This paper aims at presenting a detailed analysis of domestic air passengers behavior during a major air-traffic disturbance, from two complementary passenger-centric perspective: A passenger mobility perspective and a passenger social media perspective. By leveraging over 5 billion records of mobile phone location data per day from a major carrier in the United States, passenger mobility can be reliably analyzed, no matter which airline the passengers fly on or which airport they fly to and from. Such information is currently unavailable to the major aviation stakeholders at such scale and can be used to establish performance benchmarks from a passenger's perspective. Combining it with a Twitter analysis provides a more detailed and passenger-focused analysis than the traditional flight-centric measurements used to evaluate the overall system performance. More generally, these two passenger-centric analysis could be implemented in real-time for a daily evaluation of the Air Transportation System, enabling a faster analysis of the impact of major disruptions, whether due to meteorological conditions or system failures.
|Original language||English (US)|
|Title of host publication||IEEE International Conference on Data Mining Workshops, ICDMW|
|Publisher||IEEE Computer Societyhelp@computer.org|
|Number of pages||8|
|State||Published - Feb 7 2019|