Bilinear neural network false news detection method and system based on style guidance

A neural network and detection method technology, applied in the field of news detection in big data mining, can solve the problems of lack of analysis, news recognition accuracy is difficult to reach the expected level, etc., to achieve high recognition accuracy, improve recognition accuracy and generalization performance , the effect of good migration

Active Publication Date: 2019-09-06
INST OF COMPUTING TECH CHINESE ACAD OF SCI
View PDF6 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] When the inventors conducted research on false news detection, they found that the existing methods often rely too much on the news itself, and lack of analysis...

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Bilinear neural network false news detection method and system based on style guidance
  • Bilinear neural network false news detection method and system based on style guidance
  • Bilinear neural network false news detection method and system based on style guidance

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The purpose of the present invention is to provide a knowledge-guided false news detection method, the main problem to be solved is how to use the common language style features of false news to guide the model to obtain more generalized features, so as to improve the accuracy of the model on newly generated news. Detection effect.

[0037] Key points of the present invention include:

[0038] 1. Quantification of language style: Language style refers to the expression form of language, mainly manifested in differences in the distribution of vocabulary, grammar, and rhetorical means. Language style focuses on how events are expressed rather than the event content itself. However, language style is an abstract concept, which needs to be quantified according to specific needs;

[0039] 2. Text feature extraction: Text features are an important basis for the model to determine whether news is fake news. In the present invention, a text feature is extracted using a two-wa...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a bilinear neural network false news detection method and system based on style guidance. The method comprises the following steps: acquiring a news text to be subjected to network false news detection, quantifying language style characteristics of the news text through a neural network to obtain a style vector of the news text, and inputting the news text into a text characteristic extractor to obtain a text vector of the news text; inputting the style vector and the text vector into a bilinear neural network, the bilinear neural network comprising a bilinear function for modeling a correlation between the style vector and the text vector to obtain a style-style of the news text; using the maximum score vector in the style-text feature matrix to form a guide vector,and inputting the guide vector to the full connection layer to determine the false news label of the news text. The learning process of the deep learning model is guided according to the language style of the false news generality, and the recognition accuracy and the generalization performance of the model are improved.

Description

technical field [0001] The invention relates to the field of news detection in big data mining, and in particular to a style-guided bilinear neural network false news detection method and system. Background technique [0002] The rapid development of social media has changed people's daily life, and users can easily and freely publish and obtain information from social media. However, the flourishing of social media has also provided fertile ground for the breeding and dissemination of fake news. According to statistics, during the 2016 U.S. presidential election alone, 529 pieces of false news about presidential candidates were generated and spread up to 37 million times. False news has seriously polluted the network social environment and affected the daily life of users, so there is an urgent need for automatic detection of fake news on social media. [0003] In existing studies, researchers usually focus on news content and corresponding social relations. Martin et al...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F17/27G06N3/04G06N20/00
CPCG06N20/00G06F40/205G06F40/30G06N3/045
Inventor 曹娟王佳臣谢添李锦涛郭俊波
Owner INST OF COMPUTING TECH CHINESE ACAD OF SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap