Twitter earthquake detection: earthquake monitoring in a social world

By Paul Earle, Daniel C. Bowden, Michelle Guy. 2012

460 citations recorded by the source corpus.

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 globally-distributed 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.

Subfields: Artificial Intelligence, Communication, Epidemiology

View Paper: https://www.semanticscholar.org/paper/a0b0c0d0988c05ce0ffe0612f051c8f340821ea7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Communication

In Epidemiology

Citations in the corpus

Socializing in emergencies - A review of the use of social media in emergency situations (2015, background): “This represents a much faster identification than seismographic detections in many regions in the world, and has a low rate of false triggers (Earle et al., 2011).”
Tools and methods in participatory modeling: Selecting the right tool for the job (2018, background): “For example, van Zanten et al. (2016) estimated continental landscape values based on the social media data; and USGS has the Twitter Earthquake Detection data mining program which is used to help determine the intensity of earthquake energy felt by Twitter users (Earle et al., 2012).”
Big Data in Natural Disaster Management: A Review (2018, background): “Earle et al. [108] investigated the capability of using Twitter for rapid earthquake detection.”
Rapid assessment of disaster damage using social media activity (2016, background): “Another branch focuses on the practical aspects of classifying disaster messages, detecting events, and identifying messages from crisis regions ( 39 – 43 ).”
Real-Time Crisis Mapping of Natural Disasters Using Social Media (2014, background): “According to the US Geological Survey (USGS) [3] the main benefit of Twitter-based detection systems over sensor-based systems is their fast detection speed and low cost.”
Machine learning for data-driven discovery in solid Earth geoscience (2019, background): “Data sources such as light detection and ranging (LiDAR) point clouds (134), distributed acoustic sensing with fiber optic cables (135–137), and crowd-sourced data from smartphones (17), social media (138, 139), web traffic (140), and microelectromechanical systems (MEMS) accelerometers (141) are we”
The limits of crisis data: analytical and ethical challenges of using social and mobile data to understand disasters (2015, background): “For example, USGS researchers have shown that they can use Twitter to detect an earthquake, in some cases more quickly than traditional seismic instrumentation (Earle et al. 2011).”
Predicting crime using Twitter and kernel density estimation (2014, background): “As shown, researchers have attempted to use social media to predict or detect disease outbreaks [11], election results [12], macroeconomic processes (including crime) [13], box office performance of movies [14], natural phenomena such as earthquakes [15], product sales [16], and financial markets [1”