ИНТЕЛЛЕКТУАЛЬНЫЙ АЛГОРИТМ ИДЕНТИФИКАЦИИ ДЕСТРУКТИВНОЙ ИНФОРМАЦИИ В ТЕКСТЕ

Abstract

In the context of ensuring the information and psychological security of a society in the Russian Federation, the problem of uncontrolled growth of the Internet destructive content is being considered. The problem of search and identification of destructive information demands the minimal subjectivity and the maximum automation, because it is still solved generally by expert methods with drawing up registers of the forbidden sources. Existing search methods (expert processing, thematic search, intelligent data processing methods) used to find specific words in the text have been considered, the advantages and disadvantages of these methods have been stated. For solving the task set the intellectual algorithm of the modified search of destructive content has been suggested using foul language in the textual information as an example. The suggested approach has a different system of self-replenishment of the dictionary on the basis of identification of the unknown words as foul ones. The correctness of the dictionary replenishment is controlled by an expert. A detailed description of the developed algorithm has been presented. The example of the algorithm operation and initial results of its approbation are given.