CN112446644A - Method and device for improving quality of network questionnaire - Google Patents
Method and device for improving quality of network questionnaire Download PDFInfo
- Publication number
- CN112446644A CN112446644A CN202011458128.4A CN202011458128A CN112446644A CN 112446644 A CN112446644 A CN 112446644A CN 202011458128 A CN202011458128 A CN 202011458128A CN 112446644 A CN112446644 A CN 112446644A
- Authority
- CN
- China
- Prior art keywords
- questionnaire
- questionnaires
- analysis
- network
- quality
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for improving the quality of a network questionnaire, which comprises the following steps: designing a questionnaire, designing the questionnaire and adding test questions into the questionnaire; collecting questionnaires, publishing the questionnaires on the network and recovering the answered questionnaires, and guiding the questionnaires to be diffused to a target group by setting a threshold value of a diffusion parameter; and (4) questionnaire analysis, namely, rejecting abnormal questionnaires in the recovered questionnaires by using a clustering algorithm, and analyzing the remaining questionnaires. According to the invention, the quality control of the network questionnaire is performed through the whole process of questionnaire design, issue, collection and final data cleaning analysis, so that problem questionnaires can be effectively screened out and diffused to a target group, and real-time monitoring and dynamic monitoring of the questionnaire are realized. And the factor analysis and the clustering algorithm are combined, so that abnormal values are effectively identified, the data quality of the network questionnaire is improved, and a good data guarantee is provided for later-stage sample analysis.
Description
Technical Field
The invention relates to the technical field of questionnaire survey, in particular to a method for improving the quality of a network questionnaire.
Background
Most questionnaire survey systems on the market at present have good integration, expansion capability and business logic change capability, can realize the logic jump function in the questionnaire according to the interaction information of the user, also have the corresponding sample screening function, and create good conditions for improving the data quality of the questionnaire. As in the most widely used web questionnaire platforms at present, the questionnaire quality control measures provided by the various platforms are as follows:
TABLE 1
As can be seen from table 1 and the use examples given by the official websites, the current network questionnaire system relies more on the questionnaire recovery mechanism to perform quality control on the questionnaire, and the question settings in the questionnaire serve more on the content of the questionnaire, and the related functions thereof are not completely suitable for questionnaire quality control in specific use, and have a certain improvement space. The network questionnaire is different from the offline questionnaire, and under some special situations, users cannot be specified and limited to answer questions, and questionnaire publishers cannot see the propagation path of the questionnaire and the quality of the questionnaire in different paths. Meanwhile, for professional questionnaires, due to the fact that questionnaires are filled in for a long time, quality screening means in a common questionnaire system already have certain screening prevention capacity, while a conventional questionnaire response-gratuitous mechanism can generate a corresponding 'wool' -problem, the quality of the questionnaires is further reduced, an effective method is needed for identifying invalid samples, and the analysis quality is ensured.
Disclosure of Invention
Therefore, it is necessary to provide a method for improving the quality of a web questionnaire, which is used to solve the technical problem that the quality of the web questionnaire cannot be controlled in the prior art.
In order to achieve the above object, the present invention provides a method for improving the quality of a web questionnaire, comprising the following steps:
designing a questionnaire, designing the questionnaire and adding test questions into the questionnaire, wherein the test questions are used for screening out the questionnaire which does not meet the standard in response;
collecting questionnaires, issuing the questionnaires on the network and recovering the answered questionnaires, and guiding the questionnaires to be diffused to a target group by setting a threshold value of diffusion parameters, wherein the diffusion parameters comprise any one or more of IP (Internet protocol) of the questionnaires, response time and answer rules;
and (4) questionnaire analysis, namely, rejecting abnormal questionnaires in the recovered questionnaires by using a clustering algorithm, and analyzing the remaining questionnaires.
Further, the test questions include single test questions and combined test questions, the single test questions can judge whether the user answers the questionnaire seriously by using one test question alone, and the combined test questions judge whether the user answers the questionnaire seriously by more than two associated test questions.
