TEXT-MINING OF INSURANCE-BASED INFORMATION: DECISION SUPPORT FOR LOCAL SAFETY MANAGEMENT

Abstract- Based on underlying perspectives, different data tend to be included in reporting systems for occupational accidents and injuries. Information sought mainly for medical, legal, economic or statistical reasons can reduce or misrepresent the information needed for prevention. Actual detail of accident processes provided by local operators in verbatim will serve to counter misconceptions of risk distributions in the organisation and direct the focus to possible prevention measures. The analysis of free-text reporting of traumatic injuries, accidents and incidents promise to better represent the dynamics and detail of exposure and accident process and, when applied to valid and representative insurance data on occupational injury with the help of suitable text-mining software, will provide industry groups and local companies with decision support for prevention and safety management. The trial and development of text-mining software for injury prevention, in conjunction with the industry group safety information system, is described and examples from different exposure areas are given