Towards World-Aware Deep Learning: How External Knowledge Changes How AI Understands Text
One of the most fascinating aspects of being able to see the world at GDELT's scale is our ability to…
Announcing The WEB-PARTOFSPEECH Dataset: 101 Billion Words Part Of Speech Tagged And Dependency Tree Parsed Using Google's NLP API
Today we are immensely excited to announce a transformative new dataset for linguistic analysis: more than 101 billion tokens (words,…
New York Times: Which Democrats Are Leading the 2020 Presidential Race?
The New York Times' look at the 2020 Democratic field uses the TV Explorer to examine media coverage of the candidates. Read…
UK Office For National Statistics: GDELT For Disaster Cataloging
This report by the United Kingdom's Office For National Statistics (ONS) uses GDELT to explore disaster coverage. Read The Full…
Using BigQuery's New ML.NGRAMS() Function To Construct 122 Years Of Book NGrams With One Line Of SQL
Back in 2016 we showed how you could construct ngrams from 122 years of public domain books (1800 to 1922)…
Iran Coverage Predictably Spikes With Similar Captioning And Chyron Mentions
As the US and Iran edged closer to war this week, coverage of "Iran" and "Iranian" and "Iranians" predictably spiked…
Chyrons Versus Captioning: 'Terror' Versus 'Terrorists' In Television News
With the addition of the new Chyron Search API, you can now compare coverage of a particular person, word or…
Chyron Mentions Added To Campaign 2020 Tracker!
The new Chyron Search API, which reprocesses the Internet Archive's Television News Archive's "Lower Third" onscreen chyron text OCR data,…
Comparing Chyron And Captioning Coverage Of Hong Kong On Television News
What can we learn by comparing chyron and captioning coverage across television news for a major event like the Hong…
Tracing Impeachment And Brexit Coverage In Chyrons
Using the newly announced Chyron Explorer, you can instantly examine how often the word "impeachment" has been featured in chyrons,…
Announcing The GDELT Summary Chyron Explorer
We're incredibly excited to announce the debut of the new GDELT Summary Chyron Explorer! Similar to the Television Explorer's closed…
WashPost: The Remarkable Extent To Which Trump Gets The Benefit Of The Doubt From Republicans On Iran
The Washington Post's Philip Bump examines coverage of the Iran strike. Read The Full Article.
Chyron Summary Chronologies: PostMessage Support For Dynamic IFrame Resizing
To help facilitate embedding of our static HTML chyron summary chronologies in iframes, they now support a variant of the…
Announcing The New LowerThird Television News Chyron Search API!
We're tremendously excited to announce today the new Television News Chyron Search API! Similar to the Television News API, the…
How Chyrons Can Provide Missing Context And Speaker Identification From Incomplete Closed Captioning
While closed captioning is supposed to offer a faithful transcription of the words spoken on a given television station, the…
Chyron Correlation As A Case Study Of BigQuery's Linguistic Analytics Potential
Since August 2017, the Internet Archive's Television News Archive has extracted the chyrons of CNN, MSNBC, Fox News and BBC News by OCR'ing…
Mediaite: TV News Has Mentioned Trump’s Golfing About 12,000 Times Since He Became President, 7 Times More Than Obama
Mediaite's Tommy Christopher tracks how many times Donald Trump was mentioned alongside golfing on television news. Read The Full Article.
GDELT Summary Chyron Browser Debuts!
Last month we announced our new research chyrons dataset, created by reprocessing the Internet Archive's "Third Eye" OCR using a…
Big Data Financial Sentiment Analysis In The European Bond Markets
An interesting look at how the sentiment data in GDELT can be used to understand bond markets. We exploit the…
Television News Research Chyrons Datasets Now Available In BigQuery
We're excited to announce that both the original per-minute and new per-second resolution television news research chyron datasets are available…
Announcing Per-Second Television News Research Chyrons Dataset
Last month we announced a new research-grade chyron / "lower third" dataset for BBC News, CNN, MSNBC and Fox News…
Television News Spoken Word Neural Entity Graph (TV News GEG) Now Updating Daily
We're tremendously excited to announce that the television news spoken word neural entity graph announced last month has now been…
Using Wikipedia To Normalize The Classic Global Entity Graph (GEG) G1 Baseline
Last week we unveiled the new Wikipedia-normalized enrichment of the Classic Global Entity Graph (GEG) G1 Baseline, applying it retroactively…
Using The Classic Global Entity Graph (GEG) To Find Name Variants & References To Donald Trump In The News
One of the most powerful elements of the new Wikipedia-normalized classic Global Entity Graph (GEG) announced last week is its ability…