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

Association rule-based multi-tag Chinese emotion classification method

A sentiment classification and multi-label technology, which is applied in text database clustering/classification, semantic analysis, unstructured text data retrieval, etc., can solve problems such as poor classification effect of multi-label learning algorithms, and achieve the effect of improving mining performance

Active Publication Date: 2017-08-25
NANJING UNIV OF SCI & TECH
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Therefore, the existing multi-label learning algorithms rarely apply association rules to multi-label classification, resulting in poor classification results of multi-label learning algorithms.

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
  • Association rule-based multi-tag Chinese emotion classification method
  • Association rule-based multi-tag Chinese emotion classification method
  • Association rule-based multi-tag Chinese emotion classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] combine figure 1 , a multi-label Chinese sentiment classification method based on association rules, including the following steps:

[0017] Step 1, using the association rule algorithm to find frequent itemsets between various Chinese emotional markers;

[0018] Step 2, derive association rules between emotion tags according to frequent itemsets;

[0019] Step 3, modify the multi-label data set using association rules to obtain new data;

[0020] Step 4, use the Rank-SVM algorithm to classify the obtained new data set and learn to obtain a new model;

[0021] Step 5, use the new model to make predictions on the test dataset.

[0022] In step 1, the specific process of using the association rule algorithm to find frequent itemsets between various Chinese sentiment tags is as follows:

[0023] Step S100, set the Chinese sentiment tag set [y 1 ,y 2 ,...,y n ], the sentiment label set l corresponding to the ith example in the dataset i , generate a row vector v=[v ...

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 provides an association rule-based multi-tag Chinese emotion classification method. The method comprises the following steps of: 1, searching a frequent item set among various Chinese emotion tags by utilizing an association rule algorithm; 2, deducing an association rule among the emotion tags according to the frequent item set; 3, modifying a multi-tag data set by using the association rule so as to obtain a new data set; 4, carrying out classified learning on the obtained new data set by using a Rank-SVM algorithm so as to obtain a new model; and 5, predicting a test data set by using the new model.

Description

technical field [0001] The invention relates to a tag classification technology, in particular to a multi-tag Chinese sentiment classification method based on association rules. Background technique [0002] In traditional supervised learning frameworks, each example corresponds to only one class label, and such problems are called single-label learning problems. However, in many real-world settings, an example may not only have a single tag at the same time, but multiple category tags at the same time. For example, in medical diagnosis, a patient may have both diabetes and cancer; in gene function classification, each gene may be associated with a series of functions, such as metabolism, transcription, and protein synthesis; in scene classification, each gene A scene may belong to several semantic categories, such as beach and city. Each of the above examples corresponds to a set of labels, and the size of the label set is uncertain, such problems are called multi-label l...

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): G06F17/27G06F17/30G06K9/62
CPCG06F16/35G06F40/30G06F18/2411
Inventor 贾修一刘军煜
Owner NANJING UNIV OF SCI & TECH
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