Label-based social network user interest mining method and device

Abstract

The invention relates to a label-based social network user interest mining method and a label-based social network user interest mining device. The label-based social network user interest mining method comprises the following steps of: collecting all data of a user in a social network, wherein the data comprises textual data generated by the user in the social network and association relationship data of the user in the social network with the textual content; acquiring all labels included in the textual data generated by the user and a weight corresponding to each label; converting the association relationship data of the user with the textual content into a user-relationship chain form; combining the labels of the user on all contents to obtain a label interest column of the user; vectorizing the label interest column; abstracting a label interest vector to obtain a low- category interest vector and a high-category interest vector; and providing corresponding interest information for the social network user according to a specific requirement of the application scene based on the low-category interest vector, the high-category interest vector and the label, thereby realizing social network user interest mining.

Description

technical field [0001] The invention relates to the field of Internet information mining, in particular to a label-based method and device for mining interests of social network users. Background technique [0002] Existing methods for user interest acquisition and application are mainly divided into the following different systems: [0003] 1. Association system: The method of this system utilizes the direct association between users and entities, and uses herd methods such as collaborative filtering to associate entities that users may be interested in but have not yet been associated with the user. [0004] Advantages: Simple and clear, good judgment results can often be obtained for herd-like users and entities; [0005] Disadvantages: Can't judge the interest of niche users; can't directly define the user's interest, can only judge the user's preference for specific entities. [0006] 2. Entity labeling system: The technical means used in this system is to provide inp...

AI Technical Summary

Problems solved by technology

[0005] Disadvantages: It is impossible to judge the interests of niche users; it cannot directly define the interests of users, and can only judge the degree of preference of users for specific entities

[0008] Disadvantages: Labels cannot be standardized and difficult to use; most users are unwilling to fill in; for a single entity, the number of collected labels is small and the description is incomplete; it is impossible to directly describe user interests

[0011] Disadvantages: It is necessary to classify and map entities in advance. If the number of entities is large, it will face the problem of high mapping cost and low accuracy; the flexibility is not enough, and it cannot correctly reflect changes in user interests; the number of categories is limited, and user interests cannot be adjusted a little more detailed description

Images