In the big data era, large and complex data sets will exceed scientists’ capacity to make sense of them in the traditional way. New approaches in data analysis, supported by computer science, will be necessary to address the problems that emerge with the rise of big data. The analysis of the Close Call database, which is a text-based database for near-miss reporting on the GB railways, provides a test case. The traditional analysis of Close Calls is time consuming and prone to differences in interpretation. This paper investigates the use of visual analytics techniques, based on network text analysis, to conduct data analysis and extract safety knowledge from 500 randomly selected Close Call records relating to worker slips, trips and falls. The results demonstrate a straightforward, yet effective, way to identify hazardous conditions without having to read each report individually. This opens up new ways to perform data analysis in safety science.
|Number of pages||8|
|Journal||Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit|
|Early online date||28 Oct 2016|
|Publication status||Published - 1 Nov 2017|
Figueres-Esteban, M., Hughes, P., & Van Gulijk, C. (2017). Using visual analytics to make sense of railway Close Calls. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 231(10), 1107-1114. https://doi.org/10.1177/0954409716676221