Self-supervised learning rumor detection method and system, equipment and storage medium

Abstract

The invention discloses a self-supervised learning rumor detection method and system, equipment and a storage medium, and the related method comprises the steps: modeling a message propagation process as a propagation tree, employing a graph encoder to encode the graph structure information of the propagation tree, and obtaining a propagation representation; encoding text content information of the message by adopting a text encoder, and obtaining text representation; on the basis of a self-supervised learning mode, improving the similarity between the propagation representation and the text representation of the same message, and reducing the similarity between the propagation representation and the text representation of different messages; and performing rumor detection by using the message representation obtained based on the self-supervised learning mode. According to the scheme, information of multiple sources is synthesized through self-supervised learning, more comprehensive expression of the message is obtained, and then the accuracy and stability of a downstream automatic rumor detection task are improved.

Description

technical field [0001] The present invention relates to the technical field of rumor detection, in particular to a rumor detection method, system, device and storage medium of self-supervised learning. Background technique [0002] With the development of the Internet, social media platforms have become one of the main sources of information for users today. While bringing convenience, it also provides a fertile ground for rumors to spread, posing a serious threat to society and public safety. In the era of information explosion, online news is overwhelming, and manual screening of rumors will consume a lot of manpower and material resources. Under this background, automatic rumor detection came into being. [0003] Aiming at the problem of rumor detection on social platforms, there are currently the following types of methods: [0004] Content-based approach (Content-based). Such methods directly extract information such as part of speech, word meaning, emotion, opinion,...

AI Technical Summary

Problems solved by technology

However, when the message propagation period is long, the timing model will forget the previously learned knowledge in the later learning process

In addition, the reliance on timing features makes it difficult for the sequence model to make judgments in the early stages of news release

[0007] All in all, these methods have achieved good results in automatic rumor detection tasks, but it is difficult to get good performance in all scenarios with thin features, so the detection performance needs to be improved

Images