A method for judging relevance of app software user comments

A user review and software technology, applied in special data processing applications, unstructured text data retrieval, semantic tool creation, etc., can solve problems such as false introduction of APP, and achieve the effect of reducing time and improving efficiency

Active Publication Date: 2019-07-16
KUNMING UNIV OF SCI & TECH
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, for APP evaluation, basically only the enterprise itself conducts the evaluation, and there may be false introductions to the APP, etc.

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 for judging relevance of app software user comments
  • A method for judging relevance of app software user comments
  • A method for judging relevance of app software user comments

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] Embodiment 1: as Figure 1-5 As shown, APP software user comments are shown in Table 1,

[0039] Table 1

[0040]

[0041] The specific steps of the method for judging the relevance of the APP software user comments are as follows:

[0042] Step1. Extract num user comments of the APP software, and the comment segmentation result set WordResult of each user comment i ={w 0 / f 0 ,w 1 / f 1 ,...,w j / f j}, comment part-of-speech set Feature i ={f 0 , f 1 ,... f j}, where w j for words, f j For part of speech (i=0,1,...,num-1, j=0,1,...,n-1):

[0043]The present invention uses ICTCLAS 2015 as a tool for data processing to perform word segmentation and part-of-speech tagging of user comments. In this embodiment, the word segmentation result for user comment information is: "unintentional / vzhong / f. / wj", and the word segmentation result set is extracted: WordResult 0 ={unintentional / v, medium / f,. / wj}, extract the comment part of speech set: Feature 0 ={v, ...

Embodiment 2

[0065] Embodiment 2: as Figure 1-5 as shown,

[0066] APP software user comments are shown in Table 2,

[0067] Table 2

[0068]

[0069] The specific steps of the method for judging the relevance of the APP software user comments are as follows:

[0070] Step1. Extract num user comments of the APP software, and the comment segmentation result set WordResult of each user comment i ={w 0 / f 0 ,w 1 / f 1 ,...,w j / f j}, comment part-of-speech set Feature i ={f 0 , f 1 ,... f j}, where w j for words, f j For part of speech (i=0,1,...,num-1, j=0,1,...,n-1):

[0071] In this embodiment, WordResult 0 ={hahaha / o}, extract comment part of speech set: Feature 0 ={o}, at this time num=1.

[0072] Step2. According to the WordResult and Feature of num user comments, extract the keyword set Keywords of each comment i : In this embodiment, Keywords 0 ={};

[0073] Step3, define the number of each iteration index (index must meet no greater than num), the total number...

Embodiment 3

[0084] Embodiment 3: as Figure 1-5 as shown,

[0085] APP software user comments are shown in Table 3,

[0086] table 3

[0087]

[0088] The specific steps of the method for judging the relevance of the APP software user comments are as follows:

[0089]Step1. Extract num user comments of the APP software, and the comment segmentation result set WordResult of each user comment i ={w 0 / f 0 ,w 1 / f 1 ,...,w j / f j}, comment part-of-speech set Feature i ={f 0 , f 1 ,... f j}, where w j for words, f j For part of speech (i=0,1,...,num-1, j=0,1,...,n-1):

[0090] In this embodiment, WordResult 0 ={true / d, good / a, use / v}, extract comment part of speech set: Feature 0 ={d, a, v}, at this time num=1.

[0091] Step2. According to the WordResult and Feature of num user comments, extract the keyword set Keywords of each comment i :

[0092] Extract Keywords i Method: find Feature i Subscript all the elements of the verb, noun and adjective parts of speech, and...

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 method for judging correlativity of user comments of APP software, and belongs to the field of user evaluation of APP software. The method comprises the steps of firstly extracting a keyword set of each comment of the APP software; secondly calculating a correlativity probability score of the extracted keyword set of each comment of the APP software to a characteristic library; and finally determining whether the user comment of the APP software is related to the APP software or not by judging whether the correlativity probability score is greater than a preset threshold or not. According to the method, the keyword set of the user comment of the APP software is defined and extracted, so that the efficiency of judging the correlativity of the user comment can be improved; the correlativity probability score of the user comment of the APP software is judged in combination with a word frequency statistics method by modifying a naive Bayes text classification method, so that related comments can be screened out for a user and the comment screening time can be shortened; and by judging the correlativity of the user comment of the APP software, the user can conveniently evaluate the quality of the APP software.

Description

technical field [0001] The invention relates to a method for judging the relevance of APP software user comments, belonging to the field of APP software user evaluation. Background technique [0002] The information analysis of user comments in the fields of e-commerce and Weibo is becoming more and more mature. Most studies on Chinese comments use ICTCLAS for information processing, and finally use natural language processing to analyze the processed user comment information. For example, Yang Zhen et al. proposed a research on short text sentiment polarity discrimination based on context reconstruction; Song You et al. proposed a method for network general text processing based on regular expressions. [0003] The user's choice of application is basically based on the company's publicity and the popularity of the application itself. However, for certain applications of the same type or with similar functions, users are more willing to compare users' evaluations and descr...

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): G06F16/35G06F16/36
CPCG06F16/35G06F16/36
Inventor 姜瑛向祺鑫冉猛李凌宇丁家满汪海涛刘英莉
Owner KUNMING UNIV OF SCI & TECH
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