=Paper=
{{Paper
|id=Vol-2879/paper22
|storemode=property
|title=Approaches to the choice of tools for adaptive learning based on highlighted selection criteria
|pdfUrl=https://ceur-ws.org/Vol-2879/paper22.pdf
|volume=Vol-2879
|authors=Yaroslava B. Sikora,Olena Yu. Usata,Oleksandr O. Mosiiuk,Dmytrii S. Verbivskyi,Ekaterina O. Shmeltser
}}
==Approaches to the choice of tools for adaptive learning based on highlighted selection criteria==
https://ceur-ws.org/Vol-2879/paper22.pdf
Approaches to the choice of tools for adaptive
learning based on highlighted selection criteria
Yaroslava B. Sikora, Olena Yu. Usata, Oleksandr O. Mosiiuk, Dmytrii S. Verbivskyi1
and Ekaterina O. Shmeltser2
1
Zhytomyr Ivan Franko State University, 40 Velyka Berdychivska Str., Zhytomyr, 10008, Ukraine
2
State University of Economics and Technology, 5, Stepana Tilhy Str., Kryvyi Rih, 50006, Ukraine
Abstract
The article substantiates the relevance of adaptive learning of students in the modern information
society, reveals the essence of such concepts as “adaptability” and “adaptive learning system”. It is
determined that a necessary condition for adaptive education is the criterion of an adaptive learning
environment that provides opportunities for advanced education, development of key competencies,
formation of a flexible personality that is able to respond to different changes, effectively solve different
problems and achieve results. The authors focus on the technical aspect of adaptive learning. Different
classifications of adaptability are analyzed. The approach to the choice of adaptive learning tools based
on the characteristics of the product quality model stated by the standard ISO / IEC 25010 is described.
The following criteria for the selecting adaptive learning tools are functional compliance, compatibility,
practicality, and support. By means of expert assessment method there were identified and selected the
most important tools of adaptive learning, namely: Acrobatiq, Fishtree, Knewton (now Wiliy), Lumen,
Realize it, Smart Sparrow (now Pearson). Comparative tables for each of the selected tools of adaptive
learning according to the indicators of certain criteria are given.
Keywords
adaptability, adaptive learning, adaptive learning tools, selection criteria
1. Introduction
The main trends in global online education are related to the development of computer technol-
ogy and increase of diversity and accessibility of education. Information and communication
technologies, in particular learning management systems (LMS), serve as a means of improving
the effectiveness of learning, its individualization and differentiation. LMS provides access
to data and tools to support the learning process, accumulates information about the courses
taken by students and the results of final tests [1, 2, 3, 4, 5, 6, 7, 8]. However, the effectiveness
of such systems usually depends on the adaptive capabilities of the educational process with
consideration of psychological characteristics of students and subject area. However, sometimes
educational content is quite simple for more prepared students, and for less prepared it can be
CTE 2020: 8th Workshop on Cloud Technologies in Education, December 18, 2020, Kryvyi Rih, Ukraine
" iaroslava.sikora@gmail.com (Y. B. Sikora); o.y.usata@gmail.com (O. Yu. Usata); mosxandrwork@gmail.com
(O. O. Mosiiuk); d_verbovskiy@ukr.net (D. S. Verbivskyi); shmelka0402@gmail.com (E. O. Shmeltser)
0000-0003-2621-6638 (Y. B. Sikora); 0000-0002-0610-7007 (O. Yu. Usata); 0000-0003-3530-1359 (O. O. Mosiiuk);
0000-0002-5238-1189 (D. S. Verbivskyi); 0000-0001-6830-8747 (E. O. Shmeltser)
© 2020 Copyright for this paper by its authors.
Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
CEUR
Workshop
Proceedings
http://ceur-ws.org
ISSN 1613-0073
CEUR Workshop Proceedings (CEUR-WS.org)
398
almost inaccessible. On the other hand, most LMSs provide ample configurable capabilities, but
adaptability has not been a priority in the architecture of such systems.
The main approach to solving this problem is the use of adaptive learning tools as one of the
promising areas in modern education.
Philosophers, educators and psychologists have paid attention to the problem of adaptive
learning. In particular, the experience of Ukrainian researchers is relevant in the context of
consideration of adaptive learning systems based on programming, algorithmization and use of
web technologies [9, 10].
Pavlo I. Fedoruk considers the problems of theory, methodology and techniques and con-
struction of intelligent adaptive systems of individual distance learning on the basis of the latest
Web-technologies [11]. Igor V. Gritsuk devoted his work to adaptive testing in educational
electronic environment of maritime higher education institutions [12]. Functioning peculiarities
of intellectual adaptive educational systems were investigated by Andrii M. Striuk [13, 14].
