Digital Psychological Platform for Mass Web-Surveys
Abstract
:1. Summary
2. Data Description
2.1. Initial Dataset
- (1)
- “Do you have any responsibilities at school that are not directly related to your psychological activities?”—3694 answers.
- (2)
- “Do you have suggestions for the development of psychological service in the educational system of your region?”—16,700 answers.
2.2. Output Data
- Leaders and assistant managers.
- Attendants, educators, and counselors in the camps, librarians.
- Teachers of various educational profiles and tutors of different profiles.
- The duty, educators, and counselors in camps, librarians.
- An increase in the number of rates at school and the allocation of hours in the curriculum.
- The creation of centers and the provision of methodological support.
- The increase in salary.
- Conducting training activities.
- Technical equipment of the office and the provision of diagnostic materials.
- General development of the system.
- Creating a unified regulatory framework, documentation, and reporting.
3. Methods
3.1. Data Collection
- (1)
- version—questionnaire standard version;
- (2)
- content—questionnaire content:
- (a)
- blocks—list of blocks that determine the questionnaire structure;
- (3)
- calculation—calculations carried out as part of the questionnaire:
- (a)
- scales—scales list for performing calculations within the questionnaire;
- (4)
- resource—resource files (images, media) used as part of the questionnaire:
- (a)
- files—list of resource files such as images;
- (5)
- report—reports to be generated for samples and research:
- (a)
- items—list of reports provided to researchers;
- (6)
- settings—global questionnaire parameters:
- (a)
- language—questionnaire language:
- (b)
- restrictions—device restrictions (i.e., restrict access to portable devices only).
- (1)
- items—array of questions, instructions, and other visible elements;
- (2)
- presets—block parameters of the questionnaire:
- (a)
- itemsPerPage—maximum number of questions that can be simultaneously presented on a single page;
- (b)
- itemsOrder—order of questions presented within the block;
- (c)
- pageWidth—a setting that allows to stretch the questionnaire area to the width of the window: either standard or wide;
- (d)
- showProgressBar—display progress indicator;
- (e)
- showTimer—display of the questionnaire run time indicator;
- (f)
- expectedTime—the expected time to complete the block of questions (in seconds);
- (g)
- previousPageAccess—allowing access to the previous page;
- (h)
- interruptCondition—scale key, reflecting the condition for interruption of the block passing; it fires when the result of the scale calculation becomes “true”.
- (1)
- type—question type (in this case, input field);
- (2)
- variables—values used to refer to the results of answers for organizing calculations:
- (a)
- key—question key name for which the result will be saved;
- (b)
- tags—tags array by which it is allowed to refer to the question answers for calculations in scales;
- (3)
- request—text and other materials expressing the essence of the issue:
- (a)
- label—displayed question name.
- (4)
- answer—parameters of the answer to the question:
- (a)
- type—answer type (in described case, “string” type);
- (b)
- minLength—minimum allowed string length for input (inclusive);
- (c)
- maxLength—maximum allowed string length for input (inclusive);
- (d)
- format—valid input string format (“any”, “email”, “pattern”);
- (e)
- pattern—regular expression that defines the format of the input string.
- -
- reading and unpacking a package with a questionnaire;
- -
- checking the questionnaire description for compliance with the current standard version;
- -
- if necessary, carrying out the questionnaire migration procedure using appropriate scripts;
- -
- converting the questionnaire to internal data representation;
- -
- generating a cross-platform web interface based on the standard in the internal representation using the description of components and web frameworks;
- -
- adapting the display and structure of all interface components to the end device.
3.2. Data Processing
- Free-form answer preprocessing.
- Text data analysis and topic modeling.
- Interpretation of topic modeling.
- Grouping and use of results.
4. User Notes
4.1. Instruction for Processing the Question (1)
4.1.1. Required Software
- -
- Python version 3.6.7;
- -
- Package manager pip (https://pip.pypa.io/en/stable/).
4.1.2. Bootstrap Instructions
- -
- pip install virtualenv
- -
- python3 -m venv env
- -
- source env/Sctipts/activate
- -
- pip install virtualenv
- -
- python3 -m venv env
- -
- source env/bin/activate for linux
- -
- pip install -r requimenst.txt
4.1.3. Run Instructions
- -
- jupyter notebook
4.2. Instruction for Processing the Question (2)
4.2.1. Required Software
- -
- Node.JS version 12 or newer;
- -
- Package manager npm (https://www.npmjs.com/package/npm);
- -
- Gulp task manager version 4 or newer (https://www.npmjs.com/package/gulp).
