Text Mining for Procedure-Level Primitives in Human Reliability Analysis

  • Sarah M. EwingEmail author
  • Ronald L. Boring
  • Martin Rasmussen
  • Thomas Ulrich
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 589)


The classification of nuclear power plant procedures at the sub-task level can be accomplished via text mining. This method can inform dynamic human reliability calculations without manual coding. Several approaches to text classification are considered with results provided. When a discrete discriminant analysis is applied to the text, this results in clear identification procedure primitive greater than 88% of the time. Other analysis methods considered are Euclidian difference, principal component analysis, and single value decomposition. The text mining approach automatically decomposes procedure steps as Procedure Level Primitives, which are mapped to task level primitives in the Goals, Operation, Methods, and Section Rules (GOMS) human reliability analysis (HRA) method. The GOMS-HRA method is used as the basis for estimating operator timing and error probability. This approach also provides a tool that may be incorporated in dynamic HRA methods such as the Human Unimodel for Nuclear Technology to Enhance Reliability (HUNTER) framework.


Human reliability analysis Computation-based human reliability analysis Human error GOMS-HRA Text mining 



Every effort has been made to ensure the accuracy of the findings and conclusions in this paper, and any errors reside solely with the authors. This work of authorship was prepared as an account of work sponsored by Idaho National Laboratory, an agency of the United States Government. Neither the United States Government, nor any agency thereof, nor any of their employees makes any warranty, express or implied, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness of any information, apparatus, product, or process disclosed, or represents that its use would not infringe privately owned rights. Idaho National Laboratory is a multi-program laboratory operated by Battelle Energy Alliance LLC for the United States Department of Energy under Contract DE-AC07-05ID14517.


  1. 1.
    Boring, R., Rasmussen, M., Ulrich, T., Ewing, S., Mandelli, D.: Task and procedure level primitives for modeling human error. In: Proceedings of the 8th Applied Human Factors and Ergonomics, Los Angeles (2017, in press)Google Scholar
  2. 2.
    Ulrich, T., Boring, R., Ewing, S., Rasmussen, M., Mandelli, D.: Operator timing of task level primitives for use in computation-based human reliability analysis. In: Proceedings of the 8th Applied Human Factors and Ergonomics, Los Angeles (2017, in press)Google Scholar
  3. 3.
    Gupta, V., Lehal, G.S.: A survey of text mining techniques and applications. J. Emerg. Technol. Web Intell. 1, 60–76 (2009)Google Scholar
  4. 4.
    U.S. NPP Generating Station, “EXCESSIVE RCS LEAKRATE”Google Scholar
  5. 5.
    U.S. NPP Nuclear Generating Station, “STANDARD POST TRIP ACTIONS”Google Scholar
  6. 6.
    U.S. NPP Nuclear Generating Station, “The Steam Generator Tube Rupture”Google Scholar
  7. 7.
    U.S. NPP Nuclear Generating Station, “Panel 6 Alarm Responses”Google Scholar
  8. 8.
    U.S. NPP Nuclear Generating Station, “Panel 7 Alarm Responses”Google Scholar
  9. 9.
    U.S. NPP Nuclear Generating Station, “Loss of Charging or Letdown”Google Scholar
  10. 10.
    U.S. NPP Nuclear Generating Station, “Main Turbine”Google Scholar
  11. 11.
    R Core Team: R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria (2016)Google Scholar
  12. 12.
    SAS Institute Inc: Base SAS® 9.3 Procedures Guide. SAS Institute Inc., Cary, NC (2011)Google Scholar
  13. 13.
    Procedure Professionals Association: Procedure Writer’s Manual PPA AP-907-005 R2 (2016)Google Scholar
  14. 14.
    Murtagh, F.: Multivariate Data Analysis with Fortran, C and Java Code. Queen’s University Belfast, and Astronomical Observatory Strasbourg, BelfastGoogle Scholar
  15. 15.
    Albright, R.: Taming Text with the SVD. SAS Institute Inc, Cary (2004)Google Scholar
  16. 16.
    Knoke, J.D.: Discriminant analysis with discrete and continuous variables. Biometrics 38(1), 191–200 (1982)MathSciNetCrossRefGoogle Scholar
  17. 17.
    Hocking, R.R.: A biometrics invited paper. the analysis and selection of variables in linear regression. Biometrics 32(1), 1–49 (1976)MathSciNetCrossRefzbMATHGoogle Scholar
  18. 18.
    Beal, D.J.: Information criteria methods in SAS for multiple linear regression models. In: 15th Annual South East SAS Users Group (SESUG) Proceedings, South Carolina (2007)Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  • Sarah M. Ewing
    • 1
    Email author
  • Ronald L. Boring
    • 1
  • Martin Rasmussen
    • 2
  • Thomas Ulrich
    • 1
  1. 1.Idaho National LaboratoryIdaho FallsUSA
  2. 2.NTNU Social ResearchStudio AperturaTrondheimNorway

Personalised recommendations