Adaptive learning on the basis of modern information technologies is considered by Viacheslav
V. Osadchyi [15]. Approaches to the introduction of cloud adaptive technologies in teacher
training are explored by Yuliia H. Nosenko [16, 17].
Noteworthy are the studies [18, 19, 20], which present the results of scientific publications for
2010–2020, on the problems of personalized and adaptive learning and analyzed the ergonomic
indicators of training courses and their compliance with the principles of educational design in
adaptive learning systems. A number of researchers [17, 21] conducted a comparative analysis of
adaptive learning systems according to the scope, type of adaptive learning, functional purpose,
integration with existing learning management systems, application of modern technologies
for generation and recognition of natural language and curriculum characteristics.
The scheme of designing an adaptive learning system can be found in the work of Chang
Ming Liu, Yan Jun Sun and Hai Yu Li [22], which describe computer learning platforms.
E-learning systems that provide personalized content to users with the gradual adaptation of
educational material based on the results of student progress are considered by Ana-Maria Mirea
and Mircea Cezar Preda. They provide different types of adaptation that take into account the
content and navigation in the course, explore the student’s profile and model learning activities
[23]. In [24] it is proposed to use intelligent methods for automatic adaptation to dynamic
changes in student behavior in real time during learning.
The effectiveness of the use of adapted online training courses depends on the feedback, on
the current learning outcomes of the proposed content [25, 26, 14]. Andrew Thomas Bimba,
Norisma Idris, Ahmed Al-Hunaiyyan, Rohana Binti Mahmud and Nor Liyana Bt Mohd Shuib
considers different feedback options in an adapted educational environment based on dialogue,
intelligent e-learning systems and adaptive hypermedia systems [27].
Thus, nowadays the development of technologies for adaptive learning occurs in different
forms and contexts. The share of adaptive learning technologies in higher education in Ukraine
is small. In our opinion, technical solutions in the field of adaptive learning that would allow to
implement it are not fully studied.
The purpose of the article is to highlight the approaches to the choice of adaptive learning
tools based on the selected criteria and indicators of its selection.
399
2. Theoretical fundamentals
Adaptability is interpreted as the possibility of adaptation, coordination of the learning process,
taking into account the choice of learning pace, diagnosis of the achieved level of mastering
the material, providing the widest range of different learning tools that would make it suitable
for a wider range of users [28]. Adaptive learning system able to adapt to human, age and
psychological characteristics, in addition, adaptive training should consider and agree with the
general stage changes which experience the knowledge and ways of cognitive actions of students
during their studies. Given this, adaptive learning is a dialectical unity of two processes: a child’s
adaptation to learning and adaption of learning to the individual characteristics of the child and
provides for adaptation to modern time requirements of all the elements of pedagogical systems:
objectives; content; methods, ways, means of learning; forms of organization of cognitive
activity of students, diagnostics of results.
According to [29], adaptive learning system is a new model of learning organization, which
is characterized mainly active independent activity of students, which is controlled by curricula
and control programs, network plans and self-accounting schedules.
Adaptive learning is that an individualized learning method will help the student learn faster,
more effectively and with greater understanding. Typically, components of adaptive learning
include: monitoring activity, interpretation of results, understanding of the requirements and
benefits of learning new topics to facilitate the learning process. The main purpose of adaptive
learning is to make the learning process most effective by transferring the educational process
to the electronic environment [30].
In modern information educational systems, the problem of adaptive learning is considered
in two aspects: methodological and technical. The methodological aspects of adaptive learning
in information training systems include planning and organization of the educational process,
determination of the types of tasks, their levels of complexity, the sequence of submission of
material, conduction of various types of control, definition of evaluation criteria for each type
of task. The technical aspects include: an algorithm that offers to move to a new level with the
correct execution of most of the tasks or return to the previous level, taking into account errors
made during the tasks; algorithm for assessing student achievement, etc. [31].
Let’s dwell in more detail on the technical aspect.
The origins of adaptive learning are the first software algorithms of B. F. Skinner, Norman A.
Crowder and Gordon Pask, which were used in 1950-1960.
Skinner’s algorithm assumed that the training material should be divided into small fragments,
the answers should be taken in an open form and all participants in the learning process take
the same course regardless of individual characteristics [32]. This approach has been called
a linear algorithm. Another approach was suggested by Norman A. Crowder, according to
which the teaching material should be presented in the form of more complex tasks, which
are broken down into smaller ones in case one of the students cannot complete the initial
one. Unlike Skinner’s concept, Crowder suggested a closed form for receiving answers (choose
the correct option out of the offered), feedback appears (after answering the question, the
program explains why the answer was correct or where a mistake was made). But the most
significant is the emergence of individual learning trajectories [33]. This approach is called
branched. The concept of adaptive learning, laid down by Gordon Pask, has become widespread.