4.2.2. Bootstrap Instructions
- -
- npm install
4.2.3. Run Instructions
- -
- gulp freeform: clusterize
- -
- freeform: retrieveData—the command retrieves answers to question (2) from the entire array of answers and saves them to temporary storage on disk
- -
- freeform: preprocessData—splits sentences in one answer into separate answers, performs tokenization, removes punctuation, and stop words and brings words to normal form
- -
- freeform: buildVocabulary—performs a search for synonyms applicable to answer texts, on the basis of which it builds a dictionary to replace words
- -
- freeform: findFrequentSets—searches for clusters using the LDA algorithm, while excluding verbs, numerals, and tokens in the Latin alphabet
- -
- freeform: outputClusters—outputs the clustering result to separate files into the directory/out
5. Conclusions
Author Contributions
Funding
Conflicts of Interest
References
- Krosnick, J.A. Survey research. Annu. Rev. Psychol. 1999, 50, 537–567. [Google Scholar] [CrossRef] [PubMed]
- Roberts, M.E.; Stewart, B.M.; Tingley, D.; Lucas, C.; Gadarian, S.K.; Albertson, B.; Rand, D.G.; Leder-Luis, J. Structural Topic Models for Open-Ended Survey Responses. Am. J. Political Sci. 2014, 58, 1064–1082. [Google Scholar] [CrossRef] [Green Version]
- Hays, R.D.; Liu, H.; Kapteyn, A. Use of Internet panels to conduct surveys. Behav. Res. Methods 2015, 47, 685–690. [Google Scholar] [CrossRef] [PubMed]
- Nikulchev, E.; Kolyasnikov, P.; Ilin, D.; Kasatonov, S.; Biryukov, D.; Zakharov, I. Selection of Architectural Concept and Development Technologies for the Implementation of a Web-Based Platform for Psychology Research. Adv. Intell. Syst. Comput. 2019, 858, 672–685. [Google Scholar] [CrossRef]
- Keusch, F. Why do people participate in Web surveys? Applying survey participation theory to Internet survey data collection. Manag. Rev. Q. 2015, 65, 183–216. [Google Scholar] [CrossRef]
- Das, M.; Ester, P.; Kaczmirek, L. (Eds.) Social and Behavioral Research and the Internet: Advances in Applied Methods and Research Strategies; Routledge, Taylor and Francis Group: Oxfordshire, UK, 2018. [Google Scholar]
- Barakhnin, V.B.; Duisenbayeva, A.N.; Kozhemyakina, O.; Yergaliyev, Y.N.; I Muhamedyev, R. The automatic processing of the texts in natural language. Some bibliometric indicators of the current state of this research area. J. Phys. Conf. Ser. 2018, 1117, 012001. [Google Scholar] [CrossRef]
- Buenaño-Fernández, D.; Gonzalez, M.; Gil, D.; Luján-Mora, S. Text Mining of Open-Ended Questions in Self-Assessment of University Teachers: An LDA Topic Modeling Approach. IEEE Access 2020, 8, 35318–35330. [Google Scholar] [CrossRef]
- Kochedykov, D.; Apishev, M.; Golitsyn, L.; Vorontsov, K. Fast and Modular Regularized Topic Modelling. In Proceedings of the 21st Conference of FRUCT Association, Helsinki, Finland, 6 November 2017; pp. 182–193. [Google Scholar]
- Jasim, M. Building Cross-Platform Desktop Applications with Electron; Packt Publishing Ltd.: Birmingham, UK, 2017. [Google Scholar]
- Pietsch, A.-S.; Lessmann, S. Topic modeling for analyzing open-ended survey responses. J. Bus. Anal. 2018, 1, 93–116. [Google Scholar] [CrossRef] [Green Version]
- Blei, D.M.; Ng, A.Y.; Jordan, M.I. Latent dirichlet allocation. J. Mach. Learn. Res. 2003, 3, 993–1022. [Google Scholar]
- Finch, W.H.; Finch, M.E.H.; McIntosh, C.E.; Braun, C. The use of topic modeling with latent Dirichlet analysis with open-ended survey items. Transl. Issues Psychol. Sci. 2018, 4, 403–424. [Google Scholar] [CrossRef]
- Maier, D.; Waldherr, A.; Miltner, P.; Wiedemann, G.; Niekler, A.; Keinert, A.; Pfetsch, B.; Heyer, G.; Reber, U.; Häussler, T.; et al. Applying LDA Topic Modeling in Communication Research: Toward a Valid and Reliable Methodology. Commun. Methods Meas. 2018, 12, 93–118. [Google Scholar] [CrossRef]
- Burnham, T. Coffeescript: Accelerated Javascript Development; Pragmatic Bookshelf: Raleigh, NC, USA, 2015. [Google Scholar]
- Fain, Y.; Moiseev, A. Angular 2 Development with TypeScript; Manning Publications Co.: Shelter Island, NY, USA, 2016. [Google Scholar]
- Marani, F. Adding CSS/JavaScript to Our Django Project. In Practical Django 2 and Channels 2; Apress: Berkeley, CA, USA, 2019; pp. 179–203. [Google Scholar]
- Libby, A. Mastering PostCSS for Web Design; Packt Publishing Ltd.: Birmingham, UK, 2016. [Google Scholar]
