Continue Reading

Recovering Degraded Onscreen Text From Television News: Deepwater Horizon

Yesterday we showed how Google's Cloud Video API was able to seamlessly identify onscreen Arabic text in an ABC Evening…

Continue Reading

Multilingual OCR From Evening Television News: Arabic On ABC

As we explore how deep learning video understanding systems like Google's Cloud Video API can help us reimagine how machines…

Continue Reading

Blocked March for Life Tweets Raise Free Speech Concerns

In the lead-up to last week’s March for Life rally, Twitter generated controversy for censoring at least two different pro-life…

Continue Reading

Greater Good Gathering 3.0

Kalev will be speaking at the Greater Good Gathering 3.0 next week at Columbia University on a panel alongside Director…

Continue Reading

Discerning Certainty Amidst Chaos: The Conflicting Cacophony Of News

One of the greatest challenges in attempting to monitor the entire planet lies in discerning certainty amidst the chaotic conflicting…

Continue Reading

World Bank: How Technology & Data Are Transforming Sustainable Development

Kalev spoke to the World Bank today on how GDELT's global datasets can be used to help understand global narratives…

Continue Reading

Identifying Contradictory Climate Change Narratives Using Cloud Natural Language & The Climate Change Narratives Dataset

Moving beyond simple Q&A about climate change, could we use Google's Cloud Natural Language API and our new Climate Change…

Continue Reading

Using Cloud Natural Language & The Climate Change Narratives Dataset For Q&A About Climate Change

With yesterday's massive new dataset containing the URLs and context snippets of 6.3 million English language online news articles about…

Continue Reading

Four Massive Datasets Charting The Global Climate Change News Narrative 2009-2020

Over the past two days we have released a set of four massive new datasets designed to fundamentally advance the…

Continue Reading

A New Contextual Dataset For Exploring Climate Change Narratives: 6.3M English News URLs With Contextual Snippets 2015-2020

We are tremendously excited today to announce the fourth in our series of climate change narrative datasets, covering television, linguistics and…

Continue Reading

Can 'Cahoots' Be Anything Other Than 'In Cahoots'?

The Wall Street Journal's Ben Zimmer yesterday traced how the word "cahoots" has evolved over time, noting among other things…

Continue Reading

A New Multilingual Dataset For Exploring Climate Change Narratives: 4.1 Million News URLs In 63 Languages 2015-2020

For those interested in exploring the global news narrative around climatic change, we are excited to announce today a massive…

Continue Reading

Measuring a Trump-Size Mark on the Cable News Universe

The presidency of Donald Trump has not only divided the public, it has fractured the media landscape. The tone of…

Continue Reading

A New Part Of Speech Dataset To Explore Climate Change Narratives In English Online News 2016-2020

Yesterday we released a massive new dataset comprised of all 95,000 mentions of climate change on television news on CNN,…

Continue Reading

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…

Continue Reading

Understanding The Global Multilingual World Through Deep Learning & Data

Kalev presented again to the Wharton School today in DC on the state of GDELT and leveraging deep learning and…

Continue Reading

A New Dataset For Exploring Climate Change Narratives On Television News 2009-2020

Climate change has emerged over the past decade as a major societal fault line, with the public narrative becoming a…

Continue Reading

Climate Change Coverage Steadily Increases On BBC Compared With CNN/MSNBC/Fox News

Climate change has been attracting a growing number of headlines of late, but interestingly, as the timeline below shows, the…

Continue Reading

Visualizing Part Of Speech Distribution In A Multilingual World

As of this past Friday, GDELT's Web Part Of Speech dataset now covers 11 languages: Chinese (Simplified), Chinese (Traditional), English,…

Continue Reading

Global Entity Graph (GEG) Now Offers Multilingual Neural Sentiment

The Cloud Natural Language API-powered neural Global Entity Graph (GEG) now offers the API's neural-computed sentiment scores for the 10 languages…

Continue Reading

Using The Global Entity Graph (GEG) To Chart Tesla's Media Tone

With the merger of document sentiment scores into the core Global Entity Graph (GEG), each GEG record now includes both…

Continue Reading

Global Entity Graph (GEG) Neural Sentiment Now Merged Into Core GEG Dataset

When it first debuted last year, the Global Entity Graph (GEG)'s neural sentiment dataset was a separate dataset. As of…

Continue Reading

Neural Global Entity Graph (GEG) Now Updating Every Minute

The Cloud Natural Language API-powered neural Global Entity Graph (GEG) is now updating every minute, 24/7/365. Due to GDELT's current 15…

Continue Reading

Web Part Of Speech Dataset Now Updating Every Minute

The Cloud Natural Language API-powered Web Part of Speech dataset is now updating every minute, 24/7/365. Due to GDELT's current 15…