We are tremendously excited to announce today that over the past 24 hours we have completed the integration of Google Cloud Vision API's new Web Detect capability into the GDELT Visual Knowledge Graph! Web Detect is a truly game-changing new capability for the VGKG in that, combined with our file metadata extraction, we can now estimate […]
Having spent the past week at Google's Cloud Next 2017 conference we've gotten some incredible ideas to bring back to GDELT – stay tuned for some really amazing new announcements coming over the next month!
Kalev was interviewed for today's Google Cloud Platform (GCP) podcast recapping Day 0 at Google Cloud Next. Learn More.
Kalev spent the day today at the inaugural Google Cloud Next 2017 Community Summit, described as a gathering of "cloud insiders and developers alongside Google Cloud's engineering and executive leadership, plotting the future of cloud, un-conference style." We've come away with some incredible new ideas to bring back to GDELT, so stay tuned!
We are excited to be one of the datasets for the SBP-BRiMS 2017 Grand Interdisciplinary Data-Science Challenge focusing on "fake news" / propaganda. Participants in the Challenge may find the following GDELT resources of great interest. Note that new versions of the APIs below will be debuting in the next few weeks, adding immense new capabilities […]
We're excited to announce that starting in about a week we will begin rolling out the GDELT 2.0 APIs! These new APIs will support an incredible array of new capabilities, including for the first time making the Visual Knowledge Graph (VGKG) dataset available via API search as part of the new 2.0 Full Text API, allowing […]
We are happy to announce that earlier this afternoon we completed the final stages of the migration of the Full Text API to our new ElasticSearch infrastructure! No changes were made to functionality or interface and users should notice absolutely no difference other than the system being immensely faster now. Relevancy ranking should also be dramatically […]
USAID put together this video showcasing how GDELT is being used to catalog global wildlife crime.
First announced in May 2015, our GeoJSON API has become an immensely popular way of visualizing and interacting with the geography of the global news media through GDELT. As part of our migration to our new ElasticSearch infrastructure, we will be slowly transitioning all of our legacy APIs to the new system before rolling out […]
Kalev appeared on the Wharton Business Radio Highlights program this evening to talk about his thoughts on Mark Zuckerberg's Facebook Manifesto. Listen To the Show.
Four recent explorations showcase how GDELT, the largest open dataset ever created capturing the life of the world's media ecosystem, can be used to understand how the world's media functions and what it tells us of the world around us. They were even mentioned in the March 1st issue of the O'Reilly Data Newsletter! Creating A […]
What 121 million news articles and three quarters of a billion hyperlinks tell us about how the world’s news media is connected and the role of language, geography, culture and economic ties on what we see about the world around us. Read The Full Article.
What deep learning algorithms can tell us about the visual narratives of the world’s news imagery, from depictions of violence to the importance of people to visual context – a look inside what we see about the world around us. Read The Full Article.
Many web archiving initiatives are still using crawlers built for the web of a quarter century ago and advances in video, social media walled gardens, dynamic page generation and the mobile web are causing web archives to preserve less and less of the modern web. Read The Full Article.
With the public debut of its new deep learning-powered toxic speech filter, Alphabet Jigsaw (formerly Google Ideas) offers the perfect model: a focus on language over ideas, an open API available to others, transparency in how the model was built and what it looks for and an open feedback loop. The Christian Science Monitor cited […]
This new map repeats last year's map of global happiness using BigQuery and Carto to map global happiness in 2016 as seen through the eyes of the world's news media. Click on the map below to download the full resolution map or you can download the low resolution version. TECHNICAL DETAILS To create the map, […]
How the power of the cloud makes it possible to sentiment mine, machine translate, geocode and map a quarter billion news articles to map global happiness in 2016 as seen through the eyes of the world’s press. Read The Full Article.
Last March we released a map showcasing the deep learning-powered "visual geocoder" capability of Google's Cloud Vision API applied to 20 million images. Today GDELT's VGKG has grown to more than a quarter-billion images and we've created a new map to see what new insights a year's worth of data offers. This map is part […]
Traditionally we’ve focused on mapping the geography of text, but through deep learning we now have algorithms that can visually geocode images, recognizing where they were taken and placing them on a map – here’s what it looks like to map a quarter billion worldwide news images. Read The Full Article.
Mark Zuckerberg’s vision of a future in which Facebook knows us better than we know ourselves and can “identify problems before they happen” offers a frightening look at the “precrime” world of tomorrow’s “big data.” Read The Full Article.
As we argue about what exactly “fake news” is and how to fight it, we find that the phrase was born last century in the world of propaganda, but it was Mark Zuckerberg who entered it into our modern lexicon and President Trump who weaponized it into a media pejorative. On May 24, 2017 the […]
How our obsession with “fake news websites” masks the reality that most false and misleading information comes in the form of false claims in otherwise “real” content. Read The Full Article.
While Twitter’s new tools for combatting abusive speech are a decade-late effort to return to civil discourse, one particular instance offers a frightening preview of 1984 in which criticism of government is prohibited. Read The Full Article.
If just 50 people can vote to effectively blacklist an entire news outlet from Wikipedia without any data-driven analysis, what does this mean for a future where platforms like Facebook and Twitter increasingly control what we see online? Read The Full Article.