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

Social text emotional tendency analysis method and system based on heterogeneous graph

A technology of social text and emotional tendency, applied in the field of data processing, to achieve the effect of improving emotional information and performance

Pending Publication Date: 2021-09-03
ANHUI UNIVERSITY
View PDF1 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in sentiment analysis, no one has introduced heterogeneous graphs and combined with related deep learning models for sentiment analysis.

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
  • Social text emotional tendency analysis method and system based on heterogeneous graph
  • Social text emotional tendency analysis method and system based on heterogeneous graph
  • Social text emotional tendency analysis method and system based on heterogeneous graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0108] like figure 1 As shown, a heterogeneous graph-based social text sentiment analysis method includes the following steps:

[0109] S1. Determine the basic information of the information collection object, and collect, clean and emotionally label the relevant social text content;

[0110] S11. Use questionnaires to find the information collection objects we need, record the relevant basic information of the information collection objects, including age, gender and occupation, and use crawler technology to publish relevant text information on social networks if permitted. Collecting, including grabbing and saving the expression in the text, the basic information of the text will be preserved when saving, such as: text id, release time, release location, etc. Manually filter the stored data and delete useless text data, including advertising posts and controversial posts. Use computers to clean information such as urls and mailboxes in the text to ensure the availability o...

Embodiment 2

[0162] A heterogeneous graph-based social text sentiment analysis system, including:

[0163] The first module, the first module is used to determine the basic information of the information collection object, and collect, clean and emotionally label the relevant social text content;

[0164] The second module, the second module is used to construct meta-paths containing different semantic relations according to the co-occurrence information of words and expressions in social texts, by using the exchange matrix of each meta-path as an adjacency matrix, words and expressions are respectively formed Heterogeneous graph;

[0165] The 3rd module, described 3rd module is used for based on the Word2Vec dictionary of training, carries out vector embedding to the word and expression after cleaning, participle;

[0166] The fourth module, the fourth module is used to retrain the embedding vector based on the meta-path information of the constructed heterogeneous graph to obtain the fi...

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 social text emotional tendency analysis method and system based on a heterogeneous graph, belongs to the technical field of data processing, and aims to solve the technical problem of how to analyze the emotional tendency of a social text by adopting the heterogeneous graph and combining a deep learning model. The method comprises the steps: on the basis of co-occurrence information of words and expressions in a social text, constructing meta-paths and a heterogeneous graph through an exchange matrix of each meta-path, obtaining semantic representation vectors containing internal relations of the words and the expressions by using an adjacent matrix, finally analyzing the emotion semantic vectors through an attention mechanism and a BiLSTM network, and obtaining a high-precision emotional tendency label. According to the method, expressions of expressions and texts on emotions are comprehensively considered, the internal relation between the expressions and the texts is deeply mined, and the performance of emotion analysis is improved; expressions and important punctuation marks in the text are reserved in data processing, so that emotion information contained in the text content is improved; according to the method, richer semantic information can be obtained, and the sentiment analysis result is more accurate.

Description

technical field [0001] The invention belongs to the technical field of data processing, and relates to a heterogeneous graph-based social text sentiment analysis method and system. Background technique [0002] Emotion is a part of people's life. Everyone will have different emotional states at different times and when facing different things. However, emotional states can reflect changes in a person's psychological state and can affect a person's various emotions. Behavior. For more than two decades, researchers have been trying to analyze people's emotional states more precisely. [0003] With the development of social networks, people can not only communicate in real life, but also express their opinions and opinions on the Internet, the most common of which is text content. People express their thoughts and emotions through comments and posts. People's mutual communication, emotional expression and public opinion on the Internet will all affect the development of a ce...

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): G06F40/30G06F40/242G06F40/216G06F40/289G06F16/35G06F16/215G06F16/2458G06K9/62G06N3/04G06N3/08
CPCG06F40/216G06F40/242G06F40/289G06F40/30G06F16/35G06F16/215G06F16/2465G06N3/08G06N3/044G06N3/045G06F18/24
Inventor 王庆人孙亮崔杰张以文颜登程李海涛
Owner ANHUI UNIVERSITY
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