17. Buzzwords of History

Jon M. Kleinberg, Computer Science, developed a method for a computer to find the topics that dominate a discussion at a particular time by scanning large collections of documents or sudden, rapid bursts of words. Kleinberg scanned presidential State of the Union addresses, from Washington in 1790 to Bush in 2002, and created a list of words that reflects historical trends. The list includes words such as British, militias, Spain, slavery, emancipation, coinage, interstate, depression, atoms, communism, jobs, children, Medicare, America, and century. Kleinberg conceived the idea as he dealt with his flood of incoming email—from other computer scientists, the keywords related to hot topics; from students, the word prelim burst shortly before each midterm exam. A search for these words provided ways to categorize messages. When an important topic comes up for discussion, keywords related to the topic will show a sudden increase in frequency. He devised a search algorithm to look for “burstiness,” measuring the number of times words appear and the rate of increase in those numbers over time. His technique could have many data mining applications, including searching the Web or studying trends in society as reflected in Web pages.

› Back to Top  /  › Next Article  /  › Back to Listing

If you can see this message in a graphical web browser, then you are most likely using a non-modern browser. People who are using a graphical browser have the following options:

Upgrade to a modern generation web browser such as Mozilla, Opera, or for Mac users there is also Safari.

For people using early generation web browsers, such as Netscape 4, you can access the content of this page as is but there may be presentational errors.

Cornell University  
222 Day Hall
Ithaca, New York

P: 607.255.7200
F: 607.255.9030
E: VP Research
C: Credits