Development of Information Filtering Systems for Disaster Prevention

Description

Text data with spatio-temporal information are becoming common with the popularization of mobile phones with a GPS function and microblog services like Twitter. This study proposes a system supporting operators in a disaster prevention center who control an area in real-world. Our system has three functions: (i) automatic classification that classifies messages into a fixed category, (ii) clustering that aggregates similar messages and (iii) burst detection that detects an event in which messages are arising in high frequency. We asked 120 people to send text data with spatio-temporal information by cell phones in the Osaka Expo Memorial Park. We evaluated our system using the above data.

Details 詳細情報について

Report a problem

Back to top