Comment entity-based aspect-level emotion classification method and device and model training thereof

Abstract

The invention discloses a comment entity-based aspect-level emotion classification method and device and model training thereof. The model training comprises the steps of obtaining a training text comprising comment texts, different entities associated with the comment texts, aspect information and emotion information; Converting words, entities and aspects of the training text into word vector representations; combiing and representing comments in the corresponding entities and aspects based on the first interaction layer; Endowing words at different positions with different weights based onthe second position attention layer; extracting Basic words and syntactic features based on the third-layer LSTM network and the fourth-layer linear layer; And based on a fifth attention mechanism anda sixth context memory, extracting semantic features of the whole comment under the entity and aspect. The position-based attention mechanism adopted by the invention can better mine the sentiment internal relations of different words and comments under different entities and aspects, thereby obtaining a more accurate prediction result.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, specifically to natural language processing in the field of deep learning, and in particular to the prediction of different sentiments of review texts under multi-entity and multi-faceted conditions. Background technique [0002] The core issue of text sentiment classification is how to effectively represent the emotional semantics of the text. With the rapid development of Internet technology, social networks and e-commerce platforms have produced a large number of comment texts that contain consumers’ needs and their product experience. By mining The sentiment behind reviews can help companies improve their products, and sentiment analysis has become one of the important topics in the field of natural language processing. [0003] Sentiment analysis is divided into the extraction of emotional information, the classification of emotional information, and the retrieval and induction...

AI Technical Summary

Problems solved by technology

[0003] Sentiment analysis is divided into the extraction of emotional information, the classification of emotional information, and the retrieval and induction of emotional information. Most of the current methods regard sentiment classification as a kind of text classification problem, and most text sentiment classification models based on neural networks only consider It ignores the emotional semantics related to the text content, but ignores the emotional information of different aspects of the comment subject on different entities. It is difficult to achieve accurate classification of emotions by combining entities and aspects, and it is also difficult to meet the needs of enterprises. Therefore, the existing technology still lacks A Fine-Grained Sentiment Classification Model Combining Entities and Aspects

Images