Twitter earthquake detection: earthquake monitoring in a social world

Abstract

The U.S. Geological Survey (USGS) is investigating how the social networking site Twitter, a popular service for sending and receiving short, public text messages, can augment USGS earthquake response products and the delivery of hazard information. Rapid detection and qualitative assessment of shaking events are possible because people begin sending public Twitter messages (tweets) with in tens of seconds after feeling shaking. Here we present and evaluate an earthquake detection procedure that relies solely on Twitter data. A tweet-frequency time series constructed from tweets containing the word "earthquake" clearly shows large peaks correlated with the origin times of widely felt events. To identify possible earthquakes, we use a short-term-average, long-term-average algorithm. When tuned to a moderate sensitivity, the detector finds 48 globallydistributed earthquakes with only two false triggers in five months of data. The number of detections is small compared to the 5,175 earthquakes in the USGS global earthquake catalog for the same five-month time period, and no accurate location or magnitude can be assigned based on tweet data alone. However, Twitter earthquake detections are not without merit. The detections are generally caused by widely felt events that are of more immediate interest than those with no human impact. The detections are also fast; about 75% occur within two minutes of the origin time. This is considerably faster than seismographic detections in poorly instrumented regions of the world. The tweets triggering the detections also provided very short first-impression narratives from people who experienced the shaking.

Social media information sharing for natural disaster response

“…In recent decades, social media has become a crucial information platform during natural disasters. Applications of social media in disaster response can be categorized into domains like disaster trajectory detection (Crooks et al 2013;Earle et al 2012), situational awareness (De Albuquerque et al 2015;Power et al 2014;Yin et al 2012), information sharing (Li et al 2018;Smith et al 2017), and network performance evaluation (Kryvasheyeu et al 2016;Wang and Taylor 2018). This paper focuses on situational awareness and information sharing, which are critical for improving disaster response.…”

An Integrated Data Framework for Policy Guidance in Times of Dynamic Economic Shocks

“…In fact, the use of various sources of webdata to collect timely and reliable information has gained traction in recent years. For example, webdata from social media platforms is used for event detection to get an up-to-date picture of the situation regarding major social events (White & Roth 2010;Westerholt et al 2015) or natural disasters (Resch et al 2018;Paul S. et al 2012). Both applications have also policy relevance in terms of public security and crisis management.…”

Few Tweets After Flu Peak: Twitter-based Influenza Detection by Referring Indirect Information (Preprint)

“…2. Effectiveness of direct information and indirect information. 3. Effectiveness of data aggregation by TRAP model.…”

“…Social media are used to detect various events, such as earthquakes [2][3][4], political elections [5][6][7], and stock prices in a market [8]. Among the various applications, the study on health-related event detection referred to as infodemiology [1,34] has been gaining much attention from researchers in areas such as air pollution [49], Web-based doctor reviews [50], West Nile virus [9], cholera [10], Escherichia coli outbreak [11], dengue fever outbreak [12], and influenza [1,.…”

“…Consequently, various approaches for analyzing social data (called as social monitoring [1]) have been presented so far. These approaches have presented an important shared premise that Twitter users can be human sensors for event detection [2], and the feasibility of these approaches has been demonstrated on various occasions such as earthquakes [2][3][4], political elections [5][6][7], stock market fluctuations [8], and outbreaks of various infectious diseases . Among them, the study of social monitoring of health-related information shared on the internet is referred to as infodemiology [1,34] and gathers much attention in terms of practical needs.…”