Cross-domain emotion classification system based on attention mechanism fusion

Abstract

The invention relates to a cross-domain emotion classification system based on attention mechanism fusion. The system comprises a comment text preprocessing module used for obtaining vector forms of texts in a source domain and a target domain; a text semantic learning module which is used for learning a semantic dependency relationship between words; an attention mechanism fusion module which isused for fusing different attention modes to obtain comprehensive weights of words for text classification; a hierarchical attention module which is used for calculating attention weights of the textfrom a word level and a sentence level respectively and judging weights of words for sentence representation and sentences for document representation; and an emotion category output module which is used for obtaining a final emotion classification result by utilizing the classification function. According to the method, the potential universal features of the target domain and the source domain can be automatically extracted, the features are abstracted and combined, and finally the emotion category of the text of the target domain is recognized.

Description

technical field

[0001] The present invention relates to the field of emotion analysis and opinion mining, and more specifically, to a cross-domain emotion classification system based on attention mechanism fusion, which can learn domain-adapted feature representations through cross-domain text representation learning, and better perform cross-domain Analysis of Domain Sentiment Categories. Background technique

[0002] Sentiment classification is an important and challenging task. Remarkable success has been achieved in domains with sufficient labeled training data. However, labeling enough data is very time-consuming and labor-intensive, setting a significant barrier for adapting sentiment classification systems to new domains. At the same time, when users express emotions in different domains, they often use different words, if we directly apply a classifier trained in one domain to other domains, due to the differences between these domains, the resulting performance wi...

Images