Data mining of social media for urban resilience study: A case of rainstorm in Xi'an

Abstract

Disasters throughout the world have highlighted the urgent need for studies on urban resilience capacities. Individuals' collective responses to disasters provide significant insights into their capacity for catastrophes adaptation and an invaluable perspective for demonstrating urban resilience. Previous research on urban resilience has rarely assessed resilience on an urban scale based on individuals' collective responses. As social media data are both a personal expression of users and a subjective reflection of their surroundings, we developed a social media-based data mining method to reflect urban resilience. We examined the urban resilience with the case of a rainstorm in Xi'an on July 24, 2016. The temporal patterns of public behavioral and emotional dimensions were chosen to examine how the city tolerated the disruption and returned to normal conditions. The public's behavioral reactions peaked during the rainstorm and lasted for a long time, revealing a delayed and hysteretic response. After 33 h, the holistic sentiment index repaired from 0.412 to the baseline standard of 0.713, indicating relatively feeble urban resilience to such rainstorm disasters. Our research revealed the viability of using social media to quantify a city's resilience, which is significantly beneficial in supplementing previous research.