A Spread Control Method for Rumor-Refuting Game Based on Sparse Representation and Tensor Completion

Abstract

The invention belongs to the field of network public opinion analysis, and specifically relates to a method for controlling the spread of rumor-refutation game based on sparse representation and tensor completion. The method includes: obtaining user data information, and preprocessing the user data information; The relevant attributes of user data information; input the relevant attributes of user data information into the rumor-refutation game propagation model based on sparse representation and tensor completion, and predict the trend of user spreading rumors; according to the predicted user rumor spreading trend, the rumor spreading users to control and prevent the spread of rumors; the invention uses evolutionary game theory and neural network to predict whether users will participate in the topic of rumor-refuting rumors, and can dynamically predict when users will participate in the discussion of the topic, and predict the development trend of the rumor topic Get situational awareness.

Description

technical field [0001] The invention belongs to the field of network public opinion analysis, and in particular relates to a rumor-repudiation game propagation control method based on sparse representation and tensor completion. Background technique [0002] Network rumors refer to offensive and purposeful network information that is spread through network media (such as twitter) without factual basis. With the rapid development of the Internet and the promotion of social media, social media has the characteristics of freedom, interaction, diversity, speed, and popularity, which makes the generation and dissemination of online rumors easier. When it is spread in large numbers, it usually causes panic among the general public, and also has a bad impact on the social economy and social order. Carrying out research on the prediction model of rumors and rumor-refuting topics will help to grasp the distribution of group forwarding characteristics, which is of great significance ...

AI Technical Summary

Problems solved by technology

[0004] Understanding the law of rumor propagation is the key issue of rumor control, but most studies on rumor propagation models ignore the sparsity of valid data in the rumor propagation space, resulting in one-sided conclusions, the paper Chen J, Wu Y, Fan L, et al. N2VSCDNNR: A Local Recommender System Based on Node2vec and Rich Information Network [J]. IEEE Transactions on Computational Social Systems, 2019. Using node2vec to capture complex latent relationships between users from the corresponding network to Alleviate data sparsity problem

However, this paper only considered the influence factors of users and rumor information itself, ignoring the influence of other information in the propagation space at the same time on the spread of rumors, resulting in poor follow-up control of rumors

Images