Further, after the abnormal questionnaires in the recovered questionnaires are removed by using the clustering algorithm, the method further comprises the following steps:
performing factor analysis on the removed questionnaire to obtain a factor score;
performing clustering analysis by using the factor score instead of the original questionnaire;
and obtaining the questionnaire clustering classification and abnormal points through the clustering analysis.
(abnormal value elimination method of factor analysis and Cluster analysis)
Further, in the clustering analysis by using the factor score instead of the original questionnaire, the adopted clustering analysis includes any one of Kmeans clustering, AP clustering and DBSCAN.
Further, when the questionnaire is issued on the network and the answered questionnaire is recovered, the method further comprises the following steps: adding parameters to the sharing link of the questionnaire to record the propagation path of the questionnaire;
and according to the propagation path, whether the questionnaire is spread to a target group or not can be checked and monitored in real time.
Furthermore, a network node graph is adopted to show the propagation path of the questionnaire.
In order to solve the technical problem, the invention also provides another technical scheme:
an apparatus for improving the quality of a web questionnaire, comprising:
the questionnaire design module is used for designing questionnaires and adding test questions into the questionnaires, and the test questions are used for screening out the questionnaires with unqualified answers;
the questionnaire collecting module is used for issuing the questionnaire on the network and recovering the answered questionnaire, and guiding the questionnaire to be diffused to a target group by setting a threshold value of diffusion parameters, wherein the diffusion parameters comprise any one or more of IP (Internet protocol) of the questionnaire, response time and answer rules; and
and the questionnaire analysis module is used for eliminating abnormal questionnaires in the recovered questionnaires by using a clustering algorithm and analyzing the residual questionnaires.
Further, the questionnaire analysis module is also used for performing factor analysis on the removed questionnaire to obtain a factor score; performing clustering analysis by using the factor score instead of the original questionnaire; and obtaining the questionnaire clustering classification and abnormal points through the clustering analysis.
Further, the questionnaire collecting module is further used for adding parameters to the sharing link of the questionnaire to record the propagation path of the questionnaire; and according to the propagation path, whether the questionnaire is spread to a target group or not can be checked and monitored in real time.
Different from the prior art, the method for improving the quality of the network questionnaire in the technical scheme comprises the steps of questionnaire design, questionnaire collection and questionnaire analysis, the quality control of the network questionnaire is performed through the whole process of questionnaire design, publishing, collection and final data cleaning and analysis, the problem questionnaire can be effectively screened out, the questionnaire is diffused into a target group, and the real-time monitoring and dynamic monitoring of the questionnaire are realized. And the factor analysis and the clustering algorithm are combined, so that abnormal values are effectively identified, the data quality of the network questionnaire is improved, and a good data guarantee is provided for later-stage sample analysis.
Drawings
FIG. 1 is a flow chart illustrating steps of a method for improving the quality of a web questionnaire in accordance with an embodiment;
FIG. 2 is a network diagram illustrating the propagation of questionnaires in accordance with an embodiment;
FIG. 3 is a graph of the characteristic values of the factor analysis according to the preferred embodiment;
FIG. 4 is a graph of factor score distribution according to an embodiment;
FIG. 5 is a diagram illustrating the results of cluster analysis in accordance with an exemplary embodiment;
FIG. 6 is a block diagram of an apparatus for improving the quality of a web questionnaire according to an embodiment;
description of reference numerals:
10. a questionnaire design module;
20. a questionnaire collection module;
30. a questionnaire analysis module;
Detailed Description
To explain technical contents, structural features, and objects and effects of the technical solutions in detail, the following detailed description is given with reference to the accompanying drawings in conjunction with the embodiments.
Referring to fig. 1 to 6, the present embodiment provides a method for improving quality of a web questionnaire, which can control quality of the questionnaire through design, issue, collection, and final questionnaire data cleaning processes of the questionnaire, realize real-time monitoring and dynamic monitoring of the questionnaire by combining questionnaire contents of questionnaire issuers, and combine factor analysis and clustering algorithm to effectively identify abnormal values, improve data quality of the web questionnaire, and provide a good data guarantee for later-stage sample analysis.