400
According to the concept, curriculum must be constantly adapted to a person who interacts with
it, adjust course, maintaining the optimal level of complexity [34]. In modern interpretations of
adaptability, one can find examples of linear, branched and adaptive algorithms. The latter was
the most widely used in computer training systems.
Currently, the e-learning market has enough systems that use the term “adaptive learning” in
the description of their product. In order to individualize learning, they actively develop adaptive
learning tools – technologies that interact with the student in real time. They automatically
provide individual support to each student.
To study the existing adaptive learning systems, consider the existing classifications given in
studies [35, 36, 37, 38], and describe how adaptability is implemented in such systems.
Depending on the complexity of the curriculum , there are three levels of adaptive learning
systems: systems that provide “passive”, “active” and “intellectual” adaptability [35].
Systems that provide “passive adaptability”: the active role is delegated to the student: based
on the recommended set of parameters, the student, based on their own interests, plans the
trajectory of their progress in the material, the timing of the study of content. Such systems use
passive schemes ‘if ..., → then ...”, simple hypertext systems.
Systems that provide “active adaptability”: the system itself determines the trajectory of his
further study on the basis of already completed educational material and on the basis of the
student’s answers to test questions. In such systems active schemes “if ..., → then ...” are used,
programming is applied.
Systems that provide “intellectual adaptability”: a student profile is formed on the basis of
both psychological characteristics and personal preferences, which is constantly expanding.
Based on it, a trajectory of progress in the assimilation of content is created. Such systems use
programming methods based on the use of big data analytics in the field of learning – Learning
Analytics [39].
Lou Pugliese [36] divided adaptive systems into four types: machine learning systems,
advanced algorithm systems, rule-based systems, and decision tree systems. Others classify
systems based on a basic adaptive algorithm [37]. However, one particular adaptive algorithm
is rarely identified with a single system.
EdSurge [38] determined that adaptivity can occur in one or more elements: content, assess-
ment, sequence.
Tools with adaptive content allow you to identify material that the student does not under-
stand or misunderstands and get tips, corrections and links to useful resources.
Content is “adapted” to the student within one skill, which, at the same time, is divided into
components. That is, the student learns one component, then moves on to another – as a result,
acquires a full-fledged skill. In this case, the teacher in real time can receive information about
how fast the student is moving, at what stage he is and where he needs help.
Adaptation of assessment assumes that each subsequent question depends on what answer
the student gave to the previous one. The better it is, the more difficult the tasks, and vice versa
– if it is difficult for the student to complete, the questions will be easier until he learns the
material.
Traditionally, assessments are made in two ways: fixed form or adaptive. Fixed form assess-
ment is one in which the elements are pre-selected, and each student is tested on the same set
of questions (for example, the final exam). In adaptive assessment, elements change based on
401
how individual students answer each question. This change is often the result of the level of
complexity of the element. For example, if a student answers a simple question correctly, the
next received option is a little harder, etc.
Adaptive assessment tools are usually used for periodic monitoring every few months. Stu-
dents receive a relatively voluminous test task, the purpose of which is to check how well they
have mastered the material in 2–4 months. After monitoring, data analysis is performed, and
the results are used to further adjust the program and individual learning trajectory of each
student. Therefore, one of the advantages of adaptive tests is detailed statistics.
Continuous data collection and analysis are inherent in sequence adaptation. That is, while
the student completes the task, the adaptive program analyzes his answers and automatically
selects the relevant content, level of complexity and order of learning the material. Adaptive
sequence tools are the most complex, as they both analyze data and compose and adjust the
student’s individual trajectory in real time.
To make an individual learning trajectory, adaptive programs take into account many different
indicators: the correctness of the answer; number of attempts; use of additional tools or
resources; student interests.
Sometimes these tools take into account the social reaction to the student (comments and
likes) and even his mood.
The adaptive sequence is implemented in three stages: to collect data, analyze it and adapt
the sequence of presentation of material to the needs of a particular student.
The main advantage of a learning tool with an adaptive sequence is to fill gaps in knowledge.
If a student misses a lesson or has not mastered the topic before, and now it interferes with the
study of new material, the sequence of tasks and topics changes. Thus, student fills the gap in
knowledge first, and then moves on to the current topic.
The adaptive sequence is used by Knewton, Fishtree, BrightspaceLeap.
Some developers of adaptive learning tools use several strategies at once. For example, the
tools Aleks, ScootPad, SmartBook combine adaptive evaluation and consistency. Adaptation
of both content and evaluation is carried out by I-Ready, Fulcrum labs, Mastering CogBooks,
Mathspace, Smart Sparrow combine adaptive content and consistency.
