Detecting flood inundation information through Twitter: The 2015 Kinu River flood disaster in Japan

Abstract

For effective responses to flood disasters, it is essential to identify affected areas in real time. Recently, social media (e.g. Twitter) have emerged as new sources of disaster-related information in real time. However, concerns still remain regarding the trustworthiness and the amount of information, especially that issued from a site of crisis. This study investigated a total of 109 tweets sampled based on certain criteria during a flood disaster in the Kinu River Basin, Japan in September 2015. We classified them into five categories depending on the main contents: 1) flood inundation, 2) rescue, 3) emotion, 4) river condition, and 5) damage situation. The analysis suggests that the highest proportion (37%) of tweets were related to flood inundation followed by damage (19%) and 32% of them were posted in near real time with photos. We further compared well-positioned tweets with other inundation extent information based on our field investigations and aerial photos. The results showed good agreement between the inundation information from the posted tweets and the expected locations. Some tweets suggested additional inundated areas, not originally identified by the aerial photos. Overall, the study shows the potential use of social media to collect local details about floods.