Human Error in Maritime Operations: Analyses of Accident Reports Using the Leximancer Tool

Notes

Grech, M.R., Horberry, T. and Smith, A. (2002) 'Human Error in Maritime Operations: Analyses of Accident Reports Using the Leximancer Tool', *Proceedings of the Human Factors and Ergonomics Society Annual Meeting*, 46(19), pp. 1718–1721. doi: 10.1177/154193120204601906. Analyses 177 merchant-shipping accident reports (eight countries, 1987–2001) for loss of Situation Awareness using a three-level taxonomy adapted from Endsley (1995), comparing manual coding (26 reports, two raters) against the Leximancer machine-learning text-analysis tool. Finds 71% of human errors were SA-related (58.5% level 1, 32.7% level 2, 8.8% level 3) and that Leximancer matched manual coding (no significant difference; precision >84%, recall 89% on the abridged subset). RAW PDF is the author manuscript (5 pp.); the published version-of-record runs pp. 1718–1721 — locators use PDF page numbers.

```bibtex
@article{grech2002human,
  author  = {Grech, Michelle R. and Horberry, Tim and Smith, Andrew},
  title   = {Human Error in Maritime Operations: Analyses of Accident Reports Using the Leximancer Tool},
  journal = {Proceedings of the Human Factors and Ergonomics Society Annual Meeting},
  year    = {2002},
  volume  = {46},
  number  = {19},
  pages   = {1718--1721},
  doi     = {10.1177/154193120204601906}
}
```

Related Articles

Notes