It is worth noting the study of the evolution of the market of adaptive learning “Learning to
adapt 2.0” [40], which analyzes the adaptive learning technologies for the following opportunities
(features):
• content source (OER, developer content, customer-generated content),
• technical support services,
• opportunities for communication and cooperation between participants in the learning
process,
• adjustment functions (for example, teachers can set a scale for evaluating technology or
indicators).
These classifications will be useful for understanding how technology can collect data and
adjust adaptability. These technologies will be most effective if they are combined in one tool.
402
3. Results
In order to determine the most important tools of adaptive learning, the method of expert eval-
uation was used. The examination involved 20 people among teachers, teachers of educational
institutions who have experience and research the implementation of elements of personaliza-
tion of e-learning and understand the prospects for its use in the educational process. To select
the tool of adaptive learning, a questionnaire was developed in which teachers distributed the
selected tools by assigning a rank number. The tool that can, according to the expert, implement
adaptive learning technologies as fully as possible (regardless of the discipline), was assigned
the rank 𝑁 = 14, the least – 1.
The concordance coefficient (𝑊 ) or coefficient of agreement is used to assess the objectivity
of the opinions of experts [41]:
12𝑆
𝑊 = , (1)
𝑚2 · (𝑛3 − 𝑛)
where 𝑆 is the sum of the squares of the deviations of the sums of ranks from the average value
of the sum of ranks for a given object of study (𝑅
¯ ).
Then
¯ = 1 · 𝑚 · (𝑛 − 1),
∑︁
𝑅 (2)
2
∑︁ ∑︁
𝑆= ( 𝑅𝑖 − 𝑅¯ )2 . (3)
where 𝑅𝑖 – ranks assigned to each tool by 𝑖-expert; 𝑚 – number of experts; 𝑛 – the number of
indicators.
After performing the calculation using formulas based on experimental data, we obtain
certain value 𝑊 . The coefficient of concordance varies in the range 0 < 𝑊 < 1, and at 𝑊 = 0
agreement of experts is absent, and at 𝑊 = 1 agreement is complete. If the value of concordance
coefficient exceeds 0.40–0.50, the quality of the assessment is considered satisfactory, if 𝑊 >
0.70 − 0.80 – high.
The significance of the concordance coefficient is checked using the statistical criteria 𝜒2 . It
is significant and differences in expert assessments are not significant if the inequality holds
𝑚 · (𝑛 − 1) · 𝑊 ≥ 𝜒2𝑐𝑟𝑖𝑡𝑖𝑐𝑎𝑙 𝑣𝑎𝑙𝑢𝑒 ( 𝛼 = 0.05).
The results of expert surveys are listed in table 1.
The value of the coefficient 𝑊 = 0.79. It indicates a strong consensus of experts. Let’s check
its significance by the criterion 𝜒2 : 210.6 ≥ 36.2 = 𝜒20.05 . Therefore, at a significance level of
0.05%, the calculated concordance coefficient is taken as significant.
As a result, 6 adaptive learning tools were chosen: Acrobatiq, Fishtree, Knewton (now Wiliy),
Lumen, Realize it, Smart Sparrow (now Pearson).
Taking into account the possibilities of adaptive learning technologies, we will formulate the
criteria for selecting an adaptive learning tool.
Under the criteria for selecting tools for adaptive learning we will understand the features
and properties of adaptive learning tools necessary for the holistic use of the learning process
and its successful operation.
403
Table 1
Ranking of adaptive learning tools
Smart Sparrow (now Pearson)
Open learning invitiative
Knewton (now Wiliy)
Brightspace by D2L
Fulcrum Labs
LearnSmart
CogBooks
Acrobatiq
Realize it
Drillster
Fishtree
Experts
Cerego
Lumen
Aleks
1. 11 10 2 3 4 1 5 9 13 6 8 7 12 14
2. 9 8 4 5 3 2 6 10 14 1 11 7 13 12
3. 12 9 3 6 2 5 4 8 11 1 14 7 10 13
4. 10 8 1 7 2 5 6 9 14 3 13 4 11 12
5. 12 11 4 8 1 3 9 10 14 2 6 5 7 13
6. 11 8 2 4 5 1 14 7 13 3 10 6 9 12
7. 9 8 1 3 5 2 12 7 10 4 11 6 13 14
8. 8 10 5 2 1 4 13 6 14 3 9 7 11 12
9. 10 6 1 2 3 5 13 8 12 4 9 7 11 14
10. 9 7 2 4 5 1 12 8 10 3 11 6 13 14
11. 12 4 1 6 5 3 14 9 11 2 8 7 10 13
12. 12 8 2 6 5 4 13 3 14 1 10 7 11 9
13. 10 8 1 5 4 2 11 6 7 3 13 9 12 14
14. 9 10 3 6 1 4 12 5 11 2 8 7 14 13
15. 11 7 4 12 2 1 8 5 9 3 10 6 14 13
16. 10 8 1 5 4 2 12 6 11 3 9 7 13 14
17. 10 8 4 7 1 3 13 5 12 2 9 6 11 14
18. 9 7 2 3 4 1 11 6 12 5 10 8 15 14
19. 9 7 1 4 5 2 12 6 14 3 10 8 11 13
20. 10 9 2 6 1 3 8 5 11 4 12 7 13 14
𝑅¯ 203 161 46 104 63 54 208 138 237 58 201 134 233 260
¯
𝑅𝑖 − 𝑅 53 11 -104 -46 -87 -96 58 -12 87 -92 51 -16 83 110
It should be noted that nowadays there are no complete and fairly detailed structured descrip-
tions of the characteristics of adaptive learning tools in Ukraine. There are also no scientifically
sound methodological approaches to the selection of such tools and evaluation of their quality.
