Rumor detection method and device fusing user information and text information

Abstract

The invention provides a rumor detection method and device fusing user information and text information. The method comprises the steps of obtaining first source text information of a to-be-detected event and first user information corresponding to the first source text information; inputting the first source text information and the first user information into a conditional generative adversarial network model to obtain simulation response data of the to-be-detected event generated by the conditional generative adversarial network model; inputting the first source text information, the first user information and the simulation response data into a classification model to obtain a rumor detection result of the to-be-detected event output by the classification model; in the whole rumor detection process, the rumor detection result of the to-be-detected event can be quickly obtained only according to the first source text information and the first user information of the to-be-detected event, and good timeliness is achieved; moreover, the first source text information, the first user information and the simulation response data are combined, so that the rumor detection result is more accurate.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a method and device for detecting rumors that fuse user information and text information. Background technique [0002] Social media is a double-edged sword for news consumers. Because of its low cost, easy access and rapid information dissemination, social media brings convenience for people to keep abreast of news. However, it also creates a favorable environment for fake news to thrive. Fake news refers to intentionally fabricated rumors that are contrary to the facts. It has a certain degree of secrecy and deception and will bring adverse effects and losses to society. [0003] To deal with a large amount of news on the Internet, it is necessary to build a corresponding automatic detection model to identify fake news and detect rumor events. Existing rumor detection technologies have the following problems: (1) Most of the existing rumor detection technologies use u...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a rumor detection method and device that integrates user information and text information, which is used to solve the defects of poor performance in early detection and inaccurate detection of rumors in the prior art, and to realize fast and accurate detection of rumors

Images