- Campos, U.F.; Smethurst, G.; Moraes, J.P.; Bonifacio, R.; Pinto, G. Mining Rule Violations in JavaScript Code Snippets. In Proceedings of the 2019 IEEE/ACM 16th International Conference on Mining Software Repositories (MSR), Montréal, QC, Canada, 26–27 May 2019; pp. 195–199. [Google Scholar]
- Nikulchev, E.; Ilin, D.; Belov, B.; Kolyasnikov, P.; Kosenkov, A. e-Learning Tools on the Healthcare Professional Social Networks. Int. J. Adv. Comput. Sci. Appl. 2019, 10, 29–34. [Google Scholar] [CrossRef] [Green Version]
- Tomasdottir, K.F.; Aniche, M.; Van Deursen, A. The Adoption of JavaScript Linters in Practice: A Case Study on ESLint. IEEE Trans. Softw. Eng. 2018, 46, 863–869. [Google Scholar] [CrossRef] [Green Version]
- Mardan, A. Getting Node.js Apps Production Ready. In Practical Node.js; Springer Science and Business Media LLC.: Berlin/Heidelberg, Germany, 2018; pp. 331–364. [Google Scholar]
- Agocs, A.; Le Goff, J.-M. A web service based on RESTful API and JSON Schema/JSON Meta Schema to construct knowledge graphs. In Proceedings of the 2018 International Conference on Computer, Information and Telecommunication Systems (CITS), Colmar, France, 11–13 July 2018; pp. 1–5. [Google Scholar]
- Izquierdo, J.L.C.; Cabot, J. JSONDiscoverer: Visualizing the schema lurking behind JSON documents. Knowl. Based Syst. 2016, 103, 52–55. [Google Scholar] [CrossRef]
- Yigitbas, E.; Anjorin, A.; Jovanovikj, I.; Kern, T.; Sauer, S.; Engels, G. Usability Evaluation of Model-Driven Cross-Device Web User Interfaces. In Proceedings of the Agreement Technologies; Springer Science and Business Media LLC.: Berlin/Heidelberg, Germany, 2018; pp. 231–247. [Google Scholar]
- Sabaren, L.N.; Mascheroni, M.A.; Greiner, C.L.; Irrazá, L. A systematic literature review in cross-browser testing. J. Comput. Sci. Technol. 2018, 18, 18–27. [Google Scholar]
- Wallach, H.M. Topic modeling: Beyond bag-of-words. In Proceedings of the 23rd International Conference on Machine Learning, Pittsburgh, PA, USA, 25–29 June 2006; pp. 977–984. [Google Scholar]
- Mehrotra, R.; Sanner, S.; Buntine, W.; Xie, L. Improving LDA topic models for microblogs via tweet pooling and automatic labeling. In Proceedings of the 36th International ACM SIGIR Conference, Dublin, Ireland, 26 December 2013; p. 889. [Google Scholar]
- Mimno, D.; Wallach, H.M.; Talley, E.; Leenders, M.; McCallum, A. Optimizing semantic coherence in topic models. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, Edinburgh, UK, 27–31 July 2011; Association for Computational Linguistics: Stroudsburg, PA, USA; pp. 262–272. [Google Scholar]
Relevance of the Topic | Answer |
---|---|
0.371 | It is necessary to regulate the work of the school psychologist, because with the arrival of children with disabilities in schools, almost all the time allotted for work is reduced for work with these children, and their number increases every year, but nobody canceled the work with other children at school, so working time becomes dimensionless. It is necessary to increase the number of teachers-psychologists at educational institutions working with children with disabilities. Well, increase the salary, because work from morning to evening and the salary is much less than that of teachers. |
0.235 | The introduction of correctional and developmental classes with students in the grid of the lesson schedule, as well as the involvement of specialists such as a defectologist and speech therapist in the public educational institution. |
0.176 | To increase the number of specialists in schools with a population of over 300 people. |
0.133 | Providing everything necessary for work, including a separate office! Reducing the amount of useless paperwork, increasing salaries by 20–30%. |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Nikulchev, E.; Ilin, D.; Silaeva, A.; Kolyasnikov, P.; Belov, V.; Runtov, A.; Pushkin, P.; Laptev, N.; Alexeenko, A.; Magomedov, S.; et al. Digital Psychological Platform for Mass Web-Surveys. Data 2020, 5, 95. https://doi.org/10.3390/data5040095
Nikulchev E, Ilin D, Silaeva A, Kolyasnikov P, Belov V, Runtov A, Pushkin P, Laptev N, Alexeenko A, Magomedov S, et al. Digital Psychological Platform for Mass Web-Surveys. Data. 2020; 5(4):95. https://doi.org/10.3390/data5040095
Chicago/Turabian StyleNikulchev, Evgeny, Dmitry Ilin, Anastasiya Silaeva, Pavel Kolyasnikov, Vladimir Belov, Andrey Runtov, Pavel Pushkin, Nikolay Laptev, Anna Alexeenko, Shamil Magomedov, and et al. 2020. "Digital Psychological Platform for Mass Web-Surveys" Data 5, no. 4: 95. https://doi.org/10.3390/data5040095