A method for mining friend relationships in social networks based on user behavior

Abstract

A method for mining friend relationships in a social network based on user behavior, comprising the following steps: 1) establishing a bipartite graph and a directed transfer network, namely user-restaurant and user-taste, respectively, through the recorded data of the user's existing social behavior; )According to the network topological relationship, extract the characteristic variables about the nodes or edges that represent the social behavior between two users; 3)Use the machine learning classifier model xgboost to pass all sample data through 10-fold cross-validation, train and construct User relationship predictor model; 4) Take the average of 10 verification results as the final evaluation score of the model. The invention maps people's social behaviors to the network, and uses network topology features to reflect the common variables of social behaviors, so that the result of predicting the friendship between users has high accuracy, which is not only beneficial to guide users to find suitable new friends, but also Help merchants recommend more valuable information.

Description

technical field [0001] The invention relates to the fields of data mining and recommendation systems, in particular to a method for mining friend relationships in a social network based on user behavior. Background technique [0002] Domestic social networks emerged around 2005, imitating the applications of American social platforms such as Friendster and Facebook, and a number of social networking sites such as Xiaonei (later Renren), 51.com, Douban, Ruolin, and Tianji. The service has been launched successively. Especially in 2008, Kaixin.com launched social network games such as "buying and selling friends", "grabbing parking spaces", and "stealing vegetables", which made Kaixin.com quickly become popular among white-collar workers, catching up with Renren.com, the "boss" of the social platform at that time. . After more than ten years of development of social platforms, WeChat and Weibo, the mainstream domestic platforms, integrate social networking, shopping, and fin...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the disadvantage that the traditional friendship prediction model cannot maintain a high level of both accuracy and recall, the present invention proposes a social network based on user behavior that takes both accuracy and recall into account and has a good prediction effect Method of Mining Chinese Friendship Relationship

Images