Last edited: 23 October 2023
Hazard:
Flooding, LandslideYear:
2020Location:
Kyushu and Chubu regions, JapanScale:
CountryPublishing Organisation
unknown
Category
Real-world
Theme
Crowdsourcing, Social Media
Thematic
- Collecting and Analysing Information from SMCS
- Ensuring Credible Information
- Making Information Accessible
- Mobilising Citizens
- Targeting Communication
Disaster Management Phase
During
Description
Overview: On July 5, record-breaking rainfall caused extensive damages in Kyushu and Chubu regions (south and central regions, Japan). Social media posts requesting rescue and safety confirmation were highlighted by people who had been isolated due to landslides and other damages. Oita Prefecture, one of the regions affected by the disaster, was able to reply to the social media posts from the disaster-stricken areas, using a Twitter-based AI Disaster Risk Management Solution. This system was used to collect messages from residents in risk situations during the disaster, and its use was effective for confirming damage conditions and providing appropriate contact information, which was used for multiple rescues.
HIGHLIGHTED CASE: Some families have been saved by the use of this AI solution.
First message posted by affected family: Using the AI solution, officials from Oita Prefecture found a post of a resident who had become isolated after a road was blocked by a landslide. In one case, a resident in the area was unable to contact the authorities because a utility pole had fallen down and his landline phone was out of service, and cellular phone lines were also offline. While they managed to get an Internet connection, they posted on Twitter: "Mudslide right behind the evacuation center. Power outage, roads blocked, river flooding, we are isolated. It was too hard to evacuate with a one-and-a-half-year-old and a pregnant woman."
Message replied by the prefecture: After Oita Prefecture officials used the AI solution to find the above tweet message successfully, the government immediately used the official Twitter account to send a reply tweet to the original post, giving the contact information for the disaster headquarters. Then, residents who received the reply informed the prefecture of their family's condition and the current situation in the area. Afterward, the prefecture shared information with the local fire department. In response, fire department officials went to confirm the safety of the family.
Subsequent reports: according to local news reports, the residents who were rescued said, "At the time, I had a family member who was seven months pregnant. We also had young children and wanted someone to know what was going on. I wanted someone to find and help me in this difficult and isolated situation. That's how I felt when I posted this". Three months after the torrential rains, the residents gave birth safely. She says, "I am grateful to the prefectural government for catching the Social Media postings and connecting them to support." Also, the official from the Oita Prefecture Disaster Prevention Bureau, who used AI to find the family's tweets, said, "We in government do not have many opportunities to actually interact with residents. Social media is the most significant because it allows us to get detailed information from people on the ground".What was the overall goal of the Use Case?
Crisis information collection, notification, visualization and forecastingWhat limitations were identified?
To summarize the issues identified as overall trends in all regions affected by this disaster (Kyushu region in the south and Chubu region in the central part of Japan), in social media such as Twitter, people affected by the disaster can find a way to request rescue using the hashtag #救助 (kyujyo, meaning "rescue" in Japanese) if they are unable to make a phone call. Therefore, when trying to find information from "#rescue," tweets unrelated to rescue requests were lined up, "burying" important information.
Researchers from the International Research Institute of Disaster Science at Tohoku University (IRIDeS) analyzed 1,058 tweets in which #救助 was used and found that only 2% of the tweets were presumed to have come from the disaster area, while the rest were from outside the disaster area and were not urgent. In addition, when some news media tweeted articles calling for the use of this hashtag, they used #救助 as it is, which caused recipients to retweet the articles in order to spread them, thus contributing to the "burying" of information. The IRIDeS researchers concluded, "The challenge is to improve the social media manners of people outside the affected areas. Also, the news media should be aware of the magnitude of their influence.
The hashtag #救助 is likely to be used as a "last recourse" for communication from disaster-stricken areas when telephone service is not available. The #救助 page on Twitter urges people not to spread the hashtag unnecessarily, but to call emergency services (119 in Japan).