Network text sentiment analysis method based on Bi-GRU neural network and self-attention mechanism

Abstract

The invention relates to a network text sentiment analysis method based on a BiGRU neural network and a self-attention mechanism, and belongs to the technical field of information. The method comprises the following steps: S1, acquiring network text information, and encoding a text by utilizing a word embedding vector; S2, summarizing forward and backward information of sentences through a Bi-GRUnetwork layer, and then combining the information from the two directions to obtain a final implicit vector; S3, inputting the obtained implicit vector into a multi-layer perceptron to obtain a new implicit representation, then calculating an importance word-level context vector of a word, and performing random initialization and common learning in a training process; and S4, multiplying the implicit vector of each word by a corresponding weight obtained through a self-attention layer, and then performing text sentiment classification through an improved softmax layer. According to the method,the web text sentiment classification accuracy can be effectively improved.

Description

technical field [0001] The invention belongs to the field of information technology, and relates to a network text sentiment analysis method based on a Bi-GRU neural network and a self-attention mechanism. Background technique [0002] People communicate under the Internet through text to convey their emotions. With the help of this extensive communication method, efficient and convenient information and value transmission are realized. Therefore, mining text and the emotional relationship it conveys in the Internet environment not only promotes the research and development of the NLP field, but also has real value in people's actual lives. [0003] Sentiment analysis is currently an important research direction in natural language processing. It is a process of processing, analyzing, summarizing and inferring subjective texts with emotional factors, which can reflect people's views, emotions, and evaluations on injecting products, services, The attitude of entities such as...

AI Technical Summary

Problems solved by technology

However, the LSTM neural network can only capture the forward part of the sentence

Sometimes the semantics of a word in a sentence cannot be expressed correctly only by the historical information of the sentence. At the same time, adding multiple gates to LSTM leads to an increase in parameters, which leads to a substantial increase in the amount of calculation

Images