Information technology and society: Technology for automated classification of large scope of information has been developed

The OpenText company has presented the OpenText Auto-Classification technology intended for transparent automated classification of information. The solution offers big companies a new way of management of distribution and preservation of a large scope of automated content including the content of social networks, e-mail, office documents and archival data.

According to the developer, the OpenText Auto-Classification ensures the ordered and safe classification of the entire content directly after installation and launch of the system. The process goes without participation of the end user. The application uses the OpenText Content Analytics tool which processes every document, electronic letter or post in a social network and classifies the obtained data in accordance with corporative policy and legislation requirements. In contrast to the search and analysis of the text by the key words, OpenText Content Analytics codifies language particularities of the text defined by special groups of linguists which enables to improve significantly the accuracy of data classification.

The new application of the OpenText excels other classification systems based on the “black box” model since it includes tools for definition of documents and rules, as well as for selection of data from a large number of documents in the continuous mode. This kind of technology contributes to the permanent improvement of the system and increase of effectiveness and classification quality.

The OpenText Auto-Classification application is integrated to the OpenText Records Management which enables to use the current rules of classification and classified data at the stage of the setting of the application. The OpenText Auto-Classification application will be available for customers in the end of the year.