News comment webpage-based emotion tendency analysis system

A technology of emotional tendency and analysis system, applied in the field of data mining system to achieve the effect of improving accuracy

Inactive Publication Date: 2009-12-02
PEKING UNIV
View PDF0 Cites 40 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This makes it impossible to analyze the emotional te

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
  • News comment webpage-based emotion tendency analysis system
  • News comment webpage-based emotion tendency analysis system
  • News comment webpage-based emotion tendency analysis system

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0033] Example 1. Direct sentiment analysis on reference entities

[0034] i) Use the existing entity extraction tool to obtain the intermediate entity "Ministry of Health" from the news comment webpage to be tested.

[0035] ii) Using sentence-level sentiment analysis tools trained by users, analyze the sentiment characteristics of "Ministry of Health" and obtain the sentiment analysis data of the intermediate entity.

[0036] iii) Locate the intermediate entity in the entity-emotion relationship graph. Since "Ministry of Health" exists in the entity-emotion relationship graph and is in the same emotion relationship tree as "Chinese government", this factor is considered in sentiment analysis.

[0037] iv) If the intermediate entity "Ministry of Health" is included in the emotional relationship tree of the reference entity "Chinese Government", then directly output the sentiment analysis data for the reference entity "Chinese Government", that is, the emotional characteristic...

example 2

[0038] Example 2. Indirect Sentiment Analysis on Reference Entities

[0039] I) Using the existing entity extraction tool, the intermediate entity "United States" is obtained from the news comment webpage to be tested.

[0040] II) Using sentence-level sentiment analysis tools trained by users to analyze the sentiment characteristics of "United States", and obtain the sentiment analysis data of the intermediate entity.

[0041] III) Locate the intermediate entity in the entity-sentiment relationship graph. Since "United States" is in the entity-sentiment relationship graph but not included in the emotion relationship tree where the reference entity is located, it is necessary to match the news comment sentence of "United States" with the same emotion A subset of the news comment webpages of the topic is used for similarity determination.

[0042] IV) Since "United States" is in another emotional hierarchy tree, it is found that the current news is matched with the existing em...

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 news comment webpage-based emotion tendency analysis system, which is characterized by comprising a user input model, an entity extraction and hierarchical relationship discovery module, a peer entity extraction layer, an entity feature extraction module, an entity positioning module and an emotion output module, wherein the user input module comprises a news comment webpage collection input by a user and emotion analysis rules comprising reference entities and emotive verbs; the entity extraction and hierarchical relationship discovery module is used for extracting effective entities from news comment webpages and establishing entity hierarchical relationship graph; and the peer entity extraction module positions the reference entities in the entity hierarchical relationship graph and establishes an entity emotion relationship graph consisting of an emotion relationship tree; the entity feature extraction module is used for acquiring intermediate entities in the news comment webpages and outputs emotion analysis data of the intermediate entities; and the entity positioning module judges whether the intermediate entities exist in the entity emotion relationship graph and the emotion relationship tree.

Description

technical field [0001] The invention relates to a data mining system, in particular to an entity emotion tendency analysis system based on a news review webpage. Background technique [0002] Sentimental orientation analysis is to analyze and mine news material information to obtain the emotional orientation of public opinion on certain products, enterprises, policies and other entities. In this way, we can better grasp the public's emotional tendency towards hot issues such as government policies and enterprise dynamics, and provide scientific basis for the strategic decision-making direction of the government and enterprises. Existing product sentiment analysis systems mainly focus on the sentiment analysis of product evaluation at paragraph granularity or sentence granularity. This type of system mainly extracts the emotional features in news materials, and uses classification or statistical methods to realize sentiment analysis. This method is relatively suitable for th...

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): G06F17/30
Inventor 高军王腾蛟杨冬青陶富民常雷
Owner PEKING 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