University of California | Research | Trimming time in the stacks

Here is a link to a story about a UC computer scientist who has developed a new text mining/ topic modeling software program.  Some researchers have already used it to investigate ideas about God in over 4,000 slave narratives.  The software recognizes topics and themes in text and searches, even when the researcher does not have a specific key word that he/she is looking for.  Surprisingly, it looks like the computer accepts queries such as “What does God do?”  It returns results just like a keyword search would, only it analyzes the text and finds the likeliest areas where the text may speak to a complex question like this.  This is a big improvement over keyword searching, and presumably makes it possible to skip a lot of preliminary reading of texts in humanistic research.  Potentially a boon for scholars.

University of California | Research | Trimming time in the stacks.

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s