An Overview of Adaptive Learning Fee-based Platforms

Soukaina Hakkal, Ayoub Ait Lahcen

Engineering Sciences Laboratory, National School of Applied Science, Ibn Tofail University, Kenitra, Morocco

Keywords: Adaptive Learning, Adaptive E-learning Platforms, Personalized Knowledge.

Abstract: Because of the sanitary crisis created by the appearance of covid-19, the education system was forced to

change its system to a flexible online one; the adaptive e-learning has become the pedagogical model of the

first choice for successful education in the era of 2021. Adaptive e-learning platforms exist in abundance to

offer personalized knowledge to improve learners’ personal skills, respond to their needs, and satisfy their

interests, allowing them to master their learning. The core purpose of this paper is to provide the current state

of the art by reviewing the existing adaptive, fee-based learning platforms based on a survey that was

conducted to define the characteristics and features of each platform, with the vision to help learners choose

The most suitable adaptive e-learning platform.

1 INTRODUCTION

Everybody has the potential to learn; according to

Harold Pashler, different people learn information in

different ways, but the most successful way is to

provide learning depending on a student's individual

needs (Harold, McDaniel, Rohrer, & Bjork, 2008).

However, most of the learning models are based on a

standardized approach unsuitable for individualized

learning, ignoring the interests and abilities of each

learner; they present a course in the same way for

everyone. Benjamin Bloom (1984) has described the

effectiveness of individual “personalized” learning;

using it, we easily understand students' learning

experiences adapted to their individual needs, skills,

and interests. Therefore, to fill in the gaps in

traditional learning methods, the contemporary

education system has provided adaptive e-learning

methods; however it is difficult to apply them in

traditional education since it requires many resources,

and it is not practical to have one teacher for every

student. In addition, personalized learning is not yet

widespread in schools. Many aspects still need to be

researched. Nevertheless, this approach can help

reduce the stigma of adapted education and better suit

the needs of students with differences in learning

abilities.

Many e-learning platforms are available on the

internet; however, the provided material cannot solve

https://orcid.org/0000-0001-8739-3369

all learners’ problems due to the common syllabus

and monotonous learning styles (Abdalla & Dhupia,

Implementing Adaptive e-Learning Conceptual

Model : A Survey and Comparison with Open Source

LMS, 2019). At the same time, adaptive e-learning

platforms are among the technological innovations

that can effectively deal with this issue.

In adaptive education systems, the characteristics

of the learner are considered, and the learning

environment is appropriately adapted to provide

support and improvements to the learning process

(Khalid, Hagras, Alghazzawi, & Aldabbagh, 2017),

(Shute & Zapata-Rivera, 2012), (Oxman & Wong,

2014). These systems are attracting much attention

because of their capacity to deliver instructional

content and analysis by proactively adapting to

students' specific requirements and needs (Khalid,

Hagras, Alghazzawi, & Aldabbagh, 2017), (Shute &

Zapata-Rivera, 2012), (I., 2012).

This study will focus on evaluating some existing

adaptive fee-based learning platforms in higher and

secondary education, based on technical, pedagogical

features, and provided characteristics, as well as a

comparison between these adaptive e-learning

platforms. Therefore, twelve adaptive fee-based e-

learning platforms (Knewton, Smartsparrow,

Scootpad, Yokimi, Dreambox, Aleks, Claned, Lrnr,

Kinteract, Zzish, Embibe, Realizeit) were chosen to

complete this study.

222

Hakkal, S. and Ait Lahcen, A.

An Overview of Adaptive Learning Fee-based Platforms.

DOI: 10.5220/0010731400003101

In Proceedings of the 2nd International Conference on Big Data, Modelling and Machine Learning (BML 2021), pages 222-226

ISBN: 978-989-758-559-3

The rest of this paper is organized as follows. The

second section introduces similar works in emerging

systems, followed by a review and an analysis of the

platforms' pedagogical and organizational benefits

and drawbacks.

