Sentence level emotion classification method based on inter-sentence emotion transition probabilities
A technology of emotion transfer and classification method, applied in the field of sentence-level emotion classification based on the probability of emotion transfer between sentences, which can solve problems such as misclassification results
Active Publication Date: 2015-07-29
SUZHOU UNIV
View PDF5 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Therefore, if we only analyze the emotional characteristics of the text information itself, it may cause wrong classification results.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0025] The embodiment of the present invention discloses a sentence-level emotion classification method based on the emotion transition probability between sentences, see figure 1 As shown, the above methods include:
[0026] Step S101: Pre-classify the sentence-level texts to be tagged with emotion tags using a classifier established in advance based on the sentence-level text set with emotional tags, and obtain the sentence-level texts with pre-labeled emoti...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The application discloses a sentence level emotion classification method based on inter-sentence emotion transition probabilities. The method includes the following steps that a classifier which is created on the basis of a sentence level text set marked with emotion tags in advance is utilized to pre-classify sentence level texts to be marked with emotion tags, so that sentence level texts pre-marked with the emotion tags are obtained; inter-sentence emotion transition probabilities which are worked out on the basis of the sentence level text set marked with the emotion tags in advance is utilized to optimally classify the sentence level texts pre-marked with the emotion tags, so that an optimal classification result is obtained. In the method disclosed by the application, the final optimal classification result is obtained under the condition that both the influence of the emotional characteristics of the text information on text classification and the influence of the emotion transition probability between a previous sentence and a latter sentence on text classification are taken into consideration, and thereby the emotion classification effect of the text information is improved.
Description
technical field [0001] The invention relates to the technical fields of natural language processing and machine learning, in particular to a sentence-level emotion classification method based on the emotion transfer probability between sentences. Background technique [0002] With the rapid development of the Internet, people are more and more inclined to express their emotions on social networking sites. From a short sentence on Weibo and WeChat to long blogs, these large amounts of text information contain a lot of emotions of the author. information. [0003] At present, the research on classifying text information according to emotional labels has gradually increased, but generally it is to analyze the emotional characteristics of text information itself. Due to the subjectivity and diversity of human beings' organization and use of language, the superficial emotional characteristics of many text information are often inconsistent with the author's real emotions. There...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/30G06F17/27
CPCG06F16/353G06F16/355G06F16/95G06F40/30
Inventor 李寿山汪蓉周国栋
Owner SUZHOU UNIV