Knowledge aggregation of the WeChat Official Accounts Platform based on tag clustering

Abstract

As an important part of social networks, tags are widely used. Tags are similar to keywords, which can express and convey the main ideas or key knowledge of the article. With the increase in the number of visits to the WeChat Official Accounts Platform (referred to as WeChat platform), the number of scientific research published by the platform has also increased rapidly. However, with the increase in the number of posts, readers spend considerable time and energy. Since the articles published on the WeChat platform do not have corresponding keywords or tags, readers cannot quickly acquire knowledge, nor can they realize navigation and query of knowledge resources. To save users' effective reading time and improve users' reading efficiency, the articles published on the platform can be preprocessed to enable quick matching between readers and articles. How to extract the knowledge that users need from articles in different fields to help users find valuable knowledge quickly and effectively, in addition to how to realize domain knowledge resource retrieval and navigation, are important issues facing the current WeChat platform to carry out knowledge services. To solve the problems, this research extracts keywords from the articles published on the WeChat platform as article tags and proposes a framework for knowledge aggregation on the WeChat platform based on tag clustering.