2 RELATED WORK

In the last few years, an immense need for adaptive

learning has been created, which has attracted the

attention of many researchers. Therefore, an amount

of effort has been made to review adaptive e-learning

systems outlined as follows. In (Akrivi, Christos, &

Maria, 2018), authors reviewed some learning

management systems (LMS), as well as content

management systems(CMS), namely Moodle,

ATutor, Drupal, Joomla and WordPress and

compared them based on many technical and

educational aspects such as ease to use, accessibility,

customization, interactions, usability, etc. the main

objective of their study is to provide useful

information to higher education to choose LMS or

CMS regarding their proper needs. In a similar

context, the study in (Abdalla & Dhupia,

Implementing Adaptive e-Learning Conceptual

Model : A Survey and Comparison with Open Source

LMS, 2019), provides a comparison among similar

LMS, for instance, EduBrite, TalentLMS, Edmods,

Sakai based on their features, practical feedback from

the students and instructor, and the target customer

size. The study aims to help university students and

instructors to choose a suitable learning management

system.

In (Kasim & Khalid, 2016), the authors discuss

multiple learning management systems, which are

Sakai, Blackboard, SuccessFactor, and SumTotal and

compare them based on several characteristics such

as integration with other systems, accessibility, users’

interactions, flexibility, synchronous and

asynchronous interactions, etc. This study provides a

conclusion on the selection of platforms to be adopted

by the higher education institution. The authors in

(Yilmaz & Erol, 2019) present a comparative study of

learning management systems and e-learning author

tools, which are preferred in Turkey, based on their

technical and educational features as well as

disadvantages to contribute positively. In (Florence,

Yan, Robert, & Carl, 2020), the authors present a

systematic review of research on adaptive learning

based on publication trends, instructional context,

research methodology components, research focus,

adaptive strategies, and technologies. The study in

(Abhinaw & Eswaran, 2018), reviews several

learning management systems, namely Adobe

Captive Prime, TalentLMS, Docebo, Litmos,

Coursemill, Moodle, Blackboard, Electronic

Educational Environment (EEE) LMS, based on a

comparison of the identified and essential features. In

this study (Tsolis, et al., 2010), the authors reviewed

some traditional learning management systems and

existing adaptive e-learning systems and propose

implementing a combined solution to benefit from the

advantages of both technologies.

3 FEE-BASED E-LEARNING

PLATFORMS

KNEWTON: Knewton is a personalized adaptive

platform headquartered in New York City, used by

more than 15 million students around the world. It

identifies and supports the process of continuous

personalized learning through knowledge maps and

real-time monitoring and response to student

interactions (communication, collaboration and

game), as well as identifying and bridging the

knowledge gaps while the students are doing

homework to get them where they need to go (Peng,

Ma, & Spector, 2019). In addition, Knewton is one of

the first platforms to actively put data analysis

technologies at the service of education (Osadcha,

Osadchyi, Semerikov, Chemerys, & Chorna, 2020).

SMARTSPARROW: Smartsparrow is a

platform that allows mentors to easily build

graphically rich online tutorials. They decide on the

structure of their courses, and the platform does the

rest. It is an intuitive authoring tool that offers real-

time interactive learning components; it provides the

student with a space adapted to their specific needs

using questions and feedback. Smartsparrow is based

in Sydney Australia, and over 700 leading institutions

trust it; this technology allows improving the e-book

offer to create new generation e-books that are more

attractive.

SCOOTPAD: Used by over 400 schools in the

USA, it provides a tool for teachers and

administrators to create adaptive learning playlists for

students. Students begin a unit by taking an

assessment; this assessment determines the student's

needs and weaknesses and what instruction the

student should receive in real-time. As the student

progresses, ScootPad adapts to his or her progress,

presenting different lessons, exercises and

assessments for each student. While students work,

data is sent in real-time to a teacher's dashboard.

