Fast AI classification for analyzing construction accidents claims

摘要: Safety has long been considered an important issue in the construction industry. One means of reducing accidents is to provide for heavy compensation. As per common law system, precedents, once made, then become part legal system. Therefore, companies and firms have interest obtaining details court cases relevant ones they are currently involved with. However, cost identifying can be excessive. Computer-based text classification, process classifying documents into predefined categories with regard their content, proposed this paper as a way speed up procedure whereby identified particular claim accident The data set used project consisted 3000 sentences. 'training split' was 90% training 10% testing. results show that precision system here 95.7% recall 95.7%. This demonstrates fastText-based classification employed successfully classify papers acceptance or rejection compensation case at fairly high rate accuracy. pilot research provides practical example order showcase possibility utilising artificial intelligence, without human intervention, document classification. Such facility could reduce time taken identify past cases, so saving resources, improving turn-round times.