=Paper=
{{Paper
|id=Vol-2616/paper1
|storemode=property
|title=Architecture of the Computer-Linguistic System for Processing of Specialized Web-communities’ Educational Content
|pdfUrl=https://ceur-ws.org/Vol-2616/paper1.pdf
|volume=Vol-2616
|authors= Pavlo Zhezhnych, Anna Shilinh, Ivan Demydov
|dblpUrl=https://dblp.org/rec/conf/coapsn/ZhezhnychSD20
}}
==Architecture of the Computer-Linguistic System for Processing of Specialized Web-communities’ Educational Content==
https://ceur-ws.org/Vol-2616/paper1.pdf
Architecture of the Computer-linguistic System for
Processing of Specialized Web-communities’ Educational
Content
Pavlo Zhezhnych 1[0000-0002-2044-5408], Anna Shilinh1[0000-0003-1063-3437],
and Ivan Demydov1[0000-0002-1221-3885]
1
Lviv Polytechnic National University, 12 S. Bandery str., Lviv, 79000, Ukraine
pavlo.i.zhezhnych@lpnu.ua, anna.y.shilinh@lpnu.ua,
ivan.demydov@gmail.com
Abstract. The aim of the article is the architecture of the computer-linguistic
processing system of web-communities’ educational content, which makes it
possible to predict and form qualitative students’ contingent of higher education
institutions and to make management decisions based on the motivational inten-
tions of potential entrants. The paper proposes the architecture and functional
structure of the computer-linguistic processing system of educational communi-
ties’ content for effective planning to provision of educational services based on
procedures selection of potential entrants’ motivational intentions and the quali-
ty of information content for educational communities. Chart data streams of
complex information system automated processing of specialized educational
content describes the operation of software agents working out of the content.
The proposed software agents select relevant thematic educational discussions,
identify motivational intentions of potential entrants, and formulate reaction of
higher education institutions to selected postings to provide and create quality
content for specialized online education communities. The results of the
research are applied and can be used to effectively plan educational services
and to create quality content for specialized educational communities, taking
into account the motivational intentions of potential entrants.
Keywords: Educational Content, Data Flow Diagram, Software Agent, Com-
puter-linguistic Processing System, Architecture and Functional Structure.
1 Introduction
Today, higher education institutions (HEI) are the focus to the provision of education-
al services for higher education applicants. In general, the educational service is inter-
preted as the end result of the planning process and providing these services.
Copyright © 2020 for this paper by its authors. Use permitted under Creative Commons Li-
cense Attribution 4.0 International (CC BY 4.0). COAPSN-2020: International Workshop on
Control, Optimisation and Analytical Processing of Social Networks
That is why the developed information systems are oriented to support the main forms
of introduction of educational services in the educational process. However, the ab-
sence of educational consumers makes it impossible to carry out the process of
providing these services of higher education institutions. HEIs need to undergo major
changes in their management approach [1], which will change the way institutions
manage their processes, services and structures; and will force them to evolve into
frameworks when such elements become instruments of flexibility and innovation
rather than obstacles to growth and development [2].
Therefore, a prerequisite for the existence of HEI in the market of educational ser-
vices is to predict the consumers’ contingent of these services. For this reason, the
main task of this article is creation the architecture of the computer-linguistic pro-
cessing system of the specialized communities’ educational content for the formation
of a qualitative contingent of educational services consumers and for management
decision-making by HEI.
2 Related Works
There are several areas for studying the architecture of information systems, in par-
ticular for the efficient operation of higher education institutions today.
An analysis of the process of development of information systems architecture, as
well as instructions and rules for the development, presentation and understanding of
information systems architecture is considered in [3-5]. In particular, it is determined
that the development of information systems architecture should consist of five stag-
es, such as the planning and design phase, the operational analysis phase, the re-
quirements analysis phase, the function analysis phase, the physical synthesis phase.
The papers [6-8] formulate recommendations for the development and improve-
ment of information technologies and systems for supporting organizational goals to
increase their competitiveness.
Integrated processing method of heterogeneous information resources of web-
systems, which simplifies the technology of integrated automation and content man-
agement described in [9]. Informational resources processing intellectual systems
(IRPISes) with textual commercial content linguistic analysis usage creation, that
widespread usage is considered in [10-12].
As the vast majority of HEIs today can be considered labor-intensive and human
organizations, information systems architectures as important tools for supporting
several different institutional educational processes and providing users with relevant
data are discussed in [13-15].
The reference model for higher education institutions towards a unified infor-
mation system is described in [16-17] and aims to integrate mixed information sys-
tems and applications for the effective and competitive existence of HEIs in the edu-
cational services market.
But, none of the research areas examines the architecture of the computer-linguistic
processing system of the specialized communities’ educational content for the pur-
pose of predicting and create a high-quality contingent of university students and for
making management decisions taking into account the motivational intentions of po-
tential entrants.
