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

Chinese interactive text emotion and topic recognition method based on multi-task learning

A multi-task learning and topic recognition technology, applied in the field of Chinese interactive text emotion and topic recognition based on multi-task learning, which can solve problems such as single

Active Publication Date: 2018-02-06
XI AN JIAOTONG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, patents related to the project, such as "A method for online detection of microblog hot events based on sentiment analysis" (CN201310403005.4) have been authorized, which extracts sentiment from online microblog texts through sentiment analysis, and then realizes online real-time detection The purpose of publishing hot events on Weibo, but this patent does not combine the characteristics of e-Learning interactive text, which is relatively simple

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
  • Chinese interactive text emotion and topic recognition method based on multi-task learning
  • Chinese interactive text emotion and topic recognition method based on multi-task learning
  • Chinese interactive text emotion and topic recognition method based on multi-task learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] Embodiments of the present invention are described in further detail below in conjunction with the accompanying drawings:

[0067] Chinese Interactive Text Sentiment and Topic Recognition Framework Based on Multi-task Learning

[0068] refer to figure 1 As shown, for the supervised learning method, the Chinese interactive text emotion and topic recognition framework based on multi-task learning of the present invention includes the following four parts:

[0069] 1) According to the needs of different tasks, manually label the categories of training samples. It is necessary to label the emotion category of the dataset used for emotion classification, and label the topic category of the dataset used for topic classification;

[0070] 2) According to the different purposes of different tasks, feature extraction is performed on the data set of each task;

[0071] 3) Construct a multi-task learning model using datasets labeled with emotion and topic categories;

[0072] 4...

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 Chinese interactive text emotion and topic recognition method based on multi-task learning: in the feature extraction stage of the Chinese interactive text, the invention combines the interactive characteristics of the Chinese interactive text to extract the tendency features of the interactive text; in the emotion and topic In the identification stage, the present invention adopts a context-based multi-task classification model construction method to construct a multi-task classification model for training samples of interactive texts; the lack of tendency feature data for new users or inactive users in the e-Learning system leads to poor classification results For the problem, the present invention adopts the method of combining random walk and multi-task learning to identify new user or inactive user emotion and topic categories.

Description

technical field [0001] The invention relates to a method for recognizing emotion and topic of Chinese interactive text, in particular to a method for recognizing emotion and topic of Chinese interactive text based on multi-task learning. Background technique [0002] With the rapid development of Internet technology, E-Learning is quickly accepted by people with its advantages of "resource sharing" and "anytime, anywhere", but it also has its own shortcomings. Separation, lack of emotional communication and feedback, teachers cannot grasp students' learning dynamics in real time, and it is difficult to give comprehensive and comprehensive learning evaluations to students. In the e-Learning system, how to discover learners' emotions, adjust learners' negative emotions, and identify topics that learners are interested in has become a current research hotspot. [0003] At present, there are many methods for emotion and topic recognition of text, but compared with traditional t...

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): G06F17/27
Inventor 刘均包洪英张玲玲杨宽
Owner XI AN JIAOTONG 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