Abstract: The article describes the architecture and principles of work of the developed system of automated processing of large volumes of textual information. The system is based on the modification of the free software library LibSVM and on the implemented in it method of support vector machines. The system performs functions of search, classification, categorization, and clustering of text documents requested by the user.

Keywords: classification, categorization, clustering, text documents processing.

ACM Classification Keywords: H.3.3 Information Search and Retrieval, H.3.1 Content Analysis and Indexing.

Link:

THE SYSTEM OF MULTILINGUAL TEXT DATA PROCESSING ON THE BASE OF THE MODIFIED ALGORITHM SVM

Oleg Moyseenko

http://www.foibg.com/ijita/vol22/ijita22-03-p07.pdf