One way to validate software properties is through certification. It is carried out on the basis of
current standards.
The most common is the international standard ISO/IEC 25010 [42], which defines two quality
models:
1) a quality model in use, consisting of five characteristics that relate to the results of product
interaction when used in a given context,
404
2) product quality model consisting of eight characteristics relating to the static properties of
the software and the dynamic properties of the computer system.
The analysis of the characteristics of the product quality model described by the ISO/IEC
25010 standard and the specific features inherent in the tools of adaptive learning, allowed to
identify the following selection criteria:
(i) functional compliance – the degree to which the system provides functions of adaptive
learning, which are implemented using this tool;
(ii) compatibility – the degree of ability of the adaptive learning tool to share information
with other products or systems;
(iii) practicality – the degree of applicability of the tool of adaptive learning by users to achieve
the goals with efficiency, effectiveness and satisfaction in a given context of use;
(iv) support – determines the quality of support for the tool of adaptive learning by developers.
Each of the criteria is disclosed (deepened) in the following indicators:
(i) • The “content adaptability” indicator suggests that content can be adjusted to student
knowledge.
• The indicator of “opportunities for joint work” involves the ability of students and /
or teachers to interact with each other in the learning process.
• “Socio-emotional state” indicator describes the use of the feedback and intervention
based on student’s socio-emotional state.
• The indicator “organization of knowledge assessment” characterizes the completeness
of the presented tools for the development of various certification units.
(ii) • The “LMS compatibility” indicator provides integration with known learning man-
agement systems (LMS).
• The “standard compliance” indicator determines the types of standards for exporting
the courses.
• The “cost” indicator is responsible for the availability of a free tariff plan (even with
limited functions).
(iii) • The “learning autonomy” indicator assumes that students can influence or expand
(deepen) learning based on their own choice.
• The “accessibility” indicator takes into account the needs of all potential users,
including those with disabilities.
• The indicator “support for different forms of learning” provides the opportunity to
organize learning with the tool of adaptive learning in various forms.
(iv) • The “setting” indicator suggests that teachers and course developers can change the
content of training or assessment.
• The “content source” indicator characterizes the full range of opportunities for
management and use of educational material.
• The “documentation” indicator characterizes the completeness and quality of docu-
mentation for the tool of adaptive learning.
405
Table 2
Criterion “functional compliance” and its indicators
Indexes Content adapt- Opportunities Socio- Socio- Manifestation
Adaptive ability for joint work emotional emotional of the criterion
learning tools state state
Acrobatiq 2.00 1.42 1.33 2.42 60%
Fishtree 1.50 1.33 1.08 2.08 50%
Knewton 2.25 2.58 1.58 2.33 73%
Lumen 2.17 2.75 2.25 2.67 82%
Realize it 2.33 1.92 1.67 2.58 71%
Smart Sparrow 2.83 2.17 2.67 2.58 85%
Table 3
Criterion “compatibility” and its indicators
Indexes Compatibility Standards com- Cost Manifestation
Adaptive with LMS pliance of the criterion
learning tools
Acrobatiq 2.42 2.67 1.17 69%
Fishtree 2.67 2.58 1.67 77%
Knewton 2.33 1.92 1.58 65%
Lumen 2.67 2.00 1.17 65%
Realize it 2.25 2.42 1.83 72%
Smart Sparrow 2.42 2.50 2.17 79%
Table 4
Criterion “practicality” and its indicators
Indexes Learning auton- Accessibility Support of var- Manifestation
Adaptive omy ious learning of the criterion
learning tools forms
Acrobatiq 1.58 2.50 2.58 74%
Fishtree 1.67 1.75 1.92 59%
Knewton 2.00 2.50 2.75 81%
Lumen 2.42 2.67 2.58 85%
Realize it 2.42 2.58 2.67 85%
Smart Sparrow 2.75 2.67 2.33 86%
Another group of experts (12 people) was involved in the selection of the most important
tools for adaptive learning. Manifestation of each criterion was determined by the assessment of
its indicators: 0 points – the indicator was not met; 1 point – the indicator is no longer observed
than it is observed; 2 points – the indicator is more adhered to than not adhered to; 3 points –
the indicator is fully complied with. In addition, the indicator was considered positive if the
value of the corresponding coefficient – the arithmetic value of its parameters – was not less
than 1.5.
