Classification Module

For advanced content classification

Classification Module (formerly called InfoSphere Classification Module) automates the organization of unstructured content by analyzing full text of documents and emails.

With advanced content classification, accelerate time-to-value from your Enterprise Content Management investments such as content archiving or electronic records management.

Delivers high ROI by unburdening your end-users and saving them from manual categorization tasks.
Filters from your archive the emails and documents with limited business value.
Organizes your content with consistent, reliable and auditable logic.
Rapidly trains via “learn-by-example” approach for generating policies.
Adapts to changes in policies and categories by incorporating user feedback in real-time.
Automate classifications with high accuracy by combining multiple methods of classification ranging from keyword rules and proximity matching to pattern extraction to highly accurate ‘learn-by-example’ context-based approaches.
Natural language processing support for 18 languages: English, French, German, Italian, Spanish, Dutch, Swedish, Portuguese, Russian, Simple Chinese, Traditional Chinese, Japanese, Korean, Arabic, Farsi, Hebrew, Norwegian, and Finnish.
Is part of the Content Assessment solution.
Operating systems supported: AIX, Linux, Solaris (Sun microsystems), Windows