Abstract
News agencies work around the clock to report critical news such as earthquakes. We investigate the relationship between online news articles and seismic events that happen around the world. We have utilised computer text mining tools to automatically harvest, identify, cluster and extract information from earthquake-related reports and carry out cross-validation on the mined information. Earthquake parameters retrieved from the United States Geological Survey (USGS) Application Programming Interface (API) are organised into earthquake events, with each event consisting of daily earthquake readings taking place in a particular geographical location. The results are then visualised on a user-friendly dashboard. 268,182 news reports published by 23 news agencies from different parts of the world and 14,677 earthquakes of magnitude ranging from 4 to 8.2 listed in the bulletin were processed during a 1-year study between 2018 and 2019 resulting in 732 news clusters. The use of multilingual news sources from across six continents gives the advantage of reducing potential news bias originating from English written newspapers only. Our results confirm that the number of online published news articles for an earthquake depends on the event magnitude, on the duration of the seismicity linked to the mainshock, on the damage caused, and on the degree of the location’s inhabitation. We propose a general global relationship between the number of news agencies, the earthquake magnitude and the anticipated number of published articles. Such analysis can be used to plan and coordinate global campaigns in cases of relief efforts for disaster-struck areas or educational promotion for earthquake preparedness.
Highlights
Many researchers have tried to identify the factors that determine the level of coverage news agencies give following major earthquake events (Suzanne, 2006; Eisensee and Strömberg, 2007; Stomberg, 2012; Le Texier et al, 2016)
This study has widened considerably the source of news coverage for investigation when compared to previous studies reaching out to news agency websites spread across 16 different countries from six continents (North America, South America, Europe, Africa, Asia, and Australia - refer to Table 1) and translating 6 languages to English in the process
Out of 268,182 articles collected during a 1-year time period, 1.25% had the word “quake” and 0.4%, were mapped to the earthquake events listed in the United States Geological Survey (USGS) earthquake bulletin to validate its authenticity and establish relationships
Summary
Many researchers have tried to identify the factors that determine the level of coverage news agencies give following major earthquake events (Suzanne, 2006; Eisensee and Strömberg, 2007; Stomberg, 2012; Le Texier et al, 2016). These studies do not specify that data was automatically gathered, clustered and processed for information extraction in real time and, these studies have been limited to specific earthquakes or focused on a particular geographical region. Van Belle (2000) identified an increase in coverage when the impacted country had better social and cultural ties with the United States, which tend to lead to increased assistance to the earthquakeaffected country following the aftermath of the earthquake (Heeger, 2007). Heeger (2007) went farther, stating that while a strong correlation was found between students who followed earthquake news on TV and the financial assistance Americans provided, the relationship between the amount of time watching the event unfold and the financial contributions given, was weak
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