An Overview of Adaptive Learning Fee-based Platforms

223

YOKIMI: Launched in November 2018 in

France, and installed by more than 10000 users; it is

the first pedagogical artificial intelligence that

represents a maths teacher in the form of an instant

messenger; it is an artificial intelligence that helps to

progress in maths for primary school students. This

chatbot begins by asking questions to determine the

level of the learner in order to adapt the exercises to

his or her needs. Yokimi allows ensuring

personalized monitoring, continuous support,

pedagogical explications, and using point-earning

exercises to motivate the students.

DREAMBOX: Dreambox Learning Math is an

interactive K-8 intelligent, adaptive and self-paced

mathematics platform, used in the USA and Canada

by nearly three million students and serving 120,000

teachers; it offers interesting hands-on activities

based on the principle of game theory. It creates a

personalized path for students based on the level they

have reached and adapts this path as students learn.

As learners complete the lessons, they earn coins,

which can be used to play games or customize their

avatars, wallpaper, and music (Carrie, 2020).

ALEKS: ALEKS stands for Assessment and

LEarning in Knowledge Spaces; it is an adaptive

learning system for mathematics, chemistry, and

business, used in the USA by more than 25 million

students throughout the world. At the core of Aleks is

an artificial intelligence engine that evaluates each

student individually and continuously. Aleks is only

adaptive in the outer loop, where it reinforces mastery

learning: students can only practice problems after

they have mastered all the required prerequisites.

Student interaction in Aleks is focused on selecting a

skill to master (Benjamin, et al., 2018).

CLANED: CLANED is a collaborative

application that creates a personal learning

environment for each student; it suits schools,

universities, and corporations; it is used by nearly two

million students in 2 000 schools across India and 15

customer countries. In this environment, the students

can study, collaborate and find learning materials that

correspond to their individual needs and skills

because CLANED builds on students' orientation and

learning strengths and identifies areas of

improvement.

LRNR: Lrnr is a cloud-based adaptive learning

platform used in the united states; it integrates

educational content with easy-to-use personal

learning tools, interactive assessments, customized

learning paths, and precise analysis to facilitate the

delivery of personalized learning experiences that

make studying and learning more powerful, efficient,

and engaging. Lrnr works by continuously and

seamlessly collecting and analysing huge quantities

of data in real-time as each student interacts with the

platform. Then, using a sophisticated combination of

cognitive analysis, artificial intelligence, machine

learning in order to determine each student's

strengths, weaknesses, knowledge gaps, and optimal

combinations of instruction and content (Aravind,

2015).

KINTERACT: Kinteract is an assessment

portfolio and platform that facilitates speedy

feedback and collaboration between educators and

their students and oldsters. Employed in the United

Kingdom by many schools, Designed for college

students between the ages of three and eighteen.

Driven by artificial intelligence, KINTERACT, the

digital learning platform permits following personal

development and academic performance at any stage

of the education journey.

EMBIBE: Embibe is a platform that allows

students to maximize learning outcomes, used in

India by 160 million subscribers. Among its many

offerings: adaptive practice, university videos, user

forums, news and information articles, and evaluation

tests that help students prepare for various

competitions. The platform supports different types

of tests for all levels of learning. As with all adaptive

teaching tools, Embibe works by personalizing

mentoring and academic guidance, offering each

student the course, assignments, and revisions most

suited to their needs.

ZZISH: ZZISH is a platform that supports over

two million students and 145,000 teachers in 170

countries. This tool allows teachers to quickly and

easily access information on the classroom and

student performance, so they can identify the most

important learning gaps and help individuals learn

better and faster based on their learning needs, more

effectively than ever before. A powerful feature of

Zzish is that, by displaying real-time data on the

electronic whiteboard in a fun and engaging way, it

can turn almost any application into an interesting

game for the whole class.

