterogeneity.

The method consists of three parts:

  • Clustering grid cells of a city to reflect the main function of a grid cell by using the point of interest (POI) data, as a proxy for types of trip destination,
  • Distinguishing population segments based on mobile internet usage, and
  • Comparing the travel behaviour of each segment in terms of their preferences for types of trip destination.

The method was tested in the city of Shanghai, China, by using a special mobile phone dataset that includes not only spatial-temporal traces but also mobile internet usage of the same users. We identified significant associations between a traveller’s favourite category of mobile internet content and more frequent types of trip destinations that he/she visited. For example, compared to others, people whose favourite type of app/website is “tourism” seem to prefer touristy areas. Moreover, users with different levels of internet usage intensity show different preferences for types of destination as well. We found that people who used mobile internet more intensively were more likely to visit more commercial areas, and people who used it less preferred to have activities in predominantly residential areas.

Wang, Yihong, Gonçalo Homem de Almeida Correia, Bart van Arem, and HJP Harry Timmermans. “Understanding travellers’ preferences for different types of trip destination based on mobile internet usage data.” Transportation Research Part C: Emerging Technologies 90 (2018): 247-259.