PRINCIPLES AND METHODS OF PERSONALISING NEWS FLOW BY ANALYSING RECENTNESS AND DYNAMICS OF INFORMATION

摘要

FIELD: physics; computer engineering.;SUBSTANCE: system and method are presented for filtering temporary flow of information such as news accounts using statistical measures of information recentness. Different methods can be applied to individually complied news flow or other types of information based on information which the user has already seen. Methods are provided for analysing recentness of information along with a system which personalises and filters information for users by determining recentness of accounts in the context of accounts already browsed by the users. The system uses algorithms for analysing recentness, which present articles as a set of words and named object substances. The algorithms analyse dynamics between and inside documents by examining how information develops over time from article to article, as well as inside separate articles.;EFFECT: possibility of sorting news articles so that each article adds maximum information relative previously presented information units.;14 cl, 13 dwg