REALIZEIT: Realizeit is an adaptive learning

platform used in the United States; it enables one to

understand critical learner factors, quickly create the

right design and develop the learning product. A self-

learning engine that continually shapes the

experience to optimally deliver what each learner

needs to maximize their achievement. The Brandon

Hall Group acknowledged Realizeit as the winner of

the 2020 Excellence in Technology Award. Realizeit

has revolutionized the standard learning model by

adaptively integrating science and technology

BML 2021 - INTERNATIONAL CONFERENCE ON BIG DATA, MODELLING AND MACHINE LEARNING (BML’21)

224

learning while preserving and amplifying the art of

teaching and learning.

Table 1 : Pros, cons & price of fee-based platforms.

Platfor

Pros Cons Prices

Knewton High

adaptivity.

High

customization

Limited

content &

low learner

autonomy

39.95$/sin

gle

course,

79.95$/m

ultiple

courses

Smartspar

row

High

adaptivity.

High learner

autonom

Limited

pedagogical

design style

39$/mont

h/author/3

0students

Scootpad High students

monitoring

Dull and

repetitive

erience

3$/year/st

udent

Yokimi High

availability

A big

difference

in price

between the

premium

and

enhanced

acka

9,99$/mo

nth

Dreambox High

adaptivity

Annoying

advertiseme

nts

12,95$/m

onth/stude

Aleks High learner

autonomy &

Integration

with LMS

Privacy

limitation

19,95$/m

onth

Claned Fast & easy to

use

Usability

challenges

(limited

guidance)

Not

provided

Lrnr Engaging

activities.

Available on

cloud &

mobile

Limited

learner

autonomy

30$ - 40$

/student

/year/sem

ester

Kinteract Safe & Easy

to use

interface

The

application

crashes

randoml

Not

provided

Embibe Easy to use

interface

Android

application

needs

improvemen

Not

provided

Zzish

Real-time

interaction

The

application

crashes

randoml

5.75$/teac

her/month

billed

annuall

Realizeit High

autonomy

Limited

learner

autonom

Not

provided

Table 1 represents a set of advantages and

disadvantages of different fee-based adaptive e-

learning platforms, as well as their prices.

4 DISCUSSION

After reviewing the adaptive e-learning systems

presented previously, we found that some limitations

of existing platforms are related to the privacy,

repetitive contents, learner autonomy, or the need for

feedback based on learners’ social-emotional state.

This says a mechanism of sentiment analysis during

the learning process is needed for these platforms, as

well as integrating more attractive and diverse content

or different learning style will be useful to suit each

learning path and enhance efficiency and

performance.

From a technical angle, the platforms are

characterized by a user-friendly environment, not

requiring any technical or programming skills, an

easy deployment as well as offering a wide range of

customization options.

In addition, the fee-based platforms are featured

with a high adaptivity, high assessment, and high

collaboration, which means that the content can be

adapted to the learner’s data, with the capacity to

assess learning in collaboration with the educator to

maximize the engagement, such as Knewton,

Smartsparrow, Scootpad, Dreambox, Aleks, and

Zzish. However, most of these platforms are not

mobile compatible and are expensive. That said

Yokimi is a great mobile application, yet there is only

a French version.

5 CONCLUSION

Educating means developing a person's potential to

improve as a human being. Everyone seeks to learn

more in order to improve in a field and to acquire new

knowledge. Personalizing learning, skills,

behaviours, and approaches in the traditional context

means having a teacher for every student, which is not

easy and requires strategy, reflection, and many

resources. For this reason, adaptive e-learning

platforms were developed. Adaptive e-learning is a

combination of pedagogical techniques developed to

provide students with a unique and personal

experience, with the ultimate goal of increasing their

learning abilities.

This research is an evaluation of different existing

adaptive fee-based platforms that can be used by

An Overview of Adaptive Learning Fee-based Platforms

225

teachers to produce customized courses, as well as

students to better assimilate the lessons. From an

educational perspective, the fee-based platforms

provide an environment that understands the learners’

differences and converts them into training content

and processes that are suitable for each student. From

a technical perspective, fee-based platforms are

featured by a user-friendly environment that not

require any technical or programming skills for

deployment, high adaptivity, high user autonomy,

and a real-time interactions, but most of these

platforms are not mobile reactive.

