Unlock instant, AI-driven research and patent intelligence for your innovation.

Text sentiment analysis method, device, electronic equipment and storage medium

A sentiment analysis and text technology, applied in the Internet field, can solve the problem of low accuracy of sentiment analysis results

Active Publication Date: 2020-11-13
BEIJING SANKUAI ONLINE TECH CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The above methods all take the overall comment text as the analysis target, and conduct overall analysis on the comment text, resulting in low accuracy of sentiment analysis results

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 sentiment analysis method, device, electronic equipment and storage medium
  • Text sentiment analysis method, device, electronic equipment and storage medium
  • Text sentiment analysis method, device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] A text sentiment analysis method disclosed in this embodiment, such as figure 1 As shown, the method includes: step 110 to step 140.

[0059] Step 110, according to the character in the clause sequence obtained by segmenting the target text and the context information of the character in the target text, determine the character vector corresponding to the character.

[0060] Wherein, the target text is a user's comment text on a product, which may include one or more complete sentences.

[0061] Obtain the clause sequence obtained by segmenting the target text, perform character granularity semantic extraction on each character in the clause sequence, and combine the context information of the character in the target text to obtain the character vector corresponding to each character . Wherein, the step of segmenting the target text can be implemented before this step by the text sentiment analysis device implementing the text sentiment analysis method, and can also b...

Embodiment 2

[0091] A text sentiment analysis device disclosed in this embodiment, such as image 3 As shown, the sentiment analysis device 300 of the text includes:

[0092] The character granularity semantic extraction module 310 is used to determine the character vector corresponding to the character according to the character in the clause sequence obtained by segmenting the target text and the context information of the character in the target text;

[0093] The clause granularity semantic extraction module 320 is used to determine the clause vector corresponding to the clause according to the character vector corresponding to the character in the same clause and the context information of the clause in the target text;

[0094] The vector fusion module 330 is used to fuse the clause vectors corresponding to the clauses, the user feature vectors and the product feature vectors into the clause overall vectors corresponding to the clauses, wherein the user feature vectors are The user ...

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 embodiment of the present application discloses a text sentiment analysis method, device, electronic equipment, and storage medium. The method includes: according to the characters and the context information of the characters in the clause sequence obtained by segmenting the target text, determine the character corresponding to the character Character vector; determine the clause vector corresponding to the clause according to the character vector corresponding to the character in the same clause and the context information of the clause; user features obtained by encoding the clause vector corresponding to the clause and the user information corresponding to the target text The vector and the product feature vector obtained by encoding the product information corresponding to the target text are fused into the clause overall vector corresponding to the clause; the context sequence labeling process is performed on the clause overall vector corresponding to each clause, and the emotion corresponding to each clause is obtained polarity. The embodiment of the present application considers the context information, user information and product information at the same time to identify the emotion polarity, which improves the accuracy of the emotion analysis result.

Description

technical field [0001] The present application relates to the technical field of the Internet, in particular to a text sentiment analysis method, device, electronic equipment and storage medium. Background technique [0002] Sentiment analysis for user evaluation is one of the important ways for e-commerce platforms to obtain user feedback. Through the analysis of emotional polarity (good, bad or neutral), we can know the user's experience of the product, and then make targeted improvements or recommend corresponding products to users. [0003] In the prior art, the methods for sentiment analysis of user evaluation mainly include: 1) analysis through dictionaries: by constructing sentiment dictionaries, extracting the sentiment words in the target comment text, and judging the target comment text according to the number and weight of sentiment words 2) Analysis by combining artificial features with a classifier: map the target comments into artificial features, and then inp...

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 Patents(China)
IPC IPC(8): G06F40/211G06F40/289G06F40/30G06N3/04G06N3/08
CPCG06N3/08G06N3/044G06N3/045
Inventor 雷家欢张庆罗恒亮
Owner BEIJING SANKUAI ONLINE TECH CO LTD