Improvement of the Classification Model Performance in 119-Emergency Report Data

Eunjung Kwon, Hyuinho Park, Sungwon Byon, Kyuchul Lee

http://doi.org/10.5626/JOK.2022.49.1.89

This paper presents a study of the text classification model to provide optimal response information for each disaster situation with respect to the report content recorded by the receiver in the process of receiving the 119 emergency report. A text classification model that receives a sentence and classifies it into a category is a widely used technique in the field of natural language processing. This study defined the rules for using augmented learning data to improve the performance of the text classification model through supervised learning, and confirmed the performance of the classification model using the augmented learning data through experiments. Through this study, the possibility of extension for improving the performance of the text classification model that is input as the report contents for each emergency situation, such as disease, traffic accident, and injury, was suggested.