Mining Social Media to Inform Peatland Fire and Haze Disaster Management

摘要

Peatland fires and haze events are disasters with national, regional andinternational implications. The phenomena lead to direct damage to localassets, as well as broader economic and environmental losses. Satellite imageryis still the main and often the only available source of information fordisaster management. In this article, we test the potential of social media toassist disaster management. To this end, we compare insights from two datasets:fire hotspots detected via NASA satellite imagery and almost all GPS-stampedtweets from Sumatra Island, Indonesia, posted during 2014. Sumatra Island ischosen as it regularly experiences a significant number of haze events, whichaffect citizens in Indonesia as well as in nearby countries including Malaysiaand Singapore. We analyse temporal correlations between the datasets and theirgeo-spatial interdependence. Furthermore, we show how Twitter data revealschanges in users' behavior during severe haze events. Overall, we demonstratethat social media is a valuable source of complementary and supplementaryinformation for haze disaster management. Based on our methodology andfindings, an analytics tool to improve peatland fire and haze disastermanagement by the Indonesian authorities is under development.