It is remarkable that just over a year ago, on Dec. 31, 2019, BlueDot sent out one of the very first alerts in the world warning of the impending Covid-19 pandemic using GDELT. Its machine learning algorithms leverage GDELT's vast reach into local coverage in local languages around the world, scanning the GDELT GKG in realtime to identify the earliest glimmers of potential disease outbreaks and coupling those alerts with overlays like transportation networks, mobility corridors, health infrastructure and other information to estimate disease trajectories.
Six years ago GDELT also was among the very first to monitor the first local media reports of what would go on to become the 2014-2016 Ebola outbreak, but at the time our limited machine translation capabilities meant we weren't able to act upon those reports. This led to the creation of GDELT Translingual to allow us to live-translate everything we monitor in 65 of the 152 languages GDELT monitors. It was this mass machine translation capability that led us to inventorying the earliest reports of the future pandemic on Dec. 30, 2019 when it was still just a handful of cases of "viral pneumonia … of unknown cause" which BlueDot's algorithms flagged and led to them sending what became one of the very first worldwide alerts of Covid-19 on December 31, 2019.
That GDELT has now monitored the earliest glimmers of the two most recent pandemics and through the power of machine translation enabled the sending of one of the very first worldwide early warnings of the latter stands testament to the power of looking at the world through local eyes.
Today we continue this legacy of pioneering innovation through our collaborations with the Internet Archive and the Media-Data Research Consortium (M-DRC) and the M-DRC's Google Cloud COVID-19 Research Grant "Quantifying the COVID-19 Public Health Media Narrative Through TV & Radio News Analysis", we're exploring how the Covid-19 story is being told, how it compares to the narratives around past pandemics, how it is being swayed by sources of misinformation and what public health communicators can learn from all of this to more effectively communicate to an increasingly fatigued public.