Multi-information fusion microblog hot topic detection method

Abstract

The invention discloses a microblog hot topic detection method based on multi-information fusion. Firstly, influences of a blogger is calculated according to social relations of a microblog promulgator, and a sum of weights of a feature word in all microblogs in a given time period is further calculated based on influence information of the blogger and frequency information of the feature word; then a sudden feature word is detected according to information of the sum of the weight of the feature word along with time changes, microblog data are expanded by introducing Web news linguistic data to calculate an incidence relation valve between sudden features, and an association graph of the sudden feature word can be further constructed; finally, the association graph of the sudden feature word is divided, each strong connected subgraph indicates a topic, and accordingly detection on a microblog hot topic can be achieved. The microblog hot topic detection method comprehensively uses microblog feature word information, blogger social relation information and relative Web news document information to detect the microblog hot topic, and improves detection efficiency of the microblog hot topic.

Description

Technical field [0001] The invention relates to a microblog hot topic detection method based on multi-information fusion, which can automatically detect new hot topics in the microblog. It can be applied to various types of social media data, and is suitable for data mining in social networks and social network public opinion monitoring. Background technique [0002] With the development of Web2.0 technology, Web-based social networks have become more and more popular. Especially in recent years, online social networks have attracted more and more network users and have become the hottest network platform, social network. User-generated information has become the main source of Internet content. For example, Sina Weibo has nearly 200 million registered users in just over a year, generating more than 80 million Weibo every day, and Sohu Weibo has more than 20 million users. With the increase in the number of users, Weibo has gradually become the main place to reflect social hot ...

AI Technical Summary

Problems solved by technology

[0003] Traditional research on topic detection methods is mainly aimed at Internet information itself. Its methods and technologies are mainly oriented to traditional news document data. The data are regarded as isolated information for research. Without in-depth mining and analysis of the social relationships contained in online social networks, it is impossible to Taking advantage of the characteristics of social networks, it cannot effectively detect hot topics in Weibo

In addition, the current hot topic detection methods for Weibo face the problem of data sparsity, and these methods do not take advantage of other types of web resources

Images