Please use this identifier to cite or link to this item: http://hdl.handle.net/10125/49932

Does Daily Travel Pattern Disclose People’s Preference?

File SizeFormat 
paper0045.pdf1.26 MBAdobe PDFView/Open

Item Summary

Title: Does Daily Travel Pattern Disclose People’s Preference?
Authors: Gan, Mingxin
Gao, Ling
Han, Yang
Keywords: IT Enabled Collaboration for Development
daily travel pattern,location-based social network,recurrence ratio,preference analysis,lifestyle
Issue Date: 03 Jan 2018
Abstract: Existing studies normally focus on extracting temporal or periodical patterns of people’s daily travel for location based services. However, people’s characteristics and preference are actually paid much more attention by business. Therefore, how to capture characteristics from their daily travel patterns, is an interesting question. In order to address the research question, we first develop two basic measures in terms of repetitiveness of travel and then two advanced measures, to capture people’s activity of daily travel, and the colorfulness of lifestyle, respectively. Incorporating historical trajectories, with real-time positions from a location-based social network (LBSN), i.e. Foursquare, we conduct statistical analysis for people’s travel patterns in US cities. Finally, we illustrate people’s profiles of travel patterns and lifestyles. Results show that people’s preference can be inferred from the developed activity and colorfulness measures. Those findings demonstrate that proposed measures are supposed to be effectively adopted for researchers on travel pattern analysis and preference analysis, and further give suggestions to individuals for location-based decision making.
Pages/Duration: 10 pages
URI/DOI: http://hdl.handle.net/10125/49932
ISBN: 978-0-9981331-1-9
DOI: 10.24251/HICSS.2018.045
Rights: Attribution-NonCommercial-NoDerivatives 4.0 International
Appears in Collections:IT Enabled Collaboration for Development


Please contact sspace@hawaii.edu if you need this content in an ADA compliant alternative format.

Items in ScholarSpace are protected by copyright, with all rights reserved, unless otherwise indicated.