was successfully added to your cart.

Propaganda Analysis with NLP: What Can We Possibly Learn from “Fake News?”

How severe was the COVID-19 outbreak in China, really? Will Hong Kong protesters face a violent crackdown by Chinese military? What will be China’s next big moves in the post-COVID era? The Policy Chang Index (PCI), an open-source machine learning project, tackles policy questions like these by analyzing authoritarian regimes’ propaganda.

Applying recent advances in NLP, the project has developed several algorithms to monitor the People’s Daily — China’s flagship official newspaper — and make inferences about the Chinese government’s policy intentions. Similar PCI algorithms can also be developed for other authoritarian regimes with media control.

Learning from the vector space: extracting knowledge from x2vec

In this talk, we will consider current embedding algorithms from the perspective of knowledge extraction. I will present practical use cases for...