Topic Modeling is a form of text mining that 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.
- Press Release from U. of California-Irvine announcing a successful demonstration of topic modeling
- Mining the New York Times with machines from Ars Technica
- Tracking the Congressional attention span from Ars Technica
- Definition of "Topic Modeling" from The Tao of Mac
- Text mining the New York Times from ZDNet's Blog