From words to pictures: Text analysis and visualization
You've got a massive pile of text: some Ferguson tweets, a box of now OCRed documents, or maybe a corpus of press releases you scraped. How do you make sense of it? In this session I'll introduce some alternatives for using text visualization to see your texts in different ways. Then I'll talk about some of the machinery for text analysis that you'll need to get there, with pointers out to Python tools. Next year you'll be visualizing the SOTU like a pro.
Nick Diakopoulos is a Professor of Communication Studies and Computer Science at Northwestern University. He studies automation and algorithms as they impact news media including aspects of journalistic data mining, automated content production, news bots, and algorithmic accountability. He is author of "Automating the News: How Algorithms are Rewriting the Media" from Harvard University Press, and co-editor of "Data-Driven Storytelling" from CRC Press.
No tipsheets have yet been uploaded for this event.