ACKNOWLEDGEMENTS

This work was supported by the Al-Khawarizmi

Program funding by Morocco’s Ministry of

Education, Ministry of Industry and the Digital

Development Agency (ADD) under Project No.

451/2020 (Smart Learning).

REFERENCES

Abdalla, A., & Dhupia, B. (2019). Implementing Adaptive

e-Learning Conceptual Model : A Survey and

Comparison with Open Source LMS. the international

journal of emerging technologies in learning, 28-45.

Abhinaw, A., & Eswaran, S. (2018). A Survey of Open-

Source Learning Management Systems. Annals

Computer Science series Journal, 185-188.

Akrivi, K., Christos, T., & Maria, V. (2018). Comparing

LMS and CMS Platforms Supporting Social e-Learning

in Higher Education. 2017 8th International

Conference on Information, Intelligence, Systems &

Applications (IISA), (pp. 1-6).

Aravind, P. (2015, September). Lrnr Adaptive Learning

starts STEM course pilots at 12 colleges and

universities. Retrieved from Lrnr: https://www.lrnr.us/

Benjamin, D. N., Philip, I. P., Alistair, W., Andrew, M. O.,

Mustafa, H., & Xiangen, H. (2018). SKOPE-IT

(Shareable Knowledge Objects as Portable Intelligent

Tutors): overlaying natural language tutoring on an

adaptive learning system for mathematics.

International Journal of STEM Education.

Carrie, G. (2020, May). Dreambox Learning Math.

Retrieved from Common Sense Education:

https://www.commonsense.org

Florence, M., Yan, C., Robert, L. M., & Carl, D. W. (2020).

Systematic review of adaptive learning research

designs, context, strategies, and technologies from 2009

to 2018. Education Tech Research Dev, 1903–1929.

Harold, P., McDaniel, M., Rohrer, D., & Bjork, R. (2008).

Learning Styles: Concepts and Evidence. A JournalL

Of The Association For Psychological Science, 9, 106-

116.

I. (2012). Leveraging Intelligent Adaptive Learning to

Personalize Education: A Special White Paper Based

upon the Speak Up 2011 National Findings. ERIC.

Kasim, N. N., & Khalid, F. (2016). Choosing the Right

Learning Management System (LMS) for the Higher

Education Institution Context: A Systematic Review.

Journal of Emerging Technologies in Learning (iJET),

55-61.

Khalid, A., Hagras, H., Alghazzawi, D., & Aldabbagh, G.

(2017). A survey of artificial intelligence techniques

employed for adaptive educational systems within e-

learning platforms. De Gruyter, 47-64.

Osadcha, K., Osadchyi, V., Semerikov, S., Chemerys, H.,

& Chorna, A. (2020). The Review of the Adaptive

Learning Systems for the Formation of Individual

Educational Trajectory. CEUR Workshop Proceedings.

Oxman, S., & Wong, W. (2014). Adaptive Learning

Systems. DVX/ DeVry Education Group and Integrated

Education Solutions.

Peng, H., Ma, S., & Spector, J. (2019). Personalized

adaptive learning: an emerging pedagogical approach

enabled by a smart learning environment. Smart Learn.

Environ., 171-176.

Shute, V. J., & Zapata-Rivera, D. (2012). Adaptive

educational system. New York : Cambridge University

Press

, 7-27.

Tsolis, D., Stamou, S., Christia, P., Kampana, S.,

Rapakoulia, T., Skouta, M., & Athanasios , T. (2010).

An adaptive and personalized open source e-learning

platform. Procedia - Social and Behavioral Sciences,

38-43.

Yilmaz, S., & Erol, i. e. (2019). Comparison of the online

education platforms, and innovative solution proposals.

Communication and Technology Congress CTC, (pp.

259-267). Istanbul,Turkey.

BML 2021 - INTERNATIONAL CONFERENCE ON BIG DATA, MODELLING AND MACHINE LEARNING (BML’21)

226