Emotion reason mining method based on dependency syntax and generalized causal network

A technology that relies on syntax and causal networks, and is applied in the direction of network data retrieval, network data query, and other database retrieval, etc. It can solve problems such as error in analysis results, expansion needs to be improved, and limited scope of use, etc., to achieve the effect of improving the matching degree

Inactive Publication Date: 2020-02-11
TIANJIN UNIV
View PDF3 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But it requires emotional reasons and emotional keywords in the same sentence, which greatly limits the scope of use of this method, and the scalabi

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
  • Emotion reason mining method based on dependency syntax and generalized causal network
  • Emotion reason mining method based on dependency syntax and generalized causal network
  • Emotion reason mining method based on dependency syntax and generalized causal network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] The emotional cause mining method based on dependency syntax and generalized causal network proposed in this paper is mainly used to discover the causal relationship of texts and find out the rules of its operation. When digging for emotional causes, follow the steps described below.

[0038] figure 1 It is a flow chart of the present invention for extracting causality based on dependency syntax.

[0039] The first step: Use the existing crawler framework webmagic to crawl the news data of Tianya website as the input data of this method. The crawling method is mainly divided into three steps. First, according to the seed link, extract the target link and put it in the queue to be crawled; then parse and extract the required information from the page, where webmagic will use the Jsoup component to parse the html page; finally process Data, the extracted data is stored in file format or stored in databases and search engine index libraries, etc.

[0040] The second ste...

Embodiment 2

[0050] The emotional cause mining method based on dependency syntax and generalized causal network can not only be applied to the field of emotional cause mining, but also be applied to analyze the causes of major events. Provide guidance and suggestions for the government to control the public opinion trend of major events.

[0051] Step 1: Use the existing crawler framework webcollector to crawl the news data of Sina website. webcollector is a JAVA crawler framework (kernel) that does not require configuration and is convenient for secondary development. A powerful crawler can be implemented with only a small amount of code. First, customize the request header. In some crawling tasks, some websites have a strong anti-crawling mechanism and require login, and there may be other requests. At this time, you need to customize the request header to encapsulate the cookie information after login. The method is very simple, you can easily customize the request header by rewriting ...

Embodiment 3

[0062] The first step is to use the existing crawler framework to crawl news data as the input data of this method. The existing mainstream crawler frameworks include Heritrix, jspider, webmagic, etc., because webmagic is a Java stand-alone crawler, which meets the experimental requirements and is easy to operate, so we use the webmagic crawler framework.

[0063] The second step is to segment the input text data according to the punctuation marks. This process is mainly realized by using the existing tokenizers. The mainstream tokenizers include word tokenizers, Ansj tokenizers, and Stanford tokenizers. Because Stanford The accuracy of the tokenizer is high, so we use the Stanford tokenizer to divide each sentence into a series of words; then use Stanford's CTB to tag each word with part of speech. Finally, the semantic analysis of the sentence is performed using the Stanford parser.

[0064] The third step is to extract semantic patterns from the text according to the binar...

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 belongs to the field of natural language processing, and particularly relates to an emotion reason mining method based on dependency syntax and a generalized causal network. The emotionreason mining method mainly comprises the following steps: crawling news data and inputting data by utilizing a crawler framework; performing pretreatment; extracting a semantic mode of the text; conducting judgment; outputting the causal relationship in the statement; identifying a pair of causal relationship events; performing extraction; performing extraction; constructing a network; and performing generalized processing and evaluation. According to the emotion reason mining method, implicit meanings among words in sentences are fully interpreted; and generalized processing is carried out on the event, and the matching degree of the event is improved.

Description

technical field [0001] The invention belongs to the field of natural language processing, and specifically relates to a method for mining emotional causes based on dependency syntax and a generalized causal network. It is a method for extracting causal relationships based on dependency syntax, and then constructing a causal relationship network based on the extracted causal relationships. Web Mining of Trigger Events in Text Information that Inspire Emotion Generation and Transfer. Background technique [0002] With the rapid growth of social network platforms, more and more people tend to express their emotions on social networks, and emotion reason mining has become a new challenge in natural language processing. In recent years, the research focus of sentiment analysis is mainly on sentiment classification, but sometimes we pay more attention to the trigger events that stimulate the generation and transfer of sentiment. For example, a manufacturer wants to know the reaso...

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): G06F16/953G06F16/2458G06F40/211G06F40/289G06F40/30
Inventor 孙越恒谢英杰
Owner TIANJIN 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
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