[MAHOUT-163] Get (better) cluster labels using Log Likelihood Ratio

• Type: Improvement
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Fix Version/s: 0.3
• Assignee: Grant Ingersoll
• Reporter: Shashikant Kore
• Created: 13/Aug/09 10:35
• Updated: 21/May/11 03:24
• Resolved: 12/Jan/10 11:15

Description

Log Likelihood Ratio (LLR) is a better technique to identify cluster labels instead of the top features of the centroid vector. LLR finds terms/phrases which are common in the cluster but rare outside.