Today there are more and more sensors measuring data. Also, large amounts of data can be stored and analyzed more and more easily. This offers opportunities for human factors research. The data can be used to gain insight into the behavior that actually takes place in your organization. And more importantly, which factors influence that behavior.
Measuring behavior directly or indirectly
It is often possible to use data that is already being measured to gain insight into behavior. For example, speed and location data from trains can provide insight into driver behavior. Other examples of data that (indirectly) says something about behavior:
- the number of times a certain app is opened
- the time between receiving a report and the dispatching of emergency services
- the number of contact moments between employees at different locations during maintenance.
Influencing factors
For human factors research, it is not necessary to link the data to individuals. Instead, it is more interesting to see what factors influence the behavior of all employees. For example, does the data look different:
- during night shifts or day shifts?
- when we introduce a safety intervention?
- under different infrastructure conditions?
- when we change the interface or software?
- at specific locations?
- during specific tasks?
- in different weather conditions, such as fog or very low or high temperatures?
Advantages of big data for human factors
There are several advantages to using big data for human factors research and consulting. The three biggest advantages compared to other methods:
- Prioritization. You can examine how big an influence each factor has. So you can find out which factors do not have such a big influence and which factors actually have a very big influence.
- Specification. You can see under what circumstances a factor has a big influence and under what circumstances it does not. This allows for more targeted interventions.
- No or limited extrapolation needed. The data measures the actual behavior of your employees in your organization. This gives more certainty about the (size of the) influence of the factor. It also makes the evidence more credible.
Big data for safety
Want to start using big data as a security department, but don’t know where to start? Then I recommend my ‘four data steps’ model.
Feel free to contact me for a session on the ‘four data steps’ model. During this session we will get to work directly with the model. This session is for security consultants. Attendance by data colleagues can help put the results into practice even faster. See my page DataForSafety for more information about the model.
A presentation on using Big Data for Human Factors?
My papers on this topic
Big data research on human factors in rail
Burggraaf J, Groeneweg J, Sillem S, van Gelder P. What Employees Do Today Because of Their Experience Yesterday: How Incidental Learning Influences Train Driver Behavior and Safety Margins (A Big Data Analysis). Safety. 2021; 7(1):2.
https://doi.org/10.3390/safety7010002
Burggraaf J, Groeneweg J, Sillem S, van Gelder P. What Employees Do Today Because of Their Experience Yesterday: Previous exposure to yellow:number aspects as a cause for SPAD incidents. Journal of Rail Transport Planning & Management, 2022; 23.
https://doi.org/10.1016/j.jrtpm.2022.100332
Dissertation
Burggraaf, J. The identification of incidental learning as a cause of human error by exploring big data within railway safety. Doctoral dissertation, Safety and Security Science TU Delft, TU Delft repository, 2023.
Or
https://doi.org/10.4233/uuid:c5b1a63b-3873-4b1b-b4ed-e12390d21d40
