For this assignment, you get to screw around with the Presidents. No, this is not a chance to emulate Monica Lewinsky. Rather, you get to perform a lexomics experiment on the State of the Union addresses of every President of the United States from George Washington up to George W. Bush. Can you find certain presidents whose speeches are similar to others? Can you explain why?

For this experiment, choose the entire corpus of State of the Union speeches or just choose a selection. Following the procedure we studied in class, create a dendrogram of your collection of texts. Observe which presidents seem to have statistical similarities.

If you have ideas before class begins, or you want to discuss things like ideal chunk size, and so on, post to the forum. When you are done, write one or two paragraphs in which you try to explain what may explain the cluster pattern. Is it similar dates? Historical events? Party affiliations? Something else?

The lexomics tools and tutorials can be found here.

Post your final explanations on the forum before class on Wednesday.