Aviation Safety Report Data

This page is a distribution site of aviation safety report data for the task of Cause Identification. Data available on this page include a large corpus of unannotated aviation safety reports collected from the Aviation Safety Reporting System (ASRS) website and a smaller subset of these reports annotated with cause information.

The problem of Cause Identification for which this dataset is intended was described in:

Cause Identification Dataset

All narratives in each set have been subjected to some preprocessing to facilitate automatic analysis and to make them more easily readable by non-domain experts. This preprocessing includes the expansion of the acronyms and abbreviations found in the ASRS Decoded Abbreviations list and the partial restoration of case information to the caseless reports obtained from the ASRS website. In the labeled dataset, each report is human annotated with one or more shaping factors or shapers describing what factors may have contributed to (or caused) the incidents described therein. For a more complete description of the shaping factors, see this paper.

The creation of this website is based upon work supported in part by National Aeronautics and Space Administration (NASA) Grant NNX08AC35A and National Science Foundation (NSF) Grant IIS-0812261. Any opinions, findings, and conclusions or recommendations expressed above are those of the authors and do not necessarily reflect the views of NASA or NSF and should not be interpreted as representing the official policies, either expressed or implied, of any sponsoring institution, the U.S. government or any other entity.

If you have any questions or comments regarding this site, please send email to Isaac Persing.