A Method of Event Sentiment Classification Based on Text Similarity

A text similarity and sentiment classification technology, applied in text database clustering/classification, text database query, unstructured text data retrieval and other directions, can solve the problems of heavy monitoring workload, difficult text monitoring, etc. Effects of parameters

Active Publication Date: 2022-03-25
CHENGDU REMARK TECH CO LTD +1
View PDF16 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the face of massive data, it is difficult to ensure that all hotspots are monitored manually, and the monitoring workload is heavy during manual monitoring, and it is difficult to monitor a certain part of the text alone

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
  • A Method of Event Sentiment Classification Based on Text Similarity
  • A Method of Event Sentiment Classification Based on Text Similarity
  • A Method of Event Sentiment Classification Based on Text Similarity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] A text similarity-based event sentiment classification method, comprising the following steps,

[0048] S001, use the text similarity clustering algorithm to cluster the text set into event A, and analyze all the texts in event A, that is, θ is 100%; here, the value of θ can also be other values, mainly for the analysis of text to determine;

[0049] There are three records in event A, which are:

[0050] R1: The dream of national rejuvenation of Chinese sons and daughters vol1: 10000;

[0051] R2: The Great Revival of Chinese Famous Clan vol2: 2000;

[0052] R3: As Chinese sons and daughters with dreams, we will move forward without hesitation vol3: 1000;

[0053] S002, using the trained vector model M to generate respective 300-dimensional vectors v1, V2, V3 of the text in the event A,

[0054]v1=M(r1)=[0.11,0.04,-0.12,…,-0.11,-0.03]

[0055] v2=M(r2)=[-0.05,-0.18,-0.15,…,-0.05,0.21]

[0056] v3=M(r3)=[-0.18,0.22,-0.18,…,-0.08,0.02]

[0057] S003, according to ...

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 an event emotion classification method based on text similarity, comprising the following steps: S000, setting the emotion value of the entire event to be processed as S; S001, selecting and generating a single text emotion classification model; S002, according to the cosine similarity Clustering the text; S003, setting the segmentation parameters of the event; S004, for each event class event, selecting text judgment and analysis according to the volume value classification; S005, performing mean calculation on all text vectors in the event class to generate the mean value of the class Vector, input the mean value vector into the application model model, and output the mean value vector emotion value p_avg; S006, calculate the emotion value of the text with emotional tendency inside the event; S007, use the emotion classification model to calculate the event emotion value; S008, judge Event sentiment classification. The technical solution can monitor and analyze a large number of texts, reduce manual parameters, and quickly determine the emotional classification of events, so as to achieve the purpose of monitoring public opinion.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to an event emotion classification method based on text similarity. Background technique [0002] With the increasing popularity of computers and the rapid development of the Internet, the Internet has become the main way for users in many fields to express and give feedback on personal opinions and comments. These shared comment information not only provides users with a platform for product experience exchange, but also serves as a reference for other users before using the product. However, the amount of these comments in the network is very large. If each comment is manually read and analyzed, it will waste a lot of time for users. Therefore, how to allow users to objectively understand the overall evaluation status reflected by the review information of a product in a short period of time, that is, to perform sentiment analysis and classification on the rev...

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): G06F16/33G06F16/35
Inventor 辛如意
Owner CHENGDU REMARK TECH CO LTD
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