The procedures of computer-linguistic processing of specialized web communities’
content for planning the provision of educational services of HEI [18-20] are rather
cumbersome and require sufficiently large computational actions. Therefore, their
practical application required the creation of an appropriate system of computer-
linguistic processing of content.
The main functions of such a system are the collection, processing, creation of re-
actions and preservation of results (dictionary of motivational intentions), but also the
continuous monitoring and analysis of the quality of the educational web-
communities’ content.
This is due to changes in the entry campaign rules and requirements for entry into
the HEI, which are the key to planning the provision of high quality HEIs educational
services.
3 Architecture of Information System for Computer-
Linguistic Processing of Educational Content for
Predicting Higher Education Students
Prediction and formation of high-quality students’ contingent of higher education
institution is directly connected with consumers of educational services [2].
Therefore, consideration of their motivational intentions and the formation of reac-
tions by the HEI is a prerequisite for the architecture of the computer-linguistic pro-
cessing system of educational information content.
The architecture of the information system for computer-linguistic processing of
educational information content, which takes into account the motivational intentions
of educational services consumers, generates appropriate reactions from them by HEI
and conducts constant monitoring and analysis of the quality of information content
of educational communities is presented in Fig. 1.
The peculiarity of such a complex information system for automated computer-
linguistic processing of information content is its functioning at three architectural
levels:
1. the level of local information system;
2. the level of information processing agents;
3. the level of external information services and resources.
At the first level, work is done with information content within the local infor-
mation system, which provides:
formation of the necessary elements of educational information content;
identification of indicative features;
monitoring the quality of the content and the vocabulary of motivational intentions;
specifying selection options relevant to the entry campaign period, thematic dis-
cussions and posts.
Fig. 1. Architecture of information system for computer-linguistic processing of educational
content
At the second level, there are software agents of information processing which are
intended for:
selection of relevant educational discussions;
keeping thematic posts;
detecting users' motivational intent in posts;
matching the keywords of the entry campaign period with the identified motiva-
tional intentions;
retention of motivated intentions;
dictionary of the motivational intentions database formation.
selection of HEI reactions to identified motivational intentions
At the third level, external information services and resources are used to process the
information content:
Web-resource search services (search engines);
open Web-resources that serve as sources of educational information for content.
4 Functional structure of the automatic content
processing system for specialized educational web-
communities
Functional structure of the automatic content processing system of specialized educa-
tional communities is based on the architecture of a complex information system of
automated computer-linguistic information content processing.
The context diagram of a complex information system for automatic processing of
specialized educational communities information content is presented in Fig. 2.
Database of HEI Reactions
Processing Content of
Open Web- Dictionary of Motivational
Specialize Educational Web-
Resources Intentions
Communities
The Keyword Database of Entry
Campaign Period
Expert
Fig. 2. The context diagram of a complex information system for automatic processing of
specialized educational communities information content
Chart data streams of the complex information system for automated processing of
information of specialized educational web-communities’ content is presented in
Fig.3. It highlights the following features:
1. agent of selection relevant discussions;
2. agent of motivational intentions selection;
3. processing of motivational intentions;
4. HEI reactions;
5. monitoring the quality of educational information content.
The agent for selection of relevant discussions consists of the following functions:
keyword formation in relation to the periods of the entry campaign;
checking the relevance of the thematic discussion;
defining topical thematic discussions regarding the entry campaign periods.
1. Agent of Selection Depository of Thematic Posts
Open Web- Relevant Discussions
Resources
2. Agent of Depository of Indicative Signs
Motivational Intentions
Selection
3. Processing of
Expert
Motivational Intentions
4. HEI Reactions Database of HEI Reactions
5. Quality Monitoring of
Educational
Information Content
Fig. 3. Chart data streams of the complex information system for automated processing of
information of specialized educational web-communities’ content
Agent of motivational intention selection based on the motivational intention selec-
tion algorithm [20] contains the following functions:
identifying indicative signs of motivational intent in the posts;
matching indicative features to keywords;
maintaining motivation.
Considering the algorithm of selection of motivational intentions from thematic posts
of specialized web-communities, Processing of Motivational Intentions contains the
following functions:
setting indicative features;
reviewing educational content;
assessment of the importance of the identified motivational intentions;
export of motivational intentions.
The HEI reactions, which are the result of the algorithm of formation of the dictionary
of motivational intentions concerning a certain period of the entry campaign [21] and
the previous experience of the HEI reactions to certain situations according to the
identified motivational intentions and the period of the entry campaign, have the fol-
lowing functions:
formation of the HEI reactions;
reviewing the HEI reactions;
evaluation of results;
modernization of HEI reactions.
Quality monitoring of educational content is based on the indicators of quality of
educational content, based on the criteria [21].