406
Table 5
Criterion “support” and its indicators
Indexes Settings Content source Documentation Manifestation
Adaptive of the criterion
learning tools
Acrobatiq 2.25 2.50 1.42 69%
Fishtree 1.58 2.42 1.50 61%
Knewton 2.42 2.50 2.00 77%
Lumen 2.50 2.58 1.75 76%
Realize it 1.75 2.58 2.25 73%
Smart Sparrow 2.67 2.50 2.33 83%
The criterion was considered insufficiently manifested if less than 50% of its indicators were
positive; critical manifestation of the criterion – 50–55%; sufficient manifestation – 56–75%;
high manifestation – 76–100%.
Consider in more detail the results of each of the tools of adaptive learning. Tables 2–5 show
the indicators of the defined criteria for each of the selected tools of adaptive learning.
Thus, according to the research, among the suggested tools of adaptive learning Smart
Sparrow (now Pearson) and Lumen meet the most relevant criteria.
4. Conclusions and prospects of further research
The results of the study showed the importance of adaptive learning in the organization of the
educational process, as it ensures the coordination of the learning process, taking into account
the pace of learning, diagnosing the achieved level of mastery, providing the widest range of
different learning tools, which would make it suitable for a wider audience.
The use of adaptive learning in higher education is a new area for learning. An important
aspect is the choice of adaptive learning tool.Analysis of the characteristics of the product
quality model described by ISO/IEC 25010, and specific features inherent in adaptive learning
tools, allowed to identify and describe the criteria and indicators that should be followed when
selecting adaptive learning tools: functional compliance; compatibility; practicality and support.
According to the results of the study of adaptive learning tools according to these criteria, we
can conclude that Smart Sparrow (now Pearson) and Lumen are best implemented the ability to
show adaptability.
Prospects for further research are in-depth analysis and research of methodological aspects
of adaptive learning, as well as the development of guidelines for the use of certain criteria for
the selection of tools for adaptive learning.
References
[1] V. Ustinova, S. Shokaliuk, I. Mintii, A. Pikilnyak, Modern techniques of organizing computer
support for future teachers’ independent work in German language, CEUR Workshop
407
Proceedings 2433 (2019) 308–321.
[2] S. Shokaliuk, Y. Bohunenko, I. Lovianova, M. Shyshkina, Technologies of distance learning
for programming basics on the principles of integrated development of key competences,
CEUR Workshop Proceedings 2643 (2020) 548–562.
[3] I. Mintii, S. Shokaliuk, T. Vakaliuk, M. Mintii, V. Soloviev, Import test questions into
Moodle LMS, CEUR Workshop Proceedings 2433 (2019) 529–540.
[4] I. Mintii, Using Learning Content Management System Moodle in Kryvyi Rih State
Pedagogical University educational process, CEUR Workshop Proceedings 2643 (2020)
293–305.
[5] A. Abdula, H. Baluta, N. Kozachenko, D. Kassim, Peculiarities of using of the Moodle test
tools in philosophy teaching, CEUR Workshop Proceedings 2643 (2020) 306–320.
[6] M. Syvyi, O. Mazbayev, O. Varakuta, N. Panteleeva, O. Bondarenko, Distance learning as
innovation technology of school geographical education, CEUR Workshop Proceedings
2731 (2020) 369–382.
[7] K. Polhun, T. Kramarenko, M. Maloivan, A. Tomilina, Shift from blended learn-
ing to distance one during the lockdown period using Moodle: test control of stu-
dents’ academic achievement and analysis of its results, Journal of Physics: Confer-
ence Series 1840 (2021) 012053. URL: https://doi.org/10.1088/1742-6596/1840/1/012053.
doi:10.1088/1742-6596/1840/1/012053.
[8] V. Tkachuk, Y. Yechkalo, S. Semerikov, M. Kislova, Y. Hladyr, Using Mobile ICT for On-
line Learning During COVID-19 Lockdown, in: A. Bollin, V. Ermolayev, H. C. Mayr,
M. Nikitchenko, A. Spivakovsky, M. Tkachuk, V. Yakovyna, G. Zholtkevych (Eds.), Informa-
tion and Communication Technologies in Education, Research, and Industrial Applications,
Springer International Publishing, Cham, 2021, pp. 46–67.