As shown in fig. 1, the method for improving the quality of the web questionnaire includes the following steps:
s101, designing a questionnaire, designing the questionnaire, and adding test questions into the questionnaire, wherein the test questions are used for screening out the questionnaire which does not meet the standard in response;
s102, collecting questionnaires, issuing the questionnaires and recovering the answered questionnaires on the network, and guiding the questionnaires to be diffused to a target group by setting a threshold value of diffusion parameters, wherein the diffusion parameters comprise any one or more of IP (Internet protocol) of the questionnaires, response time and answer rules;
and S103, analyzing the questionnaires, rejecting abnormal questionnaires in the recovered questionnaires by using a clustering algorithm, and analyzing the remaining questionnaires.
The test questions comprise single test questions and combined test questions, the single test questions can judge whether the user answers the questionnaire seriously by using one test question independently, and the combined test questions judge whether the user answers the questionnaire seriously by more than two associated test questions.
In the questionnaire design of step S101, trap questions are designed by using functions of single-question screening (i.e., single test question), multi-question screening (i.e., combination test question), option citation, and the like, which are commonly used in the present questionnaire survey system, to find samples that do not answer seriously (i.e., unqualified questionnaires).
The question screening function of the questionnaire system can set some problems which are obviously false or wrong in fact, such as '2 months and 30 days are new years' or 'the earth is triangular' and the like, and the problems are used for judging whether the user reads the questionnaire question stem seriously.
And (3) double-topic screening function and option reference setting: setting trap questions, setting repeat questions and similar questions based on the user's existing answers, the answers to the associated questions should be consistent, and if the data lacks consistency, the question should be identified as an invalid questionnaire. In example two, option reference setting needs to be added into the system, and a question stem of the question 8 is generated according to the answer of the user to the question 1.
Example one:
topic 1: what kind of drugs do you use?
A. Amoxicillin medicine history B, aspirin medicine history
C. The cephalosporin medicine history D. the levofloxacin medicine history E. is none
Topic 8: what kind of drugs do you use?
A. History of Amoxicillin drug B, history of levofloxacin drug
C. Cephalosporin drug history D, aspirin drug history E, neither
Example two:
topic 1: what kind of drugs do you use?
A. Amoxicillin medicine history B, aspirin medicine history
C. The cephalosporin medicine history D. the levofloxacin medicine history E. is none
Topic 8: whether you used?
(in the system setup, if the user chooses none, then the A option, i.e. amoxicillin drug history, is displayed)
A is whether B is
In addition, it is also possible to set questions conforming to internal logics according to the contents of the questionnaire itself and perform sample quality determination using the internal logics, which is suitable for questionnaire surveys with strong professional properties such as medicine, for example, patients with inflammation generally have a history of anti-inflammatory drug therapy, and as shown in the example, if any one of the answers of question 1 and question A, B, C, D is selected, the answer of question 15 is not likely to be E, and thus data can be screened from a professional perspective.
For example:
topic 1: whether you have had an inflammation:
A. superficial gastritis B, atrophic gastritis
C. Metaplasia of the intestinal epithelium d. atypical hyperplasia
E. All are absent;
topic 15: whether you have used the following drugs:
A. amoxicillin medicine history B, aspirin medicine history
C. Cephalosporin drug history D. helicobacter pylori drug history
E. The medical history of levofloxacin is F. none;
in the process of designing the questionnaire, a plurality of screening rules can be multiplexed, and inaccurate data caused by only using one rule is prevented from entering a final sample. Generally, it is suggested that a questionnaire publisher sets at least one trap question if the number of questionnaire questions is more than 20, and sets at least two trap questions if the number of questionnaire questions is more than 35.
