Microblog popularity degree prediction method based on user and microblog theme and microblog popularity degree prediction system based on user and microblog theme

Abstract

The present invention relates to the social network analysis field, in particular to a microblog popularity degree prediction method based on a user and microblog theme and a microblog popularity degree prediction system based on the user and microblog theme. The method comprises the steps of obtaining the microblog data and the user data in a preset time period, obtaining the user attribute characteristics and the microblog theme characteristics according to the microblog data and the user data, carrying out the normalization processing on the user attribute characteristics, carrying out the user clustering on the processed user characteristics, and obtaining the user class information according to a clustering result; according to the microblog theme characteristics and the user class information, obtaining a forwarding characteristic of the user clustering under a microblog theme, and calculating a weight coefficient under the microblog theme of the user clustering; according to the microblog theme characteristics, the user attribute characteristics and the weight coefficient, constructing a microblog popularity degree prediction model, and predicting the microblog popularity degree according to the microblog popularity degree prediction model.

Description

technical field [0001] The invention relates to the field of social network analysis, in particular to a microblog popularity prediction method and system based on users and microblog topics. Background technique [0002] With the rapid rise of web2.0, Weibo has gradually become an important platform for people to obtain and share information. Due to the instant sharing, real-time, interactive and diversity of communication methods of information, Weibo has made many news events and hot spots Topics spread quickly and widely on Weibo sites, profoundly affecting people's lives and work, and greatly improving the service performance of network media. [0003] The microblog platform generates a large amount of information all the time, and microblog users tend to pay more attention to the valuable information. Therefore, there needs to be a method to dig out valuable and highly popular microblogs from the massive microblog information. Recommended to users; in addition, in ter...

AI Technical Summary

Problems solved by technology

One is to use the model for fitting, mainly starting from the basic attributes of the user and Weibo, extracting various features (including the number of user fans, followers, authentication information, Weibo text, Weibo spread, etc.), and training model parameters , use a unified model to predict the popularity of microblogs. This kind of method does not take into account the differences of different users, and the effect may be poor in predicting the popularity of a certain microblog; the second type of method is based on classification. The range prediction of the final popularity of the blog can only predict a range of the popularity of the microblog, and the popularity trend of the microblog cannot be completely obtained; the last type of method regards the popularity prediction problem as finding the closest The problem of k historical microblogs is to find the k microblogs most similar to the microblogs to be predicted from the historical microblogs through a series of features, and use the average popularity of the k microblogs as the final popularity of the microblogs to be predicted , but due to the large number of historical microblogs, the time complexity of finding the most similar k microblogs is relatively high, which can only be processed offline and cannot meet real-time needs

In summary, the existing methods lack a method that can accurately predict and support online real-time prediction of Weibo popularity.

Images