Natural Disaster Topic Selection using Decision Tree Classification
Ade Sutedi
Sekolah Tinggi Teknologi Garut
Abstract
Social media like Twitter used as a reference for popular and trusted news today. This condition caused users shared out the information to another about anything around them. This opportunity could be useful information about natural disasters that occur in certain condition related to their locations. This study aims to select the topic that related to the natural disasters that occur in Indonesia based on Twitter user timeline. The topic will use as a reference to ascertain events, conditions of victims and location, and positions of disaster locations. For the validity of disaster information, the data takes from the official Twitter account of @BNPB_Indonesia and @infoBMKG. The data extracted and divided into two main classes, then grouped into types of disasters and locations, and determine the position of location that can be used as a safe point after disasters. In this, study a decision tree classification was used to assist the topic selection process related to natural disaster events.
Keywords: Social Media, Natural Disaster, Decision Tree, Classification
Topic: Computer Science