In step S102, after the questionnaire is published on the network, the user can view the questionnaire time-sharing data in real time by using the threshold of the diffusion parameter, so as to control the publishing and recycling of the sample in the network questionnaire, and diffuse the network questionnaire to an appropriate target group. Meanwhile, related parameters are added to the questionnaire sharing link to record the questionnaire propagation path, so that the sample quality is monitored, and efficient and quality questionnaire recovery is achieved. As shown in fig. 2, in this embodiment, data can be checked and monitored in real time at the mobile phone end, and questionnaire data is visualized and displayed, so that a questionnaire publisher can control the diffusion of questionnaires conveniently, and the questionnaires are guided to a proper group, thereby ensuring that sampling is unbiased. The monitoring billboard adopts a network diagram form to display the questionnaire issuing path of the user, and allows the user to set different conditions to view the questionnaire quality of the user. The quality index of the questionnaire here includes the answering time, the number of consecutive identical answers, and the like. The mobile phone end data monitoring billboard is as shown in fig. 2, different indexes can be selected in the billboard, questionnaires collected by different users can be checked according to different time, and links with low recovery quality are invalid.
In step S103, outlier rejection is performed by using a clustering algorithm during questionnaire data cleansing. In one embodiment, an abnormal value elimination method combining factor analysis and cluster analysis is provided in combination with the practical application environment of questionnaire survey. And (4) performing factor analysis on the data after being eliminated in the steps S101-S103, calculating factor scores, and performing cluster analysis by using the factor scores instead of the original samples, wherein the cluster calculation method is not limited to Kmeans clustering, AP clustering, DBSCAN and the like. The sample data can be obviously clustered into several classes and distinguished from abnormal points through clustering analysis.
Taking a certain questionnaire data as an example, showing how to perform clustering analysis after reducing questionnaire dimensions by using factor analysis, and identifying abnormal points.
This questionnaire is a pre-questionnaire, which is a test prior to the official questionnaire. In this pre-interrogation furling set, 285 parts of valid data are collected in total.
Evaluating whether the questionnaire is suitable for factor analysis, calculating a KMO value of the questionnaire and carrying out spherical inspection on the questionnaire; in this example, the KMO value of the questionnaire is 0.663334, and the p value after the spherical examination is much less than 0.05 and 1.431e-240, so that the questionnaire is suitable for the factor analysis;
determining the number of factors in the questionnaire; the parameter estimation is carried out by utilizing a principal component method, the number of required factors is determined by utilizing a characteristic value, a characteristic value graph is shown in figure 3, and it can be seen from figure 3 that the factor analysis of the embodiment selects 5 factors which are more suitable;
thirdly, performing factor analysis on the questionnaire, wherein in the example, orthogonal rotation is adopted, and the factor score of the questionnaire factor analysis is shown in FIG. 4;
calculating the factor load of each sample to finish the data dimension reduction;
performing clustering analysis on the dimensionality reduced data, and searching abnormal points through a visual clustering result; in this example, the AP clustering algorithm is adopted, and the result of visualizing the clustering result is shown in fig. 5, as can be seen from fig. 5, the categories labeled as 2 are less aggregated than other categories, and the number of the categories is significantly less than that of other categories, and may be abnormal points, and the original data thereof is called out to be checked to further determine whether the results are caused by the sample quality.
According to the embodiment, the quality control of the questionnaire is performed through the processes of questionnaire design, issuing, collecting and final data cleaning, the questionnaire content of a questionnaire issuer is combined, the real-time monitoring and dynamic monitoring of the questionnaire are realized, the factor analysis and the clustering algorithm are combined, abnormal values are effectively identified, the data quality of the network questionnaire is improved, and good data guarantee is provided for later sample analysis.
