A Perspective-Level Text Sentiment Classification Method and System Based on External Knowledge

Abstract

The present invention relates to a view-level text sentiment classification method and system based on external knowledge. Synonyms are combined, and sentinel vectors are introduced to avoid misleading the model by external knowledge; the contribution degree of each word to the perspective word is judged through the position attention mechanism; by calculating the attention score of each memory content, the threshold recurrent unit is used to convert each The attention score of the layer is combined nonlinearly with the output of the previous layer, and the last layer is used as the emotional feature representation of the text; the final emotional classification result is obtained by using the classification function. The invention can improve the performance of view-level text sentiment classification and reduce resource consumption.

Description

technical field [0001] The invention relates to the fields of document sentiment analysis, opinion mining and machine learning, in particular to a perspective-level text sentiment classification method and system based on external knowledge. Background technique [0002] Perspective-level text sentiment analysis aims to study the sentiment polarity of review texts about a given perspective word, so as to provide more comprehensive, in-depth and fine-grained analysis than document-level or sentence-level sentiment analysis, which can be widely used in product pricing, Competitive intelligence, stock market forecasting and other fields provide people with convenient and automated tools to improve the utilization of Internet information. However, user emotion expressions have different performances in different perspectives. like figure 1 , there are two perspective words "size" and "space" in the text, the sentimental polarity expressed in the text is positive for the perspe...

AI Technical Summary

Problems solved by technology

The researchers proposed an adaptive recursive neural network (Adaptive Recursive Neural Network, AdaRNN) to model the adaptive propagation of emotional words to specific perspective words. doesn't work

The researchers propose to use the attention mechanism and memory network model to solve the above problems. The memory blocks are constructed through the bidirectional long-short-term memory network and combined with the location information, and then the results of multiple attention are calculated. Finally, the threshold control unit is used for nonlinear combination. Perform perspective-level text sentiment classification. Although this type of method can better handle complex sentences, it lacks consideration of the different meanings of words in different contexts.

Images