Unreal information detection method based on BERT model and enhanced hybrid neural network

Abstract

The invention discloses an unreal information detection method based on a BERT model and an enhanced hybrid neural network. The method comprises the steps of preprocessing a to-be-detected text; performing convolution and pooling operation on the input matrix by using a CNN network, and splicing the input matrix into a feature sequence; taking the feature sequence as the input of a BiLSTM network,and comprehensively capturing the deep semantic features of the text from the front direction and the rear direction by using a forward LSTM unit and a backward LSTM unit respectively; generating a semantic code containing attention distribution by utilizing an attention layer, and optimizing a feature vector; and finishing classification detection of the feature vectors by utilizing a classifierof the output layer, and judging whether the feature vectors are the non-real information. According to the method, the CNN, the BiLSTM and the attention mechanism are combined, the detection precision of the unreal information is high, local phrase features and global context features of the text of the unreal information can be extracted, text keywords can also be extracted, and the unreasonable influence of irrelevant information on a detection result is reduced.

Description

technical field [0001] The invention belongs to the field of text detection and recognition, and in particular relates to a false information detection method based on a BERT model and an enhanced mixed neural network. Background technique [0002] With the rapid development of Internet technology, false information on the Internet is rampant, and the dissemination of false information on the Internet affects the normal social order and disrupts social order. It is very important to effectively and quickly detect false information on the Internet and suppress its spread. In recent years, platforms for exposing false information on the Internet mostly rely on experts in various fields to identify false information, which consumes a lot of manpower and time. It is difficult to guarantee the accuracy of detection and the detection time is long. Therefore, it is very realistic to build an automatic false information detection system. significance. [0003] The feature engineeri...

AI Technical Summary

Problems solved by technology

In recent years, platforms for exposing false information on the Internet mostly rely on experts in various fields to identify false information, which consumes a lot of manpower and time. It is difficult to guarantee the accuracy of detection and the detection time is long. Therefore, it is very realistic to build an automatic false information detection system. significance

[0003] The feature engineering of the false information detection algorithm based on traditional machine learning is cumbersome, so most researchers focus on the deep learning-based false information detection algorithm, but the existing deep learning-based false information detection algorithm ignores the false information text Differential expressions of polysemous words, and most of them use a single deep neural network, which cannot aggregate the advantages of different types of deep neural networks, resulting in unsatisfactory detection results

Images