Towards an Adaptive Study Management Platform: Freedom

Through Personalization

Amir Dirin

and Teemu. H. Laine

Business Information Technology, Haaga-Helia University of Applied Science, Helsinki, Finland

Department of Computer Science, Electrical and Space Engineering, Luleå University of Technology, Skellefteå, Sweden

Keywords: Adaptive Learning, Personalization, Study Management, Data Mining, Higher Education.

Abstract: Technological advancements have brought abundant freedom to our lives. In an educational context, however,

the technology utilization is still relatively low despite recent developments on various learning platforms

such as e-learning, mobile learning, MOOCs, and social networks. The contemporary technological

advancement in smart gadgets enables us to bring learning resources with appropriate content format to the

learners at the right time in the right learning situation. Yet there remains a need for an adaptive study

management solution that would apply data mining algorithms to assist university students both before and

during their studies in a personalized manner. This assistance can be of many kinds, such as campus

orientation to new students, course curriculum recommendations, and customization of study paths. In this

paper, we present the concept and an initial implementation the Adaptive Study Management (ASM) platform

that aims at facilitating a university student’s academic life in different phases by tracing the student’s

activities and providing personalized services, such as a course curriculum recommendation, based on their

behavior and achievements during a period. The ASM platform creates a profile for the student based on their

achievements and competencies. Consequently, the platform aims to grant freedom to students on their study

management, eases teachers’ workloads on assessing students’ performance, and assists teachers and

administrators to follow up students and dropouts. The goal of this platform to increase graduation rates by

personalizing study management and providing analysis services, such as dropout prediction.

1 INTRODUCTION

The use of ICT in education and training has caused

several paradigm shifts, e.g., the Internet has offered

flexible and powerful ways to accomplish a range of

pedagogical goals (Anderson and Dron, 2011).

Higher educational institutes often organize an

orientation week for new students. The orientation

week has significant impact on students

psychologically, sociologically, and for future

learning efficiency. Already in 2002, Murphy, et al.

(2002) utilized a web-based college orientation to

help students to adapt with the new environment.

Orientation week is also important for new employee

in companies. Acevedo & Yancey (2011) designed a

framework which focuses on a Realistic Orientation

Program for new Employee Stress (ROPES).

Furthermore, recent advancements in mobile and

wireless technologies have enabled learners to carry

out educational tasks anywhere at any time. This

trend is evolving, as mobile learning has become

more than an add-on in e-learning platforms.

However, providing learning materials to mobile

devices is associated with design and development

challenges (Dirin, 2016).

Smartphones and other context-sensing

technologies have enabled context-aware learning

experiences. These smart devices may overcome the

traditional educational and classroom constraints,

such as place, time and presence, as they enable

learning to happen anytime, anywhere, with presence

when needed (e.g. via videoconferencing). A range of

context-aware learning systems have been proposed

for different purposes (Schmidt, 2005; Gómez et al.,

2014), but most of them do not tackle the task of

managing one’s academic life in an efficient and

personalized manner.

Bloom (1984) demonstrates that the one-to-one

expert tutoring is more efficient than conventional

classrooms and master learning. It is therefore a

desired feature of an adaptive study management

system to provide one-to-one expert tutoring in a

432

Dirin, A. and Laine, T.

Towards an Adaptive Study Management Platform: Freedom Through Personalization.

DOI: 10.5220/0006788104320439

In Proceedings of the 10th International Conference on Computer Supported Education (CSEDU 2018), pages 432-439

ISBN: 978-989-758-291-2

personalized manner. To understand the learner’s

context and thereby achieve personalized one-to-one

expert tutoring, a system must collect and analyze

large quantities of data. Fortunately, there exists an

abundant repertoire of knowledge discovery and data

mining algorithms that can be utilized to achieve this.

In this paper, we propose a novel concept for a

Adaptive Study Management (ASM) platform that

utilizes knowledge discovery and data mining

algorithms to achieve context-awareness to the

student’s individual academic profile, including

academic performance, preferences, behavioral data,

competencies, and study activities. The platform’s

goal is help students efficiently plan and manage their

studies, thus resulting in improved competency.

Through presenting the ASM concept and

implementations of first components of the prototype,

we discuss the advantages and disadvantages of this

future trend of adaptive study management where

academic life is facilitated by seamless context-aware

interaction with classroom and peers.

