Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A tourism network comment emotion analysis and service quality evaluation method

A technology of network comments and sentiment analysis, applied in calculation models, marketing, instruments, etc., can solve the problems of poor accuracy and scalability, and achieve the effect of improving accuracy and overcoming efficiency and accuracy problems

Inactive Publication Date: 2018-12-18
成都中科大旗软件股份有限公司
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The technology of text sentiment analysis using machine learning methods mostly uses a single classification model, for example, the publication number is CN103116644A "Web topic tendency mining and decision support method" mainly uses support vector machine classification method to analyze text sentiment tendency, Limited by the preference of a single classification method, its accuracy and scalability are poor

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 tourism network comment emotion analysis and service quality evaluation method
  • A tourism network comment emotion analysis and service quality evaluation method
  • A tourism network comment emotion analysis and service quality evaluation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] Such as figure 1 A method for sentiment analysis of tourism network comments is shown, comprising the following steps:

[0049] A. Preprocessing the tourism network evaluation;

[0050] B. Construct an emotional trend training set;

[0051] C. Use the emotional trend training set to train the logistic regression model, the support vector machine model and the naive Bayesian model respectively, and output the training results of the three basic training models G m (x);

[0052] D. Establish a voter model, process the training results output in step C, and calculate the emotional tendency of the comments;

[0053] E. After processing the test travel network comment data, input it into the voter model to obtain the emotional tendency of each comment.

Embodiment 2

[0055] Based on the principles of the foregoing embodiments, this embodiment takes a detailed embodiment to describe it.

[0056] A. Use web crawlers and other methods to obtain user travel comment data, and at least store the data in terms of food, housing, transportation, travel, entertainment, and shopping.

[0057] Among them, from the existing network data, the above-mentioned data on food, housing, transportation, tourism, entertainment, and shopping can be obtained from the following websites:

[0058] Eat: Ctrip, Dianping, etc.;

[0059] Live: Mafengwo, Tuniu, eLong, Lvmama, Tongcheng, Dianping, etc.;

[0060] Line: Dianping, etc.;

[0061] Tourism: Baidu Travel, JD.com, Ctrip, Tongcheng, Qunar, Mafengwo, Lvmama, Tuniu;

[0062] Shopping: Ctrip, Dianping, etc.;

[0063] Entertainment: Dianping, etc.

[0064] The hive HQL format is used to normalize the data, and to remove spaces and duplicates. Using dynamic programming algorithm and python text processing techno...

Embodiment 3

[0107] Based on the above-mentioned embodiments, this embodiment discloses a method for evaluating the quality of travel services, including the following steps:

[0108] The emotional tendency of the tourist destination reviews to be detected and evaluated is obtained by adopting the method of the above-mentioned embodiment;

[0109] Display the obtained results.

[0110] The display method includes at least one of method P1, method P2, method P3, and method P4,

[0111] Method P1 is: calculate and display the number and percentage of positive and negative reviews in terms of food, housing, travel, travel, entertainment, and shopping;

[0112] Method P2 is: according to the aspects of food, housing, travel, tourism, entertainment, and shopping, display the number and percentage of positive and negative reviews in each aspect’s subordinate dimensions, as well as the corresponding representative review content;

[0113] Specifically, the subordinate analysis dimensions of foo...

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 a tourism network comment emotion analysis and service quality evaluation method. The emotion analysis comprises the following steps: preprocessing the tourism network evaluation; constructing the training set of emotion trend; training the logistic regression model, support vector machine model and naive Bayesian model with the set of emotion trend training, and outputtingthe training results Gm (x) of three basic training models ; establishing a voter model, dealing with the training results, calculating the emotional tendency of comments; after processing the tourism network review data to be tested, inputting the voter model to get the emotional tendency of each comment. By synthesizing various machine learning algorithm models, the three classification algorithm models of logistic regression, support vector machine and Bayesian are inegrated to overcome the efficiency and accuracy of a single algorithm model, improve the accuracy of emotional analysis of tourism reviews, help tourists choose tourism services, provide decision support for tourism authorities to evaluate and improve the quality of regional tourism services.

Description

technical field [0001] The invention relates to the technical field of computer data processing and analysis, in particular to a method for sentiment analysis and service quality evaluation of travel network comments. Background technique [0002] With the rise and development of tourism e-commerce, more and more tourists purchase travel services through the Internet, and make comments after receiving travel services, express their views on the quality of travel services, and express their emotions or feelings for travel services. It has very important reference significance for other tourists to evaluate and choose tourism services, evaluate the quality of regional tourism services, and improve the quality of tourism services. However, in the face of massive tourism review data, manual or simple statistical analysis methods are time-consuming and laborious, and it is difficult to give full play to the value of tourism reviews. How to effectively analyze the emotional tenden...

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 Applications(China)
IPC IPC(8): G06Q30/02G06Q50/14G06F17/27G06F17/30G06N99/00
CPCG06F40/216G06F40/289G06Q30/0282G06Q50/14
Inventor 周道华古鹏飞曾俊
Owner 成都中科大旗软件股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com