Continue Reading

Experiments In Meme Tracking: Cataloging Stories According To UN SDGs

Continuing our meme tracking series, let's look at how LLMs can be used to catalog stories according to their relevance…

Continue Reading

Experiments In Meme Tracking: Cataloging & Classifying Memes By Conflict Enhancing Bias

Long before conflict becomes kinetic, narratives drive divisions within and between societies. Some narratives, especially those revolving around gender, racial,…

Continue Reading

The Unintended Consequences & Harms Of Multimodal LLM Debiasing: Detection Vs Generation

Multimodal LLMs represent uncharted new territory in the push to "debias" and "globalize" computer vision models. Past generations of object…

Continue Reading

The Limitations Of Multimodal Large Language Models: Automated Image Description, Captioning & Reasoning

Multimodal Large Language Models (LLMs) are touted as the future of automated reasoning, with the ability to look across imagery…

Continue Reading

Spinmeisters Of Russia: The Bucha Massacre Likened To WWII Nazis

On Sunday evening, Russia-24 presented a 2-part piece (~50 minutes) framing Ukraine's fight against Russia’s invasions as a product of…

Continue Reading

ChatGPT Experiments: Summarizing Russian Television News – Asking ChatGPT To Explain "60 Minutes"

As part of our ongoing ChatGPT experiments, we explored using cascading summarization to distill a 2.5-hour episode of Russia 1's…

Continue Reading

One Year After Afghanistan Fell To The Taliban It Remains Absent From Television News

On the one-year anniversary of Afghanistan's fall to the Taliban, the country remains largely absent from television news. Within two…

Continue Reading

The Storm Media: The Issue Of Gender Bias Revealed By The Russian-Ukrainian War

The Storm Media summarizes a report in Foreign Policy magazine about coverage of women in news about the invasion of…

Continue Reading

TFIDF Using BigQuery + Radio News NGrams To Chart The Most Significant Words Per Day On BBC World Service In 2020

How might we use the new Radio News NGrams dataset to examine the Internet Archive's Radio News Archive's ASR of…