Young drivers and cellphone distraction: Pattern recognition from fatal crashes

More than 30% of cellphone-distracted fatal crashes occurred to drivers younger than 25-years-old in 2018, even though they constitute less than 12% of total licensed drivers in the U.S. Using joint correspondence analysis (JCA), this study analyzed six years (2014–2019) of cellphone-related fatal crashes involving young drivers based on the data from the Fatality Analysis Reporting System (FARS). This unsupervised learning algorithm can graphically display the co-occurrence of variable categories in a lower-dimensional space by effectively summarizing the knowledge of a complex crash dataset. The Boruta algorithm was applied to select the relevant features from the preliminary crash dataset. The empirical results of JCA manifest a few interesting fatal crash patterns. For example, young male drivers in light trucks were involved in deadly collisions while performing specific cellphone activities (other than talking and listening), cellphone-related fatal crashes occurred to young females with prior crash records, and so on. Apart from alcohol and drug involvement, this study identified young drivers’ additional risk-taking maneuvers while engaged in cellphone usage, including: disregarding traffic signs and signals, speeding, and unrestrained driving. The associations could guide the safety officials and policymakers in developing appropriate engineering, education, and enforcement strategies when dealing with cellphone-distracted young drivers.

  • Record URL:
  • Availability:
  • Supplemental Notes:
    • © 2022 Taylor & Francis Group, LLC and The University of Tennessee 2022. Abstract reprinted with permission of Taylor & Francis.
  • Authors:
    • Hossain, Md Mahmud
    • Zhou, Huaguo
    • Das, Subasish
    • Sun, Xiaoduan
    • Hossain, Ahmed
  • Publication Date: 2023-3


  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01879334
  • Record Type: Publication
  • Files: TRIS
  • Created Date: Apr 17 2023 9:01AM