In another embodiment or apparatus for improving the quality of a web questionnaire is provided, as shown in fig. 6. The device for improving the quality of the network questionnaire can control the quality of the questionnaire through the design, release and collection of the questionnaire and the final questionnaire data cleaning process, realizes real-time monitoring and dynamic monitoring of the questionnaire by combining the questionnaire content of a questionnaire publisher, combines factor analysis and clustering algorithm, effectively identifies abnormal values, improves the data quality of the network questionnaire, and provides good data guarantee for later sample analysis. The apparatus for improving the quality of the web questionnaire as shown in fig. 6 comprises:
a questionnaire design module 10, which is used for designing questionnaires and adding test questions into the questionnaires, wherein the test questions are used for screening out questionnaires with unqualified answers;
a questionnaire collecting module 20, configured to issue the questionnaire on the network and recover the answered questionnaire, and guide the questionnaire to be diffused to a target group by setting a threshold of diffusion parameters, where the diffusion parameters include any one or more of an IP of the questionnaire, response time, and answer rules; and
and the questionnaire analysis module 30 is used for eliminating abnormal questionnaires in the recovered questionnaires by using a clustering algorithm and analyzing the residual questionnaires.
The questionnaire design module 10 is configured to design trap questions by using functions of single-question screening (i.e., single test question), multi-question screening (i.e., combined test question), option citation, and the like, which are commonly used in the questionnaire survey system, so as to find out samples that do not answer seriously (i.e., unqualified questionnaires).
The question screening function of the questionnaire system can set some problems which are obviously false or wrong in fact, such as '2 months and 30 days are new years' or 'the earth is triangular' and the like, and the problems are used for judging whether the user reads the questionnaire question stem seriously.
And (3) double-topic screening function and option reference setting: setting trap questions, setting repeat questions and similar questions based on the user's existing answers, the answers to the associated questions should be consistent, and if the data lacks consistency, the question should be identified as an invalid questionnaire.
The questionnaire collecting module 20 is further configured to, after the questionnaire is published on the network, enable a user to view questionnaire time-sharing data in real time by using a threshold of the diffusion parameter, thereby controlling publication and recovery of the sample in the network questionnaire, and diffusing the network questionnaire to an appropriate target group. Meanwhile, related parameters are added to the questionnaire sharing link to record the questionnaire propagation path, so that the sample quality is monitored, and efficient and quality questionnaire recovery is achieved. As shown in fig. 2, in this embodiment, data can be checked and monitored in real time at the mobile phone end, and questionnaire data is visualized and displayed, so that a questionnaire publisher can control the diffusion of questionnaires conveniently, and the questionnaires are guided to a proper group, thereby ensuring that sampling is unbiased. The monitoring billboard adopts a network diagram form to display the questionnaire issuing path of the user, and allows the user to set different conditions to view the questionnaire quality of the user. The quality index of the questionnaire here includes the answering time, the number of consecutive identical answers, and the like. The mobile phone end data monitoring billboard is as shown in fig. 2, different indexes can be selected in the billboard, questionnaires collected by different users can be checked according to different time, and links with low recovery quality are invalid.
The questionnaire analysis module 30 is used for implementing outlier rejection by using a clustering algorithm when questionnaire data is cleaned. In an embodiment, the questionnaire analysis module 30 is further configured to propose an abnormal value elimination method combining factor analysis and cluster analysis in combination with an actual application environment of the questionnaire survey. The questionnaire analysis module 30 performs factor analysis on the removed data, calculates a factor score, and performs cluster analysis by using the factor score instead of the original sample, and the cluster calculation method is not limited to Kmeans cluster, AP cluster, DBSCAN, and the like. The sample data can be obviously clustered into several classes and distinguished from abnormal points through clustering analysis.
It should be noted that, although the above embodiments have been described herein, the invention is not limited thereto. Therefore, based on the innovative concepts of the present invention, the technical solutions of the present invention can be directly or indirectly applied to other related technical fields by making changes and modifications to the embodiments described herein, or by using equivalent structures or equivalent processes performed in the content of the present specification and the attached drawings, which are included in the scope of the present invention.
