A Multi-Strategy Based Microblog Information Priority Collection Method

Abstract

The invention relates to a multi-strategy-based microblog information priority collection method. In the case of limited collection capability, by constructing a multi-strategy priority collection method, blogger information can be obtained in a timely and effective manner. First of all, the bloggers are screened by building a classification model, spam bloggers are eliminated, and the remaining bloggers are divided into three categories according to the number of microblogs and the number of fans. Second, construct different collection strategies for different categories. By clustering the posting time of the big V bloggers, the best collection time of the big V bloggers is extracted; through the microblog statistics of the bloggers, the regression model is trained and the blogger’s activity value is predicted. According to the activity value, the Bloggers sorted. Finally, a multi-strategy microblog priority collection method is designed by synthesizing the three types of collection strategies, and the timeliness of the collection strategy is maintained by regularly updating the collection queue. Experiments show that the present invention can not only acquire hot microblog information in a timely and effective manner, but also greatly increase the number of acquisitions.

Description

technical field [0001] The invention belongs to the field of text information processing, and specifically designs a method for preferentially collecting microblog information based on multiple strategies. Background technique [0002] Weibo has become one of the most important information exchange platforms in China. Daily news at home and abroad, celebrity activities, and interesting events in life will all become topics of discussion for people, so a large number of related information will be updated every day. information, these are often referred to as hotspot information. By analyzing the hotspot information on Weibo, we can effectively obtain the hotspots that netizens pay attention to. Web crawlers can effectively collect the page information of Weibo bloggers, so as to obtain hotspot information in a timely manner. However, with the huge increase of microblog bloggers and the limited collection capacity, it is difficult to collect microblog information in real ti...

AI Technical Summary

Problems solved by technology

[0005] Finally, there are a large number of potential zombie accounts or marketing accounts among Weibo bloggers, and the Weibo posts are not only insufficient in information, but also have a large number of Weibo, which wastes a lot of time in the collection process, causing normal bloggers hotspot information cannot be collected in time

Images