Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Text topic and emotion joint detection method and device

A joint detection and topic technology, applied in the field of machine learning, can solve the problem of low joint detection accuracy and achieve the effect of improving accuracy

Inactive Publication Date: 2017-01-11
SHENZHEN UNIV
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method and device for joint detection of text topic and emotion, aiming to solve the problem of low accuracy in the joint detection of text emotion and topic in the prior art

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
  • Text topic and emotion joint detection method and device
  • Text topic and emotion joint detection method and device
  • Text topic and emotion joint detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0022] figure 1 It shows the implementation flow of the text topic and emotion joint detection method provided by the first embodiment of the present invention. For the convenience of explanation, only the parts related to the embodiment of the present invention are shown, and the details are as follows:

[0023] In step S101, the initial sentiment tendency of each word in the input target text is calculated using a preset sentiment dictionary.

[0024] In the embodiment of the present invention, after receiving the text topic and emotion acquisition request sent by the user, the preset emotion dictionary is used to calculate the initial emotion tendency of each word in the input target text. The target text can be a public traditional topic detection data sample, or it can be a data document such as Weibo, blog, forum, and online comment data from the Internet. Of course, after these documents are acquired, preprocessing should be performed on these documents, for example, w...

Embodiment 2

[0040] figure 2 The structure of the text topic and emotion joint detection device provided by Embodiment 2 of the present invention is shown. For the convenience of description, only the parts related to the embodiment of the present invention are shown, including:

[0041] Emotional tendency calculation unit 21, used to calculate the initial emotional tendency of each word in the input target text using a preset sentiment dictionary;

[0042] The word vector setting unit 22 is used to set the word vector of the pre-acquired external corpus as the initial value of the word vector of the target text;

[0043] The text training unit 23 is used to train the input target text using a preset topic-emotion mixed model, so as to obtain the initial distribution between each emotion topic pair and words in the target text; and

[0044] Topic emotion acquisition unit 24, for scanning each document included in the target text according to the initial emotional tendency of each word in...

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 is applicable to the technical field of machine learning and providesa text topic and emotion joint detection method and device. The method comprises the following steps of: computing an initial emotional tendency of each word in an input target text by using a preset emotion dictionary, setting word vectors of pre-acquired external corpora as initial values of word vectors of the target text, training the input target text by using a preset topic and emotion mixed model to obtain initial distribution between each emotion-topic pair and each word in the target text, scanning each document in the target text according to the initial emotional tendency of each word in the target text, the initial values of the word vectors and the initial distribution between each emotion-topic pair and each word, executing a preset topic and emotion detection step to each scanned training target word to obtain the topic and emotion involved in the target text. Thereby, the accuracy of the obtained topics and emotions of the target text is improved.

Description

technical field [0001] The invention belongs to the technical field of machine learning, and in particular relates to a joint detection method and device for text topics and emotions. Background technique [0002] The main goal of the joint topic-emotion mixed model is to analyze and process a large number of text collections, summarize and deduce the hidden semantic structure and emotional tendency of the text, so as to identify the topics discussed and emotional tendency. In recent years, with the rapid popularization and development of the mobile Internet, a large number of emerging social media such as Weibo, blogs, forums, and WeChat have emerged, making it more and more convenient for users to express opinions and share comments on personal computers and mobile terminals. Therefore, More and more users of different age groups are actively participating in physical reviews of products, services, news, etc. In the face of massive data, how to effectively organize, colla...

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): G06F17/27
CPCG06F40/30
Inventor 傅向华武海瑛
Owner SHENZHEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
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