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

Domain-adaptive opinion data classification method and device

A data classification and adaptive technology, applied in the Internet field, can solve the problem of inaccurate classification results, and achieve the effect of ensuring accuracy and reducing differences

Active Publication Date: 2020-04-24
HUAZHONG NORMAL UNIV +1
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] When related technologies implement domain-adaptive opinion data classification, since all the words involved in the selected source domain and target domain may not be clearly divided into domain-specific words or domain-independent words, the domain The classification result of adaptive opinion data to classify opinion data is not accurate

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
  • Domain-adaptive opinion data classification method and device
  • Domain-adaptive opinion data classification method and device
  • Domain-adaptive opinion data classification method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] In order to make the object, technical solution and advantages of the present invention clearer, the implementation manner of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0035] With the rapid development of Internet technology, more and more opinion data that can identify users' emotions are shared on the Internet. For example, when a user makes a successful online purchase, he will post comments on the purchased product in the comments; when a user publishes a blog, other users will comment on the content published by the user, etc. Among them, the opinion data may be derogatory or commendatory; it may be subjective or objective. That is to say, opinion data has a certain emotional polarity, and the emotional polarity of opinion data includes positive and negative, etc. The process of studying the emotional polarity of opinion data is the process of classifying opinion data. It is of great significan...

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 an adaptive field viewpoint data classification method, and belongs to the technical field of internets. The classification method includes the steps: determining a source field search word matrix and a target field search word matrix; determining a source field objective function and a target field objective function; determining a total objective function according to the source field objective function and the target field objective function; respectively determining target values of various parameters in the total objective function; training designated classification models according to the target values of various parameters and marked viewpoint data in a source field, and performing classification for viewpoint data in a target field by the designated classification models obtained in a training manner. The total objective function is connected with a special source field topic matrix, a special target field topic matrix and a hub matrix expressing sharing topics between the source field and the target field, so that the adaptive field viewpoint data classification method is achieved by the sharing topics, and differences between the source field and the target field can be decreased by the sharing topics, so that accuracy of classification results can be ensured.

Description

technical field [0001] The present invention relates to the technical field of the Internet, in particular to a field-adaptive opinion data classification method and device. Background technique [0002] With the development of Internet technology, users share more and more opinion data on the Internet. For example, user reviews posted by users on shopping websites, user feedback on a product, etc. are opinion data. Among them, the opinion data shared by users will involve multiple fields, such as the clothing field and the book field. In order to facilitate the research or statistics of opinion data in various fields, it is usually necessary to classify the opinion data in various fields. Usually, when classifying opinion data in a certain field, it is necessary to label the opinion data in this field first, and then train a classifier based on the marked opinion data. However, since the opinion data in the Internet involves many fields, labeling the opinion data in each...

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 Patents(China)
IPC IPC(8): G06F16/35
CPCG06F16/35
Inventor 周光有张小鹏肖磊刘婷婷王巨宏
Owner HUAZHONG NORMAL UNIV