Dialogue sentiment analysis method based on interactive long-short-term memory network

A long-term and short-term memory and sentiment analysis technology, applied in semantic analysis, biological neural network models, instruments, etc., can solve the problem of ignoring the interaction and influence of the talker, and achieve the effect of improving efficiency, accuracy and accuracy.

Inactive Publication Date: 2021-06-04
ZHENGZHOU UNIVERSITY OF LIGHT INDUSTRY
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In addition, traditional sentiment analysis methods often treat each speaker in a dialogue in isolation, and analyze the emotional polarity of each sentence separately, ignoring the interaction and influence between the speakers

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
  • Dialogue sentiment analysis method based on interactive long-short-term memory network
  • Dialogue sentiment analysis method based on interactive long-short-term memory network
  • Dialogue sentiment analysis method based on interactive long-short-term memory network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The technical solution of the present invention will be further described in detail below in conjunction with the accompanying drawings, but the protection scope of the present invention is not limited to the following description. figure 1 It shows the flow of the dialogue sentiment analysis method based on the interactive long short-term memory network proposed by this method; figure 2 Shows the interaction flow chart between the talkers in the chat conversation; image 3 A diagram showing the internal structure of the long short-term memory network; Figure 4 An interactive LSTM network structure diagram is shown; Figure 5 The comparison results of emotion prediction experiments of different emotion recognition methods are shown. Specific steps are as follows:

[0055] (1): Collect chat dialogue data based on online chat community forums, and initially obtain dialogue data. The method is as follows:

[0056] Step 1: Formulate three principles to select chat for...

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 relates to a dialogue sentiment analysis method based on an interactive long-short-term memory network, which is characterized by comprising the following steps of: constructing a dialogue sentiment corpus set; preprocessing the dialogues in the dialogue emotion corpus set; defining interaction in the dialogue sentiment analysis scene, summarizing three characteristics including semantic comprehension, credibility and influence contained in the interaction, and adopting corresponding calculation methods for different characteristics; respectively fusing the calculated semantic vector ui, credibility cred (u) and influence R of each statement into an LSTM structure, so that the LSTM structure can model interaction between talkers in a conversation, and is called as an interactive long short-term memory network Interactivity-LSTM; and carrying out model training.

Description

technical field [0001] The invention relates to the technical field of dialogue emotion classification, in particular to a text dialogue emotion analysis method. Background technique [0002] With the rapid development of the Internet and social networks, more and more users rely on instant messaging software such as WeChat, QQ, and DingTalk, which have become the main channels for people's daily communication. The Internet records a large number of chat conversations every day. These conversations are usually With a large number of evolving subjective attitudes and emotions of the talkers, dialogue sentiment analysis is becoming a new research topic, attracting the attention of both academia and industry. Its importance has been recognized by all walks of life in society, for example, it can help product manufacturers improve their products, and help the government understand the preferences of the people. Therefore, dialogue sentiment analysis not only has important theor...

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): G06F16/332G06F16/33G06F40/30G06N3/04
CPCG06F16/3329G06F16/3344G06F40/30G06N3/044
Inventor 马军霞张亚洲陈锐楚杨阳
Owner ZHENGZHOU UNIVERSITY OF LIGHT INDUSTRY
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap