Deep learning sentiment analysis model based on semantic enhancement and analysis method thereof

Abstract

The invention discloses a deep learning sentiment analysis model based on semantic enhancement, and the model consists of six layers: a word embedding layer, a sentiment semantic enhancement layer, aCNN convolution sampling layer, a pooling layer, an LSTM layer, and a sentiment classification layer in sequence from the bottom to the top. The word embedding layer converts words of the sentences into low-dimension word vectors; the emotion semantic enhancement layer is used for enhancing emotion semantics of the model; the CNN convolution sampling layer is used for automatically extracting wordfeatures; the pooling layer is used for reducing the dimension of the feature vector; the LSTM layer is used for capturing a long-distance dependency relationship in the statement and memorizing long-time dependency serialized information; and the sentiment classification layer adopts Softmax to perform sentiment classification. According to the method, the LSTM layer is added, so that the emotion analysis accuracy can be improved, and meanwhile, the emotion semantic enhancement layer is added, so that the emotion semantics of the model is enhanced, and the emotion analysis effect is improved; the invention further discloses a sentiment analysis method based on the deep learning sentiment analysis model, and the accuracy of Chinese short text sentiment analysis can be improved.

Description

technical field [0001] The invention relates to the technical fields of natural language processing and deep learning, in particular to a deep learning sentiment analysis model and analysis method based on semantic enhancement. Background technique [0002] Sentiment analysis, also known as "opinion mining", is devoted to the computational study of thoughts and emotions expressed in text. It includes predicting whether the opinions expressed in the text are positive or negative. In traditional sentiment analysis methods, dictionary-based methods are limited by the coverage of the dictionary, depending on the quality of the sentiment dictionary and judgment rules, which require manual design. The design of judgment rules requires manual analysis of the syntactic structure of annotation sentences in the dataset. Therefore, the merits of these methods depend heavily on manual design and prior knowledge, and their ability to generalize is poor. Machine learning-based methods ...

AI Technical Summary

Problems solved by technology

[0004] The present invention proposes a deep learning sentiment analysis model based on semantic enhancement and its analysis method, aiming to solve the complex feature engineering and artificial engineering problems based on dictionaries and statistical machine learning methods, and at the same time, it can improve the accuracy of sentiment analysis of Chinese essays Rate

Images