The National Transportation Safety Board in the United States and the Transportation Safety Board of Canada publish reports about major railroad accidents. The text from these accident reports were analyzed using the text mining techniques of probabilistic topic modeling and k-means clustering to identify the recurring themes in major railroad accidents. The output from these analyses indicates that the railroad accidents can be successfully grouped into different topics. The output also suggests that recurring accident types are track defects, wheel defects, grade crossing accidents, and switching accidents. A major difference between the Canadian and U.S. reports is the finding that accidents related to bridges are found to be more prominent in the Canadian reports.
Skip Nav Destination
Close
Sign In or Register for Account
2016 Joint Rail Conference
April 12–15, 2016
Columbia, South Carolina, USA
Conference Sponsors:
- Rail Transportation Division
ISBN:
978-0-7918-4967-5
PROCEEDINGS PAPER
Text Mining Analysis of Railroad Accident Investigation Reports
Trefor Williams
,
Trefor Williams
Rutgers University, Piscataway, NJ
Search for other works by this author on:
John Betak
,
John Betak
Collaborative Solutions, LLC, Albuquerque, NM
Search for other works by this author on:
Bridgette Findley
Bridgette Findley
University of Texas-San Antonio, San Antonio, TX
Search for other works by this author on:
Trefor Williams
Rutgers University, Piscataway, NJ
John Betak
Collaborative Solutions, LLC, Albuquerque, NM
Bridgette Findley
University of Texas-San Antonio, San Antonio, TX
Paper No:
JRC2016-5757, V001T06A009; 5 pages
Published Online:
June 10, 2016
Citation
Williams, T, Betak, J, & Findley, B. "Text Mining Analysis of Railroad Accident Investigation Reports." Proceedings of the 2016 Joint Rail Conference. 2016 Joint Rail Conference. Columbia, South Carolina, USA. April 12–15, 2016. V001T06A009. ASME. https://doi.org/10.1115/JRC2016-5757
Download citation file:
- Ris (Zotero)
- Reference Manager
- EasyBib
- Bookends
- Mendeley
- Papers
- EndNote
- RefWorks
- BibTex
- ProCite
- Medlars
Close
Sign In
28
Views
0
Citations
Related Proceedings Papers
Related Articles
A Framework Based on K-Means Clustering and Topic Modeling for Analyzing Unstructured Manufacturing Capability Data
J. Comput. Inf. Sci. Eng (February,2020)
Energy Savings Due to Wheel/Rail Lubrication—Seaboard System Test and Other Investigations
J. Eng. Ind (May,1985)
Head Injury in Facial Impact—A Finite Element Analysis of Helmet Chin Bar Performance
J Biomech Eng (December,2000)
Related Chapters
Part of Speech Tagging
International Conference on Computer and Automation Engineering, 4th (ICCAE 2012)
Data Preprocessing in Web Text Mining
International Conference on Advanced Computer Theory and Engineering, 5th (ICACTE 2012)
Research on Internet Chinese News Geography Name Text Mining
Proceedings of the International Conference on Technology Management and Innovation