Hot Neuron releases Clustify 2.2

Hot Neuron has announced the release of Version 2.2 of its Clustify document clustering software, featuring user-adjustable word weights and other improvements.

Clustify groups related documents into clusters and labels each cluster with a few words to tell what it is about, allowing the user to explore the document set and efficiently and consistently categorize documents. Version 2.2 gives users the ability to adjust the weighting of words used for clustering in order to encourage clusters to form around words that are of special interest. The new version also features an improved near-duplicate detection algorithm, more flexible export of results to other e-discovery tools and more useful cluster sorting.

Clustify can generate concept-based clusters, or it can require documents in the same cluster to contain identical passages of text to detect near-duplicates (i.e. different revisions of the same document). It also has an automatic categorization capability to reduce the amount of manual labor necessary for categorization when new documents are added to a dataset. It can handle millions of documents on a typical desktop computer.