US Department of Defense SMA Speaker Series Presentation 2016

Kalev presented today as part of the US Department of Defense SMA Speaker Series, providing an update on GDELT's massive progress through 2015, including an overview of its new Stability and Full Text APIs, BigQuery Terascale/Petascale analysis capabilities and its early use of the new Cloud Vision API to apply deep learning analysis of global news […]

What It Looks Like To Process 3.5 Million Books In Google’s Cloud

GDELT's processing of the complete 1800-2015 English-language public domain digitized books collections from the Internet Archive and HathiTrust (totaling 3.5 million volumes) was featured last week on the Google Cloud Platform blog! You can learn more about the project, see more technical detail, experiment with sample BigQuery queries mining the entire collection, or even perform […]

Liberation Technology: Mobile Phones and Political Mobilization in Africa

Researchers Macro Manacorda and Andrea Tesei of Queen Mary University of London and the Centre for Economic Performance (CEP) at the London School of Economics published a study last month titled "Liberation Technology: Mobile Phones and Political Mobilization in Africa" exploring the link between the spread of mobile phone technology on the African continent and political protest, using […]

Does Social Media Actually Reflect Reality?

Kalev's latest piece for Forbes explores the degree to which social media reflects reality and the implications of this for using social indicators to understand global society. Read the Full Article.

Data Sharing And Replication In The Sciences

Kalev's latest piece for Forbes explores the state of data sharing and replication in the sciences and why open data projects like GDELT are so critical to the future of scientific discovery. Read the Full Article.

Why The Web Is So Slow And What It Tells Us About The Future Of Online Journalism

Kalev's latest piece for Forbes explores the state of online journalism and uses some of the diagnostic tools built into the Google Chrome browser to quantitatively measure the bloat afflicting modern news sites, finding that news websites stand out among all other tested websites for being the slowest, most bloated, and most non-mobile-optimized, yet that […]

Visual Global Knowledge Graph (VGKG) February 2016 Snapshot Dataset

Given the enormous interest we've been receiving in the new GDELT Visual Knowledge Graph (VGKG), which processes an ever-growing fraction of all global news imagery monitored by GDELT through Google's "deep learning" Cloud Vision API, we've boxed up the 14.6 million images we've processed to date and made them available as a downloadable CSV file […]

Aftenposten Features Candidate Television Tracker

Lorns Bjerkan writes for Aftenposten, Norway's largest newspaper, about American television coverage of Donald Trump using GDELT's 2016 Candidate Television Tracker, which uses data from the Internet Archive's Television News Archive. Read the Full Article.

Columbia Journalism Review Features Candidate Tracker

David Uberti recently wrote for the Columbia Journalism Review using GDELT's 2016 Candidate Television Tracker, which uses data from the Internet Archive's Television News Archive, to track Trump's rise in media coverage. Read the Full Article.

VGKG 1.0 Now Processing All Monitored News Imagery

We're tremendously excited to announce that as of GDELT Visual Knowledge Graph (VGKG) 1.0, we are now processing both the SocialSharingImage and RelatedImages fields of the GDELT Global Knowledge Graph, meaning that as of February 14, 2016, we are now attempting to process 100% of the images GDELT finds in all articles it monitors each day (though due […]

VGKG 1.0 Arabic, Persian, Thai, Chinese And Script OCR

As we noted on Saturday, with the release of the Visual Knowledge Graph (VGKG) 1.0, we are now passing language hints to the Google Cloud Vision API estimating the likely language(s) it should expect to see of any text that might be present in each image. This has had a dramatic impact on the recognition […]

GDELT Visual Knowledge Graph (VGKG) V1.0 Available

We're excited to announce that as of late yesterday afternoon, Version 1.0 of the GDELT Visual Knowledge Graph (VGKG) is now available, bringing with it many new features and enhancements from the Alpha release! In particular, the Google Cloud Vision API has added a number of new features and enhancements, including a new set of descriptors […]

How Fragile Are Our Cities?

The Igarapé Institute teamed up with the United Nations University, the World Economic Forum, the World Bank and SecDev, with support from the Canadian government, to explore and visualize the correlates of city fragility. Among the many variables they examined were several from GDELT, as seen in the images below, and the visualizations were shown at the […]

IRIN News: Why Does No One Care About Yemen?

IRIN News published a feature earlier today exploring how the Yemen conflict has largely faded from global media attention and uses GDELT to show that coverage of Yemen has significantly declined even among Arabic language presses. Read the Full Article.

Shorouk News Features Candidate Television Tracker: Bernie Sanders

Mohammed Minshawi writes for Shorouk News, a prominent Arabic language newspaper published in Egypt, about Bernie Sanders and uses GDELT's 2016 Candidate Television Tracker, which uses data from the Internet Archive's Television News Archive, to comment on television coverage of his campaign. Read the Full Article.

Announcing the American Television Global Knowledge Graph (TV-GKG)

We are enormously excited to announce today the unveiling of our latest massive new dataset: the American Television Global Knowledge Graph (TV-GKG). The Internet Archive's Television News Archive, covering more than 150 unique English language domestic American television stations in 20 markets, some dating as far back as June 2009, have been processed through the GDELT GKG 2.0 pipeline, totaling […]

Georgetown University Wizard of Big Data Video

From 2013-2014 GDELT creator Kalev Leetaru was the Yahoo! Fellow in Residence of International Values, Communications Technology & the Global Internet at Georgetown University's Edmund A. Walsh School of Foreign Service, where he was also adjunct faculty. While he was there, Georgetown produced this fantastic video about his work to go along with their feature […]

Emotions of American Television 2009-2016 Dataset

For those of you interested in building your own visualizations or analytic models of the emotional undercurrents of American television from July 2009 to February 7, 2016, we are releasing the entire emotional dataset behind the new Television Emotions Explorer. The 1GB GZIP file will uncompress to around 3.3GB and contains one ASCII text file per emotion. […]

Visualizing The Emotions of American Television News 2009-2016

Back in October 2014 we released a massive dataset and interactive visualization of the emotional undercurrents of American domestic television applying a very early prototype version of GDELT 2.0 to the Internet Archive's Television News Archive. We are tremendously excited to announce today the unveiling of a new reimagination of that original vision of news as […]