Claims (9)
1. A method for improving the quality of a web questionnaire, comprising the steps of:
designing a questionnaire, designing the questionnaire and adding test questions into the questionnaire, wherein the test questions are used for screening out the questionnaire which does not meet the standard in response;
collecting questionnaires, issuing the questionnaires on the network and recovering the answered questionnaires, and guiding the questionnaires to be diffused to a target group by setting a threshold value of diffusion parameters, wherein the diffusion parameters comprise any one or more of IP (Internet protocol) of the questionnaires, response time and answer rules;
and (4) questionnaire analysis, namely, rejecting abnormal questionnaires in the recovered questionnaires by using a clustering algorithm, and analyzing the remaining questionnaires.
2. The method of claim 1, wherein the test questions comprise a single test question and a combined test question, the single test question can determine whether the user answers the questionnaire carefully by using one test question alone, and the combined test question can determine whether the user answers the questionnaire carefully by using more than two associated test questions.
3. The method for improving the quality of the network questionnaire according to claim 1, wherein the step of rejecting abnormal questionnaires in the recovered questionnaires by using a clustering algorithm further comprises the following steps:
performing factor analysis on the removed questionnaire to obtain a factor score;
performing clustering analysis by using the factor score instead of the original questionnaire;
and obtaining the questionnaire clustering classification and abnormal points through the clustering analysis.
4. The method for improving the quality of the network questionnaire according to claim 3, wherein the clustering analysis using the factor score instead of the original questionnaire comprises any one of Kmeans clustering, AP clustering and DBSCAN.
5. The method for improving the quality of the network questionnaire of claim 1, wherein when the questionnaire is issued on the network and the answered questionnaire is recovered, the method further comprises the steps of: adding parameters to the sharing link of the questionnaire to record the propagation path of the questionnaire;
and according to the propagation path, whether the questionnaire is spread to a target group or not can be checked and monitored in real time.
6. The method of claim 5, wherein a network node graph is used to show the propagation path of the questionnaire.
7. An apparatus for improving the quality of a web questionnaire, comprising:
the questionnaire design module is used for designing questionnaires and adding test questions into the questionnaires, and the test questions are used for screening out the questionnaires with unqualified answers;
the questionnaire collecting module is used for issuing the questionnaire on the network and recovering the answered questionnaire, and guiding the questionnaire to be diffused to a target group by setting a threshold value of diffusion parameters, wherein the diffusion parameters comprise any one or more of IP (Internet protocol) of the questionnaire, response time and answer rules; and
and the questionnaire analysis module is used for eliminating abnormal questionnaires in the recovered questionnaires by using a clustering algorithm and analyzing the residual questionnaires.
8. The apparatus for improving network questionnaire quality of claim 7, wherein the questionnaire analysis module is further configured to perform factor analysis on the rejected questionnaire to obtain a factor score; performing clustering analysis by using the factor score instead of the original questionnaire; and obtaining the questionnaire clustering classification and abnormal points through the clustering analysis.
9. The apparatus for improving the quality of the web questionnaire of claim 7, wherein the questionnaire collecting module is further configured to add a parameter to a sharing link of the questionnaire to record a propagation path of the questionnaire; and according to the propagation path, whether the questionnaire is spread to a target group or not can be checked and monitored in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011458128.4A CN112446644A (en) | 2020-12-11 | 2020-12-11 | Method and device for improving quality of network questionnaire |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011458128.4A CN112446644A (en) | 2020-12-11 | 2020-12-11 | Method and device for improving quality of network questionnaire |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112446644A true CN112446644A (en) | 2021-03-05 |
Family
ID=74739993
