Monitoring method and system for microblogging public opinion

Abstract

The invention relates to monitoring method and system for microblogging public opinion. The system comprises a data acquiring die for crawling real-time microblog data and writing into a database, a hot microblog detecting module for sequencing the real-time microblog data within the preset time according to the preset algorithm and screening the hot microblogs within the specific time quantum, an abnormal microblog monitoring device for vectoring microblog texts, clustering the vectored microblog texts and selecting the microblogs with the highest hot level from various microblogs to be used as the monitored abnormal microblogs, and a data display module for displaying the hot microblogs and the abnormal microblogs with corresponding quantity according to the preset threshold. With the adoption of the method and system, the microblogs within a period of time can be quickly analyzed, the hot microblogs can be extracted, and the hot microblog topic can be tracked; the real-time microblog within a period of time can be monitored, and the abnormal microblog within the latest period of time can be detected; the data can be automatically cleaned by the system; the mature clustering method is used as the algorithm to ensure relatively high stability and accuracy.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to a microblog public opinion monitoring method and monitoring system. Background technique [0002] Weibo is a new media emerging in recent years, which has the characteristics of convenience, face-to-face and originality. In today's data explosion, it is impossible for users to obtain real-time emergencies by reading a large amount of Weibo information. Therefore, it is very meaningful to mine unexpected events that users are interested in from massive microblog data. [0003] In the prior art, emergent events are mined in the order of emergent feature recognition, and emergency event recognition can be divided into text-centered methods and burst feature-centered methods. The former is to cluster the text first, and then extract the burst features in the class to identify the burst event; the latter is to extract the burst features first, then group the burst features...

AI Technical Summary

Problems solved by technology

[0004] The text-centered method works well for traditional texts, but microblog texts are sparse and contain a lot of spam. Clustering first and then burst feature recognition will introduce a lot of noise information, and there are still some noises in the text clustering. There are many threshold selection problems. The threshold selection is mostly set based on empirical values ​​and is sensitive to clustering results.

The bursty feature-centric method avoids the threshold problem, but does not solve the spam problem well

Images