Method and device for predicting viral transmission of network information in social network

Abstract

The invention provides a method for predicting viral propagation of information in a social network, which can judge whether a concerned subject is developed into viral propagation or not, and comprises the following steps of: acquiring time and evaluation content of forwarding the concerned subject, constructing a propagation event, slicing according to a time sequence, extracting features, splicing the obtained propagation magnitude characteristics and emotion ratio characteristics, inputting the spliced propagation magnitude characteristics and emotion ratio characteristics into a first CNN filter model for learning to obtain first fusion characteristics, splicing semantic evolution characteristics in each time slice, and inputting the spliced semantic evolution characteristics into a Bi-LSTM network model to obtain second fusion characteristics; splicing the obtained first fusion feature and the second fusion feature, and inputting the first fusion feature and the second fusion feature into a second CNN filter model for learning to obtain a third fusion feature; and constructing a time sequence prediction model, inputting the third fusion feature into the trained time sequence prediction model, outputting a prediction probability that the concerned theme becomes viral propagation, and when the prediction probability is greater than a prediction threshold, determining that the development becomes viral propagation.

Description

technical field [0001] The invention relates to the technical fields of data mining and social network public opinion analysis, and in particular to a method, device and storage medium for predicting viral spread of information in a social network. Background technique [0002] With the rapid development of the Internet, events in social networks are spread in the network with information as the carrier, and the growth rate of its spread has become an evaluation index of social public opinion. If information spreads too fast like a virus infection, it will become a public opinion event. Any news source in the network may become the source of public opinion events, and it will be forwarded in a large amount like a virus in a short period of time, such as network emergencies, judicial events, economic events, security events, etc. It spread widely, and even became a "black swan" event that caused bad social impact. [0003] Viral dissemination of network information means tha...

AI Technical Summary

Problems solved by technology

[0005] However, most of the research that has been done is based on the analysis of the underlying structure of the information dissemination network, including the topology of the dissemination network and user relationship network. Data makes it difficult to obtain global network structure data, and hidden user relationships (such as user relationship networks) are even more difficult to obtain, resulting in poor performance of existing algorithms in practical applications and inaccurate prediction results.

Images