Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Sentiment classification method and device based on combined feature vector and SVM[perf] (Support Vector Machine)

A technology of combining features and sentiment classification, which is applied in the fields of text database clustering/classification, character and pattern recognition, special data processing applications, etc. Effect

Inactive Publication Date: 2016-09-28
TSINGHUA UNIV
View PDF2 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the transaction volume of an e-commerce platform can reach tens of thousands every day, resulting in a huge amount of comment information, which is also difficult for humans to process in a timely and effective manner, and it is laborious

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
  • Sentiment classification method and device based on combined feature vector and SVM[perf] (Support Vector Machine)
  • Sentiment classification method and device based on combined feature vector and SVM[perf] (Support Vector Machine)
  • Sentiment classification method and device based on combined feature vector and SVM[perf] (Support Vector Machine)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0033] The following describes the combined eigenvector and SVM-based perf The emotion classification method and device, first will describe the combined feature vector and SVM based on the combination of feature vectors and SVM perf sentiment classification method.

[0034] figure 1 Is based on the combined feature vector and SVM of the embodiment of the present invention perf Flowchart of our sentiment classification method.

[0035] Such as figure 1 As shown, this is based on combining eigenvectors and SVM perf The senti...

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 discloses a sentiment classification method and device based on a combined feature vector and a SVM[perf] (Support Vector Machine). The method comprises the following steps: obtaining a plurality of comment texts from the Internet; carrying out word segmentation on the plurality of comment texts, and dividing each sub-component word; obtaining the morphology features of a sentence; extracting the syntax features of each comment text; through a preset algorithm, combining the morphology features with the syntax features to obtain the combined feature vector of each comment text; and according to the combined feature vector of each comment text, training a SVM[perf] model so as to regulate the operation parameter of the SVM[perf] to obtain an optimal classification result. The method uses the combined feature vector with the SVM[perf] to carry out sentiment classification on the comment texts so as to obtain the optimal classification result, classification accuracy is improved, the emotional tendency of a user in the text is better identified, and the method is simple and convenient.

Description

technical field [0001] The present invention relates to the field of computer and Internet technologies, in particular to a combination feature vector and SVM perf The Chinese emotion classification method and device of the present invention. Background technique [0002] With the continuous development of the Internet and Web 2.0, e-commerce has become an important shopping channel that is indispensable in people's daily life. On the e-commerce website, buyers can comment on the purchased items and express their opinions and satisfaction, and these comments often contain emotional factors, including the buyer's attitude. By analyzing the purchase reviews posted by users, the emotions of users can be classified. All e-commerce companies are also fully aware of the important value of this part of data information, and strive to obtain more accurate and effective data to provide data support for future decision-making. However, the transaction volume of an e-commerce platfo...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/30G06K9/62
CPCG06F16/35G06F18/2411
Inventor 徐华徐嘉帅孙晓民邓俊辉
Owner TSINGHUA UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com