WEB PAGE TOPIC DETERMINATION DEVICE, WEB PAGE TOPIC DETERMINATION METHOD AND WEB PAGE TOPIC DETERMINATION PROGRAM

摘要

PROBLEM TO BE SOLVED: To determine a proper topic specialized for a certain language by constructing a feature from the URL of a web page in consideration of the language used by main browsers.

SOLUTION: The URL of a web page of determination object is input in an input part 10 of a web page topic determination device 1. A language determination part 11 identifies a host use country from the host name in the URL input in the input part 10 and determines a main language in the use country. A feature quantity extraction part 12 extracts a feature quantity corresponding to the main language from a character string of a token obtained by dividing the URL with a symbol or the like. A topic determination part 13 determines a topic in the web page from the feature quantity by using a determination device which has learned whether a topic belongs to a specified topic. An output part 14 outputs the determination result.

COPYRIGHT: (C)2013,JPO&INPIT