Quality monitoring of educational content contains the following features:
analysis of plural keywords;
analysis of plural motivational intentions;
analysis of the relevance content;
analysis of the assistance level of HEI reactions;
analysis of the deficiencies.
5 Results
Since the architecture of the computer-linguistic processing system of web-
communities’ educational content takes into account motivational intentions consum-
ers of educational services and generates appropriate reactions from the HEI, informa-
tive indicators of this system are the speed of HEI reactions in the process of commu-
nicative activity and analysis of enrollment of potential entrants.
According to the results of the analysis of educational web-forum for entrants
communication activity and relevant thematic groups in social networks of Lviv Poly-
technic National University, the reaction time indicator decreased by 20% - 40% de-
pending on the period of the entry campaign (Fig. 4), and, on average, 30% for the
2016/2019 introductory campaigns (Fig. 5).
14
I period
12
II period
10
III period
Time of reaction
8 IV period
6 V period
4
2
0
2016/2017 2017/2018 2018/2019
Fig. 4. Dynamics of the reaction time by HEI in relation to the periods of entry campaign for
the 2016/2019 entry campaigns
60
50
Time of reaction
40
30
20
10
0
2016/2017 2017/2018 2018/2019 Entry Campaign
Fig. 5. Dynamics of the reaction time by HEI for the 2016/2019 entry campaigns
The analysis of the information system work shows the positive dynamics of
change in the number of enrolled students for 2016/2019 to the Lviv Polytechnic Na-
tional University, by an average of 3%.
4450
4400
4350
4300
Number of enrolled students
4250
4200
4150
4100
4050
4000
2017 2018 2019 Years of the entry
Fig. 6. Dynamics of change in the number of enrolled students for the 2016/2018 entry
campaigns
6 Conclusion
Therefore, this article develops the architecture of the computer-linguistic processing
system of web-communities’ educational content to plan effectively the provision of
educational services and to make management decisions by the HEI during the entry
campaign based on the procedures for selecting motivational intentions of potential
entrants indicators of the quality of the content of educational web-communities ,
which in practice allowed to establish a system of maintaining the relevance and cor-
rectness of educational information the content of educational web-communities and
official web-resources of higher education institutions with the ability to properly
support the quality of information content. The analysis of the results of the commu-
nication activities of the consumers of educational services in specialized web-
communities showed a decrease in the time for a response by HEI to the identified
motivational intentions of potential entrants, as well as the positive dynamics of actu-
ally enrolled entrance in relation to the entry campaigns in recent years for the HEI.
References
1. Pucciarelli, F, Kaplan, A.: Competition and strategy in higher education: Managing com-
plexity and uncertainty. Business Horizons 59, 311–320 (2016).
2. Mikhno, N., Sorokina, L.: Trend analysis of the educational choice of university entrants
as tool to improve the quality of educational service. International Journal of Information
and Communication Technologies in Education 6(3), 36-39 (2017).
3. Xuemina, Zh., Zhimingb, S., Pinga, G.: The Process of Information Systems Architecture
Development. In Proceedings of the International Workshop on Information and Electron-
ics Engineering (IWIEE) Procedia Engineering, 775 – 779 (2012).
4. Abel, R., Brown, M, Suess, J.: A New Architecture for Learning. Educause Review 48,
88–102 (2013).
5. Xiaohai, L., Yafei, T.: Architecture Framework and its Design Method. Fire Control
& Command Control 1, 6-8 (2010).
6. Prayitno, T.: Planning of Higher Education Information Technology Strategy Using
TOGAF. Indonesian Journal of Information Systems 2(1). 67-79 (2019).
7. Luftman, J. N., Lewis, P.R., Oldach, S.H.: Transforming the enterprise: The alignment of
business and information technology strategies, IBM System Journal 32(1), 198–
221(2010).
8. Mardiana, Araki, K.: EA-MDA Model to Resolve is Characteristic Problems in Education-
al Institutions. International Journal of Software Engineering & Applications 4(3), 1–20
(2013).
9. Kanishcheva, O., Vysotska, V., Chyrun, L., Gozhyj, A.: Method of integration and content
management of the information resources network. Advances in Intelligent Systems and
Computing 689, 204-216. Springer (2018).
10. Vysotska, V.: Linguistic analysis of textual commercial content for information resources
processing. Modern Problems of Radio Engineering, Telecommunications and Computer
Science. Proceedings of the 13th International Conference on TCSET 2016, Art No.
7452160, pp. 709-713 (2016).
11. Su, J., Vysotska, V., Sachenko, A., Lytvyn, V., Burov, Y.: Information resources pro-
cessing using linguistic analysis of textual content. Proceedings of the 9th International
Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technolo-
gy and Applications, IDAACS 2017, Vol. 2, No. 8095038, 573-578 (2017).
