11 Oct 2005
CS 5244 - Computational Document
Analysis
13
Genre vs.
Subject (Lee & Myaeng 02)
¡Genre: style and purpose of text
¡Subject: content of text
What about the interaction
between the two?
Study found that certain genres
overlap signficantly in subject vocabulary
¡So, want to use terms that cover more subjects represented
by a genre
¡Do this by selecting terms that:
1.Appear in a large ratio of documents belonging to the
genre
2.Appear evenly distributed among the subject classes
that represent the genre
3.Discriminate this genre from others