Course #
30520

The purpose of the class is to provide the public policy student a set of skills that he or she can use in their professional career to compile and analyze unstructured data. If a public policy analyst is asked by the chief of staff to compile everything that is known about managed care for elderly patients, the analyst should be able to mine the available databases on the web to pull out a set of abstracts, data, information, or policy recommendations so that he or she can have report done in hours rather than weeks. If a congressman asks his aid to pull information on earmarks on a particular topic from the United State Public Laws, they should be able to do that in a few hours after taking this class. 

The first half of the class will include lectures on the importance of the techniques for public policy.  Much of the remainder of class will be devoted to teach natural language text processing through a set of weekly exercises.  The other focus of the class will be application of that programming to “real” datasets that reflect public policies. The class with jointly create a corpus from publicly available sources. The final weeks of the class will focus on student projects, individual or group, making use of the corpus.  These projects will be presented to the entire class and a paper will be required.