Note that selecting the option to create a cluster score on each document object in the source set when performing the cluster mass operation will lead to the Analytics engine taking far longer to complete the process.
Updated: Dec 29, 2021
top of page
LITIGATION SUPPORT TIP OF THE NIGHT
The views expressed in this blog are those of the owner and do not reflect the views or opinions of the owner’s employer. All content provided on this blog is for informational purposes only. The owner of this blog makes no representations as to the accuracy or completeness of any information on this site or found by following any link on this site. The owner will not be liable for any errors or omissions in this information nor for the availability of this information. The owner will not be liable for any losses, injuries, or damages from the display or use of this information. This policy is subject to change at any time. The owner is not an attorney, and nothing posted on this site should be construed as legal advice. Litigation Support Tip of the Night does not provide confirmation that any e-discovery technique or conduct is compliant with legal, regulatory, contractual or ethical requirements.
New tips for paralegals and litigation support profesionals are posted to this site each week. Click on the blog headings for better detail.
Search
When running the Cluster mass operation in Relativity you'll see an option labeled, 'Create Cluster Score Field'.
If this box is checked off, the Analytics engine will generate a field which will show each document object's coherence score for a given cluster. This score shows a document's coherence score within the cluster. The coherence score used in the field tree for a cluster indicates how conceptually similar all of the documents in a cluster are. The document object cluster coherence score shows how far the document is from the middle of the cluster.
A coherence score will be some value between 0.0 and 1.0, with 1.0 indicating the greatest possible similarity, and a score of 0.0 for the lowest end of coherence for a cluster.
The cluster score field will be named in this format, 'Cluster :: [ClusterName] :: Score'. So in this below example we can see a set of documents which have scores of between 0.0 and 1.0 in the field named, 'Cluster :: custodians :: Score'. The document, AZIPPER_0007291 is in the cluster named, '02 gas, spread, heat, charts' and then down in the subcluster, '2.2 energy, power, trading, curve' and the sub-subcluster, '2.2.1 energy, curve, futures, nat ', and it has a score of 0.64, indicating how well it represents the cluster's overall concept. The coherence score for the cluster is 0.53 which shows how conceptually similar all 517 documents in the cluster are.
Clustering is a Relativity analytics process which is performed by selecting Cluster from the mass operations menu:
Another way to perform clustering automatically is to set the option to cluster documents when creating a conceptual index:
bottom of page