[9] O. Haranin, N. Moiseienko, Adaptive artificial intelligence in RPG-game on the Unity
game engine, CEUR Workshop Proceedings 2292 (2018) 143–150.
[10] M. Petrova, M. Mintii, S. Semerikov, N. Volkova, Development of adaptive educational
software on the topic of “Fractional Numbers” for students in grade 5, CEUR Workshop
Proceedings 2292 (2018) 162–192.
[11] P. Fedoruk, Technology for construction of individual learning trajectory using knowledge
script examples in adaptive systems of distance learning, Cambridge, 2011, pp. 88–92.
doi:10.2316/P.2011.734-021.
[12] O. S. Diahyleva, I. V. Gritsuk, O. Y. Kononova, A. Y. Yurzhenko, Computerized adaptive
testing in educational electronic environment of maritime higher education institutions,
CEUR Workshop Proceedings (2020, in press).
[13] Y. Tyshchenko, A. Striuk, The relevance of developing a model of adaptive learning, CEUR
Workshop Proceedings 2292 (2018) 109–115.
[14] N. Shapovalova, O. Rybalchenko, I. Dotsenko, S. Bilashenko, A. Striuk, L. Saitgareev,
Adaptive testing model as the method of quality knowledge control individualizing, CEUR
Workshop Proceedings 2393 (2019) 984–999.
[15] V. Osadchyi, I. Krasheninnik, O. Spirin, S. Koniukhov, T. Diuzhikova, Personalized and
adaptive ICT-enhanced learning: a brief review of research from 2010 to 2019, in: CEUR
Workshop Proceedings, volume 2732, 2020, pp. 559–571. URL: http://ceur-ws.org/Vol-2732/
20200559.pdf.
408
[16] M. Marienko, Y. Nosenko, A. Sukhikh, V. Tataurov, M. Shyshkina, Personalization of
learning through adaptive technologies in the context of sustainable development of
teachers’ education, E3S Web of Conferences 166 (2020) 10015. doi:10.1051/e3sconf/
202016610015.
[17] Y. Nosenko, M. Popel, M. Shyshkina, The state of the art and perspectives of using adaptive
cloud-based learning systems in higher education pedagogical institutions (the scope of
ukraine), CEUR Workshop Proceedings 2433 (2019) 173–183. URL: http://ceur-ws.org/
Vol-2433/paper10.pdf, 6th Workshop on Cloud Technologies in Education, CTE 2018 ;
Conference Date: 21 December 2018.
[18] H. Chemerys, K. Osadcha, V. Osadchyi, I. Naumuk, H. Ustiuhova, Analysis of ergonomic
indicators and compliance with the principles of the instructional design of education
courses in adaptive learning systems, CEUR Workshop Proceedings 2732 (2020) 619–633.
URL: http://ceur-ws.org/Vol-2732/20200619.pdf.
[19] K. Osadcha, V. Osadchyi, S. Semerikov, H. Chemerys, A. Chorna, The review of the adaptive
learning systems for the formation of individual educational trajectory, CEUR Workshop
Proceedings 2732 (2020) 547–558. URL: http://ceur-ws.org/Vol-2732/20200547.pdf.
[20] V. Osadchyi, H. Chemerys, K. Osadcha, V. Kruhlyk, S. Koniukhov, A. Kiv, Conceptual
model of learning based on the combined capabilities of augmented and virtual reality
technologies with adaptive learning systems, CEUR Workshop Proceedings 2731 (2020)
328–340.
[21] N. Morze, L. Varchenko-Trotsenko, T. Terletska, E. Smyrnova-Trybulska, Implementation
of adaptive learning at higher education institutions by means of Moodle LMS, Journal of
Physics: Conference Series 1840 (2021) 012062. URL: https://doi.org/10.1088/1742-6596/
1840/1/012062. doi:10.1088/1742-6596/1840/1/012062.
[22] C. M. Liu, Y. J. Sun, H. Y. Li, Adaptive learning system designed and learning program
optimization algorithm, in: Applied Mechanics and Materials, volume 347, Trans Tech
Publ, 2013, pp. 3114–3118. doi:10.4028/www.scientific.net/amm.347-350.3114.
[23] A.-M. Mirea, M. C. Preda, Adaptive learning based on exercises fitness degree, in: 2009
IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent
Technology, volume 3, IEEE, 2009, pp. 215–218. doi:10.1109/WI-IAT.2009.266.
[24] E.-N. El Mokhtar, Z. Abdelhamid, et al., Hybrid approach of the fuzzy c-means and the
k-nearest neighbors methods during the retrieve phase of dynamic case based reasoning
for personalized follow-up of learners in real time, International Journal of Electrical and
Computer Engineering 9 (2019) 4939–4950. doi:10.11591/ijece.v9i6.pp4939-4950.