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011458128.4A Pending CN112446644A (en) | 2020-12-11 | 2020-12-11 | Method and device for improving quality of network questionnaire |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112446644A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116703332A (en) * | 2023-07-28 | 2023-09-05 | 成都数智创新精益科技有限公司 | Petroleum questionnaire investigation analysis system and method based on micro-service architecture |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001184273A (en) * | 1999-12-22 | 2001-07-06 | Nec Corp | Questionnaire system, and method of automating questionnaire work |
| CN107480187A (en) * | 2017-07-10 | 2017-12-15 | 北京京东尚科信息技术有限公司 | User's value category method and apparatus based on cluster analysis |
| CN110334934A (en) * | 2019-06-27 | 2019-10-15 | 苏州众言网络科技股份有限公司 | The method and device of data analysis |
| CN110955846A (en) * | 2018-09-26 | 2020-04-03 | 北京国双科技有限公司 | Propagation path diagram generation method and device |
-
2020
- 2020-12-11 CN CN202011458128.4A patent/CN112446644A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001184273A (en) * | 1999-12-22 | 2001-07-06 | Nec Corp | Questionnaire system, and method of automating questionnaire work |
| CN107480187A (en) * | 2017-07-10 | 2017-12-15 | 北京京东尚科信息技术有限公司 | User's value category method and apparatus based on cluster analysis |
| CN110955846A (en) * | 2018-09-26 | 2020-04-03 | 北京国双科技有限公司 | Propagation path diagram generation method and device |
| CN110334934A (en) * | 2019-06-27 | 2019-10-15 | 苏州众言网络科技股份有限公司 | The method and device of data analysis |
Non-Patent Citations (1)
| Title |
|---|
| 唐焱 等: "苏南地区农民土地承包经营权置换城镇保障的意愿研究", 《华中农业大学学报（社会科学版）》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116703332A (en) * | 2023-07-28 | 2023-09-05 | 成都数智创新精益科技有限公司 | Petroleum questionnaire investigation analysis system and method based on micro-service architecture |
| CN116703332B (en) * | 2023-07-28 | 2023-10-17 | 成都数智创新精益科技有限公司 | Petroleum questionnaire investigation analysis system and method based on micro-service architecture |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dalvi-Esfahani et al. | Social media addiction: Applying the DEMATEL approach | |
| McCreadie et al. | TREC incident streams: Finding actionable information on social media | |
| Hamid et al. | Role of social media in information-seeking behaviour of international students: A systematic literature review | |
| Knott | Everyday nationalism: A review of the literature | |
| Rourke et al. | Methodological issues in the content analysis of computer conference transcripts | |
| Karduni et al. | Can you verifi this? studying uncertainty and decision-making about misinformation using visual analytics | |
| Walker et al. | Epidemiological analysis of the quality of HIV sero-surveillance in the world: how well do we track the epidemic? | |
| Blooma et al. | Predictors of high‐quality answers | |
| Hornbæk et al. | Comparison of techniques for matching of usability problem descriptions | |
| Saleem et al. | Systematic literature reviews in cyberbullying/cyber harassment: A tertiary study | |
| Li et al. | Computing the veracity of information through crowds: A method for reducing the spread of false messages on social media | |
| Ruangnapakul et al. | A systematic analysis of cyber bullying in Southeast Asia countries | |
| Finn et al. | The Co-retweeted Network and Its Applications for Measuring the Perceived Political Polarization. | |
| Ross et al. | Beyond “fake news”: The role of analytic thinking in the detection of inaccuracy and partisan bias in news headlines | |
| Nawaz et al. | Recommendation of effectiveness of YouTube video contents by qualitative sentiment analysis of its comments and replies | |
| CN112446644A (en) | Method and device for improving quality of network questionnaire | |
| Babcock et al. | Pretending positive, pushing false: Comparing captain marvel misinformation campaigns | |
| Tachaiya et al. | SentiStance: quantifying the intertwined changes of sentiment and stance in response to an event in online forums | |
| Liang et al. | The dynamics of event-based political influencers on Twitter: A longitudinal analysis of influential accounts during Chinese political events | |
| Manoli et al. | Perceptions of the role of traditional and social media in communicating corruption | |
| Chen | Understanding paracrisis communication: Towards developing a framework of paracrisis typology and organizational response strategies | |
| Schwanda-Sosik et al. | Online microsurveys for user experience research | |
| Gruzd et al. | The analysis of online communities using interactive content-based social networks | |
| Okkonen et al. | Off-the-shelf assessment of information ergonomics | |
| Mukherjee et al. | Analyzing attitude of second screen social media messages |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210305 |
|
| WD01 | Invention patent application deemed withdrawn after publication |