12. Davydov, M., Lozynska, O.: Information system for translation into Ukrainian sign lan-
guage on mobile devices. Proceedings of the 12th International Scientific and Technical
Conference on Computer Sciences and Information Technologies, CSIT 2017, Vol. 1, Art
No. 8098734, pp. 48-51 (2017).
13. Bidan M, Rowe F, Truex D.: An empirical study of IS architectures in French SMEs: inte-
gration approaches. European Journal of Information Systems 21, 287–302 (2012).
14. Natek, S, Lesjak, D.: The process architecture of information systems - higher education
institution’s managerial tool. Issues Information Systems 1, 29– 34 (2010).
15. Natek, S, Lesjak, D.: Integrated Higher Education Information systems - Professors’
knowledge management tools. Issues Information Systems 12, 80–86 (2011).
16. Sanchez-Puchola, F., Pastor-Colladoa J. A., Borrell, B.: Towards an Unified Information
Systems Reference Model for Higher Education Institutions. Procedia of computer science
121, 542-553 (2017).
17. Charles Sturt University. Higher Education Process Reference Model. Charles Sturt Uni-
versity. Work Process Improvement (2010). [Electronic resource] Available at:
http://www.csu.edu.au/special/wpp/resources/reference-model
18. Zhezhnych, P., Shilinh, A., Melnyk, V.: Linguistic analysis of user motivations of infor-
mation content for university entrant’s web-forum. International Journal of Computing
18(1), 67-74 (2019).
19. Shilinh, A., Zhezhnych, P.: Linguistic approaches to the planning of educational services
in higher education institution. ECONTECHMOD 7(4), 13-20 (2018).
20. Zhezhnych, P., Shilinh, A., Tkachuk, V.: Computer-linguistic Selection of Potential En-
trances' Motivation Intentions from Posts of Education Web-Community. In Proceedings
of the 1st International Workshop on Control, Optimization and Analytical Processing of
Social Networks (COAPSN-2019), pp.134146. Lviv (2019).
21. Systems and software engineering. Systems and software Quality Requirements and Eval-
uation (SQuaRE). System and software quality models. ISO/IEC 25010.2:2008. Mode of
access: http://sa.inceptum.eu/sites/sa.inceptum.eu/ files/Content/ISO_25010.pdf. (2008).
22. Trach, O., Fedushko, S. Determination of measures of counteraction to the social-oriented
risks of virtual community life cycle organization (2020) Advances in Intelligent Systems
and Computing, 1080 AISC, pp. 680-695. DOI: 10.1007/978-3-030-33695-0_46
23. Fedushko, S., Kolos, S., Malynovska, Y. MBTI principles in detecting emotional manipu-
lators among digital platforms users (2019) CEUR Workshop Proceedings, 2588, .
24. Fedushko, S., Syerov, Y., Kolos, S. Hashtag as а way of archiving and distributing infor-
mation on the internet (2019) CEUR Workshop Proceedings, 2386, pp. 274-286.
25. Mastykash, O., Peleshchyshyn, A., Fedushko, S.,Trach, O. and Syerov, Y.: Internet Social
Environmental Platforms Data Representation. 13th International Scientific and Technical
Conference on Computer Sciences and Information Technologies (CSIT), Lviv, Ukraine,
2018, pp. 199-202. doi: 10.1109/STC-CSIT.2018.8526586
26. Syerov Yu., Fedushko S., Loboda Z.: Determination of Development Scenarios of the Ed-
ucational Web Forum. Proceedings of the XIth International Scientific and Technical Con-
ference (CSIT 2016), pp. 73-76. Lviv (2016).
27. Mastykash O., Peleshchyshyn A., Fedushko S., Trach O., Syerov Y.: Internet Social Envi-
ronmental Platforms Data Representation, IEEE 13th International Scientific and Tech-
nical Conference on Computer Sciences and Information Technologies (CSIT), pp. 199-
202. Lviv, Ukraine (2018).
28. Korobiichuk I., Syerov Y., Fedushko S.: The method of semantic structuring of virtual
community content. Advances in Intelligent Systems and Computing, vol. 1044, pp. 11-18
(2020).
29. Korobiichuk I., Fedushko S., Juś A., Syerov Y.: Methods of Determining Information
Support of Web Community User Personal Data Verification System. In: Szewczyk R.,
Zieliński C., Kaliczyńska M. (eds) Automation 2017. ICA 2017. Advances in Intelligent
Systems and Computing, vol. 550, pp. 144-150. Springer (2017).
30. Korzh R., Peleschyshyn A., Syerov Yu., Fedushko S.: Principles of University’s Infor-
mation Image Protection from Aggression. Proceedings of the XIth International Scientific
and Technical Conference (CSIT 2016), pp. 77-79. Lviv, Ukraine (2016).