Novelty Detection in Text Corpora

Novelty Detection in Text Corpora

Detecting Novelty Using Text Analytics

Detecting novel events – new words, meaning new events – is one of the most important text analytics tasks, and is an important step towards predictive analytics using text mining.

On July 24, 2015, The New York Times (and many other news sources) published an article identifying potential inclusion of classified information in the emails which Hillary Clinton had sent via private email and stored on her private email server.

Hillary Clinton's emails: from sensitive-but-unclassified to alleged classified: How do we detect novel news item?
Hillary Clinton’s emails: from sensitive-but-unclassified to alleged classified: How do we detect novel news item?

How would we use text analytics to detect novelty in this situation?

This slidedeck explains novelty detection in text corpora.

Italian-renaissance-border-2-thin

 

Ready to learn more about text analytics?

Leave a Reply

Your email address will not be published. Required fields are marked *