Unlock instant, AI-driven research and patent intelligence for your innovation.

Method, device and processor for text categorization

A text classification and classifier technology, which is applied in the fields of electrical digital data processing, special data processing applications, instruments, etc., can solve the problem of low accuracy of classification results

Active Publication Date: 2013-10-09
SUZHOU UNIV
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the inventor found in the research process of this application that when using the above-mentioned method to perform emotion classification or emotion classification on the text to be classified, the accuracy of the obtained classification results is low

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method, device and processor for text categorization
  • Method, device and processor for text categorization
  • Method, device and processor for text categorization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] 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 creative efforts fall within the protection scope of the present invention.

[0071] In order to solve the problem of low classification accuracy in the prior art when performing text classification, the present application provides a text classification method to improve the text classification accuracy.

[0072] see figure 1 In the schematic diagram of the workflow shown, the text classification methods disclosed in the present application include:

[0073] Step S11. Obtain a classifier, where the classifier includes: an emotion classifie...

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

No PUM Login to View More

Abstract

The invention relates to the technical field of natural language processing and pattern recognition, and discloses a method, device and processor for text categorization. The method includes the steps of obtaining the initial probability that sentiment test samples and emotion test samples belong to various sentiment categories and various emotion categories respectively according to a classifier, then selecting the sentiment test samples and the emotion test samples to be used as common samples, obtaining the joint probability of the common samples, conducting the weighted sum on the joint probability and the initial probability, and obtaining the sentiment categories and / or the emotion categories of a text to be classified according to the sum result. In the process, the sentiment and the emotion of the text to be classified are combined so that sentiment classification and / or emotional classification to the text can be achieved. Due to the fact that the sentiment and the emotion of the same text are closely associated, and when the sentiment and the emotion of the text to be classified are combined and the text to be classified is classified, the precision of text categorization can be effectively improved.

Description

technical field [0001] The invention relates to the technical field of natural language processing and pattern recognition, in particular to a text classification method, device and processor. Background technique [0002] In human activities, people's attitudes or views on things are often affected by emotions and emotions. Among them, emotion is a kind of attitude experience produced by people on whether objective things meet their needs, including positive, intermediate or negative, etc., while emotion refers to people's inner psychological reactions and feelings, such as happiness, anger, sadness and joy, etc. . Sentiment classification helps to understand the consumption habits of users and the advantages and disadvantages of products, so as to analyze and make decisions on product reviews; it helps to understand the satisfaction and demands of the public, and to discover social hot issues in time; it helps to analyze current social hot spots Public opinion informatio...

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
no application Login to View More
IPC IPC(8): G06F17/30G06K9/62
Inventor 李寿山高伟周国栋
Owner SUZHOU UNIV