텍스트 마이닝 분석을 통한 해상교통안전진단서 개선 방안에 관한 기초연구

Abstract

Maritime traffic safety Audit is a kind of consultation process that secures the safety of ship passage and prepares a plan to reduce maritime accidents for various stakeholder in a wide range of areas due to the nature of maritime traffic. The result of this process, the maritime traffic safety audit report, is composed of a vast amount of text and is the most essential part of the maritime traffic safety audit system. Traditionally, text analysis methods include a method that the researcher directly reads and analyzes, and a text data approach that regards text as quantitative data and utilizes statistical techniques. The text mining method is one of the text data approaches, an effective method for quantitatively analyzing a large amount of unstructured data such as a maritime traffic safety audit report. In this study, the maritime traffic safety audit report was analyzed through the method. As a result of the analysis, issues such as the distribution of the roles of the central administrative agency and the local administrative agency, and improvement of standards for port design were derived. Since it may have an effect, it was suggested to improve the maritime traffic safety audit report by confirming that neutral words should be used as much as possible. As a result of the analysis, pending issues such as the distribution of the roles of the central administrative agency and the local administrative agency, and improvement of port design standards were derived. And according to the sentiment analysis result, a lot of positive words were used in general, but since this can have a direct/indirect effect on the evaluation of the maritime traffic safety audit report, it was suggested that neutral words should be used to improve the maritime traffic safety audit report.