Continue Reading

Visualizing An Entire Day Of Global News Coverage: How UMAP + t-SNE Reduces HDBSCAN Clustering Noise

Yesterday we explored how applying UMAP and then t-SNE dimensionality reduction one after another prior to HDBSCAN clustering yielded much…

Continue Reading

Visualizing Nine Days In The Life Of The Global News Landscape

Earlier this week we visualized for the first time an entire day of global news coverage, including examining a sequence…

Continue Reading

Good Authority: Why The U.S. Border Wall Is Getting More And More Popular

A look at how the US border is being covered in the media. Read The Full Article.

Continue Reading

Visualizing An Entire Day Of Global News Coverage: Technical Experiments: PCA vs UMAP For HDBSCAN & t-SNE Dimensionality Reduction

This week's visualizations of an entire day of global news coverage were limited by one key factor: computational tractability. Even…

Continue Reading

Wired: The UN Hired An AI Company To Untangle The Israeli-Palestinian Crisis

"Their idea for an AI program that models the belief systems that drive human behavior first began when Lane moved…

Continue Reading

Putin On Russia's AI Investments From This Past July

This past July, Russian President Vladimir Putin had an exchange with Sberbank's CEO on Russia's AI investments that was covered…

Continue Reading

Visualizing An Entire Day Of Global News Coverage: A First Experiment

Last week we visualized an entire day of television news coverage through the eyes of three channels in China, Iran…

Continue Reading

Gender & Race Bias In Multimodal Image Embedding Models: A Case Study Of OpenAI's CLIP & How White Men Are Doctors & CEOs Not Black Women

Over the past few months we've documented innate existential racial and gender bias in many of the textual embedding models…

Continue Reading

Experiment In At-Scale Visualizations Of News Coverage

Stay tuned for a series of experiments coming soon on visualizing and exploring the global news media landscape at scale.

Continue Reading

A Python Notebook For Comparing Multimodal Image Embedders: OpenAI's CLIP Vs Google's Vertex AI

Over the past year we've explored multimodal image embedders through the eyes of both OpenAI's CLIP and GCP's Vertex AI…

Continue Reading

A Dynamic Monitoring Method Of Public Opinion Risk Of Overseas Direct Investment – Based On Multifractal Situation Optimization

The negative public opinions and views on overseas direct investment (ODI) of a multinational enterprise (MNE) will damage the image…

Continue Reading

A Comparative Three-Country Visualization Of One Day Of TV News Coverage: China, Iran & Russia Through Multimodal Embeddings

Lying at the heart of our series this week exploring the visual landscape of television news across the world has…

Continue Reading

Comparing The Domestic & International Narrative Landscapes Of Iranian TV News Using Multimodal Image Embeddings

One of the most existential questions lying at the very heart of public interest international media scholarship is the question…

Continue Reading

Using Multimodal Image Embeddings To Explore The Visual Landscape Of An Entire Day Of A Second Iranian TV News Channel

Earlier this week we visualized a day of Iranian television news of the domestic Persian-language channel IRINN using multimodal image…

Continue Reading

Comparing One Day Of TV News Coverage Through Multimodal Image Embeddings: China Vs Iran Vs Russia

Over the past two days we've mapped the visual landscape of a complete single day (October 17, 2023) of television…

Continue Reading

Using Multimodal Image Embeddings To Explore The Visual Landscape Of An Entire Day Of Chinese TV News

As we continue to explore how journalists and scholars can make sense of our ever more unstable world, we've examined…

Continue Reading

Using Multimodal Image Embeddings To Explore The Visual Landscape Of An Entire Day Of Iranian TV News

In a global world beset by an growing number of crises and conflicts, it is more important than ever for…

Continue Reading

Using Multimodal Image Embeddings To Explore The Visual Landscape Of An Entire Day Of Russian TV News

Yesterday we explored how, in an ever more unstable world, we can use multimodal image embedding models to cluster, search,…

Continue Reading

Using Multimodal Image Embeddings To Visualize, Cluster & Search The Visual Landscape Of A Russian TV News Broadcast

In this era of ever-growing crises across the world, how might machines help journalists and scholars look across the landscape…

Continue Reading

How The World Covers Global Events: The Myriad Voices Of Planet Earth

One of the most powerful dimensions of GDELT is the way in which it makes it possible to look across…

Continue Reading

The Web On Television: How Television News Turned To The Web Twenty Years Ago To Cover 9/11 Headlines

In a fascinating bit of history, look at how Greek television news turned to a sequence of screenshots of the…

Continue Reading

WashPost: The Perils Of Never Questioning What Jim Jordan Says

The Washington Post's Philip Bump examines media coverage of Jim Jordan. Read The Full Article.

Continue Reading

Visual Explorer: Transcribing The TV News Archive's 9/11 Global Television News Archive

Earlier this morning we announced that we have transcribed the first decade of the Internet Archive's TV News Archive. As…

Continue Reading

Visual Explorer: The First Decade & 19M Minutes Transcribed Through Google's Chirp

We are tremendously excited to announce today that in collaboration with the Internet Archive, the entire first decade (2001-2010) of…