Coarse-grained emotion analysis method based on hierarchical BERT neural network

Abstract

The invention relates to a coarse-grained emotion analysis method based on a hierarchical BERT neural network, and belongs to the technical field of Web mining and intelligent information processing.The method comprises the following steps: corpus acquisition: acquiring a corpus of coarse-grained sentiment analysis; corpus preprocessing, wherein character cleaning, subordinate clause segmentationand subordinate clause vector construction are included; constructing sentence vectors: calculating the subordinate clause vectors by utilizing a bidirectional long and short term memory network, a multi-layer perceptron and an attention mechanism to generate sentence vectors; gradient coordination mechanism optimizing: introducing the gradient coordination mechanism to solve the problem of datatype imbalance in coarse-grained sentiment analysis; and carrying out coarse-grained sentiment analysis by adopting a hierarchical BERT neural network. Compared with the prior art, t the sentence vectors containing deep semantic information are constructed for the comment text through the hierarchical BERT neural network, the accuracy of coarse-grained emotion analysis tasks is improved, and the method has a wide application prospect in the fields of information recommendation, public opinion monitoring and the like.

Description

technical field [0001] The invention belongs to the technical field of Web mining and intelligent information processing, and relates to a coarse-grained sentiment analysis method based on a hierarchical BERT (Bidirectional Encoder Representation from Transformers, full name Bidirectional Encoder Representation from Transformers) neural network. Background technique [0002] Coarse-grained text sentiment mining, referred to as coarse-grained sentiment analysis. Coarse-grained sentiment analysis aims to classify the sentiment polarity of review texts. Sentiment polarity includes three categories: commendatory, derogatory and neutral. Commentary text is divided into chapter-level commentary text and sentence-level commentary text. [0003] At present, coarse-grained sentiment analysis methods mainly include methods based on rule and statistical fusion, methods based on machine learning, and methods based on deep learning. [0004] The coarse-grained sentiment analysis metho...

AI Technical Summary

Problems solved by technology

Traditional language models are mostly shallow one-way neural networks, which are difficult to deeply describe or reflect the semantic information of the text

Second, the existing coarse-grained sentiment analysis methods lack deep mining of text semantic information when generating text vector representations, and lack of optimal processing for the imbalanced problem of classified data categories

Images