[25] N. D. Wirastuti, G. Sukadarmika, I. A. Suyadnya, D. C. Krishne, et al., Adaptive on-
line learning design using Moodle, in: 2016 International Conference on Smart Green
Technology in Electrical and Information Systems (ICSGTEIS), IEEE, 2016, pp. 98–101.
doi:10.1109/ICSGTEIS.2016.7885773.
[26] C.-H. Wu, T.-C. Chen, Y.-H. Yan, C.-F. Lee, Developing an adaptive e-learning system for
learning Excel, in: 2017 International Conference on Applied System Innovation (ICASI),
IEEE, 2017, pp. 1973–1975. doi:10.1109/ICASI.2017.7988583.
[27] A. T. Bimba, N. Idris, A. Al-Hunaiyyan, R. B. Mahmud, N. L. B. M. Shuib, Adaptive feedback
in computer-based learning environments: a review, Adaptive Behavior 25 (2017) 217–234.
doi:10.1177/1059712317727590.
409
[28] M. Shyshkina, Perspective technologies of e-learning systems development, Information
technologies in education (2011) 132–139.
[29] S. M. Honcharov, A. A. Biletskyi, O. M. Hubnytska, T. A. Kostiukova, Formy, metody i
orhanizatsiia navchalnoho protsesu v kredytno-modulnii system, NUVHTT, Rivne, 2007.
[30] N. Moiseienko, M. Moiseienko, S. Semerikov, Mobilne informatsiino-osvitnie sere-
dovyshche vyshchoho navchalnoho zakladu (The mobile information and educational
environment of higher educational institution), Bulletin of the Cherkasy Bohdan
Khmelnytsky National University. Series "Pedagogical Sciences 11 (2016) 20–27. URL:
http://ped-ejournal.cdu.edu.ua/article/view/1610/1673.
[31] V. Borogev, Psikhologo-pedagogicheskie osnovy sistemy adaptivnogo obucheniia (Psycho-
logical and pedagogical foundations of the system of adaptive learning), Nauka i shkola
(2001) 12–15.
[32] B. F. Skinner, Science and human behavior, Simon and Schuster, 1965. URL: http://www.
bfskinner.org/newtestsite/wp-content/uploads/2014/02/ScienceHumanBehavior.pdf.
[33] N. A. Krauder, O razlichiyakh mezhdu linejnym i razvetvlyonnym programmirovaniem
(on the differences between linear and branched programming), in: I. I. Tikhonov (Ed.),
Programmirovannoe obuchenie za rubezhom, Vysshaya shkola, Moskva, 1968, pp. 58–67.
[34] G. Pask, The cybernetics of human learning and performance: A guide to theory and
research, Hutchinson Educational, London, 1975.
[35] W. Stangl, Stichwort: Adaptivität | online lexikon für psychologie und pädagogik, 2019.
URL: https://lexikon.stangl.eu/982/adaptivitaet/.
[36] L. Pugliese, Adaptive learning systems: Surviving the storm, 2016. URL: https://er.educause.
edu/articles/2016/10/adaptive-learning-systems-surviving-the-storm.
[37] H. Khosravi, S. Sadiq, D. Gasevic, Development and adoption of an adaptive learning system:
Reflections and lessons learned, in: Proceedings of the 51st ACM Technical Symposium
on Computer Science Education, 2020, pp. 58–64. doi:10.1145/3328778.3366900.
[38] Decoding adaptive, 2016. URL: https://www.pearson.com/content/
dam/one-dot-com/one-dot-com/global/Files/about-pearson/innovation/
Pearson-Decoding-Adaptive-v5-Web.pdf.
[39] M. S. Mazorchuk, T. S. Vakulenko, A. O. Bychko, O. H. Kuzminska, O. V. Prokhorov,
Cloud technologies and learning analytics: web application for PISA results analysis and
visualization, CEUR Workshop Proceedings (2020, in press).
[40] G. Bryant, Learning to adapt 2.0: The evolution of adaptive learn-
ing in higher education, 2016. URL: https://tytonpartners.com/library/
learning-to-adapt-2-0-the-evolution-of-adaptive-learning-in-higher-education/.
[41] O. Pursky, T. Dubovyk, I. Gamova, I. Buchatska, Computation algorithm for integral
indicator of socio-economic development, volume 2393, CEUR-WS, 2019.
[42] ISO/IEC 25010:2011. Systems and software engineering — Systems and software Quality
Requirements and Evaluation (SQuaRE) — System and software quality models, ISO, 2011.
URL: https://www.iso.org/standard/35733.html.
410