USER INTEREST INFERENCE METHOD AND SYSTEM IN SNS USING TOPICS ON SOCIAL ACTIVITIES WITH NEIGHBORS

摘要

PURPOSE: Provided is to enhance the accuracy and to reduce errors which are occurred in a traditional approach method inferring user interests through familiarity analysis or neighbor interest analysis. CONSTITUTION: A topic is extracted from communication log between a user and his/her neighbors (S110). Similarity of interests is calculated from the extracted topic (S120). Calculate the familiarity between the user and neighbors (S130). Based on the similarity and familiarity, a correlation diagram is produced which explains how much a topic is related to the user in each category (S140). Using the produced correlation diagram, infer the interests of the user (S150). [Reference numerals] (110) Extract topic from communication log between a user and his/her neighbors; (120) Calculate similarity of interests per each society and neighbor from the extracted topic; (130) Calculate familiarity between the user and social neighbors; (140) Calculate familiarity indicating explains how much a topic is related to the user in each category; (150) Infer the interests of the user by using the produced correlation diagram; (AA) Start; (BB) End