ZDNet: Text mining the New York Times
UCI: UCI researchers ‘text mine’ the New York Times, demonstrating evolution of potent new technology
UCI researchers performed their experiment using a statistical topic model based on a text model developed at UC Berkeley in 2003. Thanks to an improved solution technique proposed by Mark Steyvers and a research partner, this model has advanced from academic use to something that is now widely used in the research community. Topic modeling looks for patterns of words that tend to occur together in documents, then automatically categorizes those words into topics. Older text-mining techniques require the user to come up with an appropriate set of topic categories and manually find hundreds to thousands of example documents for each category. This human-intensive process is called supervised learning. In contrast, topic modeling, a type of unsupervised learning, doesn’t need suggestions for an appropriate set of topic categories or human-found example documents. This makes retrieving information easier and quicker.
natural language processing