Comment emotion reason triple extraction method

A technology of triples and emotions, applied in biological neural network models, semantic analysis, marketing, etc., to achieve the effect of improving user experience

Pending Publication Date: 2021-12-10
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to overcome the defects existing in the extraction of emotional reasons in the prior art, and to improve the utilization rate and application effect of emotional reasons, a kind of end-to-end comment emotional reason triple extraction method is proposed

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
  • Comment emotion reason triple extraction method
  • Comment emotion reason triple extraction method
  • Comment emotion reason triple extraction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0064] A review sentiment reason triple extraction method, including the following steps:

[0065] Step 1: Label the sentiment-cause pairs in each document in the dataset and label the sentiment types of sentiment sentences. Use the Chinese word segmentation tool jieba for word segmentation, and separate words with spaces.

[0066] For example: the following documents:

[0067] The computer just arrived, 1

[0068] Can't wait to open it up to try it out. 2

[0069] The appearance is really amazing to me, 3

[0070] Thin and technologically advanced, 4

[0071] Prettier than the picture shows. 5

[0072] Used it for a while and overall it's good, 6

[0073] But there are some small problems when using it, 7

[0074] The fan is very loud, 8

[0075] Kind of annoying. 9

[0076] Among them, the third sentence is an emotional sentence, the emotion type is surprise, and the corresponding reason sentences are the fourth and fifth sentences. The ninth sentence is an emot...

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 comment emotion reason triple extraction method, and belongs to the technical field of emotion analysis and information extraction in natural language processing. The method integrates an emotion reason extraction technology, an emotion analysis technology and an information extraction technology, extracts an emotion sentence, a reason sentence and an emotion type triple, namely an emotion reason triple, and applies the emotion reason triple to a comment scene. According to the method, the defects that an emotion reason extraction result is low in practicability and limited in application scene are overcome, the defects that an existing emotion reason extraction method has error propagation, is complex to use, consumes time and the like are overcome, and end-to-end extraction of the emotion reason triple is achieved. According to the method, the problems of relatively coarse classification granularity, excessive information and the like of an existing comment mode are solved, and the use experience of a user can be well improved.

Description

technical field [0001] The invention relates to a method for extracting comment emotion reason triples, and belongs to the technical field of emotion analysis and information extraction in natural language processing. Background technique [0002] The development and rapid start of sentiment analysis, thanks to the rapid development of social media on the Internet, such as product reviews, forum discussions, Weibo, and WeChat, is the first time in human history that such a huge number of records has been recorded. Currently, sentiment analysis has grown into one of the most active research fields in natural language processing (NLP), with extensive research in data mining, web mining, text mining, and information retrieval. [0003] The traditional sentiment analysis technology can only get the sentiment polarity (positive, neutral, negative) of the text. However, more deep-level information (such as the cause of emotion, the object expressing emotion, etc.) still deserves ...

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 & AuthorityApplications(China)
IPC IPC(8): G06F16/35G06F40/216G06F40/30G06N3/04G06Q30/02G06Q50/00
CPCG06F16/35G06F40/216G06F40/30G06Q30/0201G06Q50/01G06N3/044
Inventor宋大为宋昊霖华玲誉
OwnerBEIJING INSTITUTE OF TECHNOLOGYGY