Summary

KEA is an algorithm for extracting keyphrases from text documents. It can be either used for free indexing, where keyphrases are selected from the document itself, or for indexing with a controlled vocabulary. KEA can also be used for automatic tagging.

KEA is implemented in Java and is platform independent. It is an open-source software distributed under the GNU General Public License.

Authors: Olena Medelyan and Eibe Frank (University of Waikato, New Zealand)

Need support?

There is a support discussion group for all users of Maui: http://groups.google.com/group/kea-and-maui-support

KEA as a service

Joseph Turian has provided an XML-RPC service for Kea on GitHub. He has also written an informative blog post about this service and keyphrase extraction software in general.

More info

• General information
• Previous versions
• How it works
• Publications
• Examples
1. Agrovoc thesaurus for agricultural documents
2. Medical Subject Headings
3. High Energy Physics
4. Keyphrase extraction of computer science articles

See also: Maui - algorithm for topic indexing, which can be used for the same tasks as Kea, but offers additional features. Maui also allows indexing using Wikipedia as a controlled vocabulary.

Name

In real life, the Kea is one of New Zealand's native parrots, famed for theft, destroying cars and cameras, forming street gangs, pecking sheep to death for their delicious kidney fat, and other cutesy antics.