Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Leveraging Accident Investigation Reports as Leading Indicators of Construction Safety Using Text Classification
Despite containing a wealth of information pertaining to construction accidents, accident investigation reports have traditionally been used to understand the immediate cause of accidents and keep statistical records. Such analyses only provide insight into what has happened on-site and are classified as lagging indicators of safety. This study intends to explore the potential of using accident investigation reports as a predecessor to reveal latent factors that can potentially lead to an accident. In this regard, accident investigation reports were manually annotated to tag the type of injury precursor, energy source, accident type, and injury severity. By studying a large volume of accident reports, a more comprehensive knowledge of which conditions and factors have resulted in which type and severity of accidents were generated. This paper also presents a framework to automate such an analysis process by proposing an automated natural language processing-based method to distill crucial information from a tremendous amount of readily available accident reports. This study will help industry practitioners to discover hidden factors causing accidents and provide guidance to avoid accidents on site. This study will also assist safety managers to prioritize operations based on potential hazards and pay more attention to activities that seem harmless but have led to a significant loss in the past.
Leveraging Accident Investigation Reports as Leading Indicators of Construction Safety Using Text Classification
Despite containing a wealth of information pertaining to construction accidents, accident investigation reports have traditionally been used to understand the immediate cause of accidents and keep statistical records. Such analyses only provide insight into what has happened on-site and are classified as lagging indicators of safety. This study intends to explore the potential of using accident investigation reports as a predecessor to reveal latent factors that can potentially lead to an accident. In this regard, accident investigation reports were manually annotated to tag the type of injury precursor, energy source, accident type, and injury severity. By studying a large volume of accident reports, a more comprehensive knowledge of which conditions and factors have resulted in which type and severity of accidents were generated. This paper also presents a framework to automate such an analysis process by proposing an automated natural language processing-based method to distill crucial information from a tremendous amount of readily available accident reports. This study will help industry practitioners to discover hidden factors causing accidents and provide guidance to avoid accidents on site. This study will also assist safety managers to prioritize operations based on potential hazards and pay more attention to activities that seem harmless but have led to a significant loss in the past.
Leveraging Accident Investigation Reports as Leading Indicators of Construction Safety Using Text Classification
Shrestha, Shraddha (Autor:in) / Morshed, Syed Ahnaf (Autor:in) / Pradhananga, Nipesh (Autor:in) / Lv, Xuan (Autor:in)
Construction Research Congress 2020 ; 2020 ; Tempe, Arizona
Construction Research Congress 2020 ; 490-498
09.11.2020
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Enhancing Construction Worker Safety Performance Using Leading Indicators
| British Library Online Contents | 2013
An improved text mining approach to extract safety risk factors from construction accident reports
| BASE | 2021