SAS® Content Categorization illuminates unstructured and semistructured content so organizations can lead with confidence

Easy-to-use software automates categorization of multilingual content, including wikis and blogs, to reveal valuable insights

Organizations are clamoring to purge content chaos. Applying search techniques to content that lacks a well-defined organizational structure just is not effective in gleaning value from data generated by applications, records, business processes, blogs, wikis and external sources proliferating in today’s organizations. Shipping now, SAS Content Categorization, from the leader in business analytics, correctly and meaningfully parses and analyzes enterprise content for entities and events. It creates robust metadata to trigger business processes that can improve organizational performance. The new standalone product is powered by a division of SAS, Teragram, the market leader in mobile and multilingual natural language processing technologies.

“SAS Content Categorization organizes and dramatically increases the findability quotient for information,” said Gaurav Verma, Global Marketing Manager for Business Analytics at SAS. “It processes enormous volumes of content and eliminates manual and redundant content tagging that many organizations struggle with. Its advanced linguistic and natural language processing techniques recognize and analyze more than 30 languages, allowing global organizations to better manage and govern multilingual content that is critical in today’s regulatory environment.”

With SAS, organizations can fully leverage content assets and provide for reuse across disparate departmental repositories, regardless of who owns the content or where it was generated. Capabilities that competing offerings cannot deliver include:

* Taxonomy creation – The intuitive and easy-to-use graphical interface lets users create an organized information system of categories and concepts.
* Category classification – Custom-defined category rules let users classify documents that match a rule and exclude texts that do not.
* Collaboration – Multiple taxonomists and developers, working individually or in teams, can securely access projects.

"Leading organizations such as the Associated Press, CNN, Factiva, eBay, Forbes.com, NYTimes Digital, Reed Business Information, Sony, washingtonpost.com, Wolters Kluwer, the World Bank and Yahoo! are using unstructured data in their analyses – of customers, market opportunities, internal operations, supply chains – and we enable fast, accurate access to the information they need for decision making,” said Yves Schabes, President of Teragram. “Teragram’s advanced categorization technologies power SAS Content Categorization to provide instant, advanced classification of enterprise documents to help organizations fully leverage their information assets.”

As an example, taxonomy creation is helping Reed Business to process billions of b-to-b related documents, including information on 14 million companies, millions of people, and thousands of product categories and topics. Reed Business uses this technology to deliver better search results to its sites’ visitors.

SAS Content Categorization provides flexibility by applying advanced linguistic rules for unique, identifying terms, increasing specificity and defining category rules to classify documents that match those rules. In doing so, SAS Content Categorization drastically reduces the overhead associated with the content categorization process – which is good news to management who must help control expenses.