2 BACKGROUND

2.1 Mining Big Data

Sagiroglu and Sinanc (2013) define big data as

massive data sets which have a complex and varied

structure, with challenges of storing, analyzing, and

visualizing for further processes (e.g. personalization

of learning). Big data are often collected from

multiple autonomous sources. Big data analytics is

the process of identifying patterns among the

collected data, and it has become popular across

industry domains. Big data analytics help develop

new business opportunities for companies (Schultz,

2013), but research and applications of it in the

educational context less common. Wassan (2015)

recommends applying big data anaalytics to

educational contexts, as there are vast amounts of

valuable data involved especially in online courses.

One of the essential methods of big data analytics

is data mining, which refers to the process of

extracting hidden knowledge from a large amount of

data. The generic goal of data mining is to identify

patterns and relationships in the data, which, in turn,

can be used for making predictions of future events

(e.g. student dropouts). There are various approaches

to data mining, such as association rules,

classification, decision trees, clustering, neural

networks, and clustering. Many of these are defined

under the term of machine learning (ML), which is a

family of algorithms making predictions based on

what they have previously been learning of the data.

ML algorithms can be divided into two

categories: supervised and unsupervised. Moreover,

semi-supervised ML algorithms are hybrids of the

two main categories. Supervised ML algorithms are

provided with a set of instructions and a definition of

what the predictions should aim at (James et al.,

2013). For example, a supervised ML algorithm

detecting the learner’s emotions is given a time of

day, the learner’s heart rate and galvanic skin

response, and examples of correct predictions. With

this training data, the algorithm learns to make

accurate predictions using similar data sets in the

future. Supervised ML is useful when the data to be

analyzed is consistent and the number of prediction

classes is reasonably low. In contrast, in unsupervised

learning the input data is unlabeled, and the algorithm

must decide what the appropriate output should be

based on data clustering or association from the

example data (Ghahramani, 2004). Unsupervised

learning is useful in scenarios with a wide range of

acceptable predictions, such as recognizing students

by their facial features.

In the domain of educational applications, as with

many other domains where large amounts of data are

generated, data mining can be used for many

purposes, such as predicting dropouts, personalizing

learning experiences or even increasing security of an

educational platform. Chen, Hsieh, & Hsu (2007)

applied an association rule method – whereby

correlations between variables in the data set are

revealed – for diagnosing the learner’s common

learning misconceptions. As another example,

Romero & Ventura (2013) applied data mining to

gain an insight on how students learn in order to

improve educational outcomes. Almazroui (2013)

conducted a survey to learn about the use of data

mining in the e-learning context.

2.2 IoT and Learning

The Internet-of-Things (IoT) is an emerging

technology that is said to affect the way we live, learn

and play more than the Internet has done so far.

Already today this technology is used in a number of

areas, such as healthcare and education. The IoT is an

extension to the Internet as we known it, through

bringing everyday objects and sensors online. These

IoT devices enable truly smart environments and

applications that finally realize Weiser’s vision of

ubiquitous computing (Weiser, 1999).

With the IoT, it is expected that huge amounts of

data about different entities, like learners and their

Towards an Adaptive Study Management Platform: Freedom Through Personalization

433

environments, will be produced. This means that the

IoT has the ability to become a core technology in

future educational applications that utilize the

analytical power of data mining algorithms. For

example, Njeru et al. (2017) utilized IoT in online

learning to collect and min the data to improve the

course materials and the delivery of their online

courses. De La Guia et al (2016) investigated the

benefits of using wearable and IoT technologies in

providing task-based language learning scenarios.

They demonstrate that by applying these technologies

freeing the instructors oh having to keep records of

the task performed by each student during the class.

Xu et al. (2015) predicts that the application of IoT in

education will increase due to its unique advantages

for improving the quality of education.

2.3 Context-aware Learning

IoT and data mining are essential for developing

context-aware learning solutions, whereby the

learning system is able to detect and act upon the

changes in the learner’s context. Chen (2008) defined

context-aware and ubiquitous learning as a computer-

supported learning paradigm for identifying the

learner’s situations and surrounding context to

provide integrated, interoperable, pervasive and

seamless learning experiences. By this enhancement,

learning contents are not only accessible from

anywhere and anytime, but learning can happen at the

right time and in the right place with the right

resources. To enable this, context-aware learning is

typically supported by mobile devices with sensing

capabilities such as GPS, camera and other sensors.

A context-aware learning space can detect and act

upon changes in the learner's context, thus resulting

in the provision of learning content relevant to the

learner's situation. Context not only includes physical

location but also environmental parameters, states of

the learner's body and mind, social group, and any

other information that constitutes a situation in which

the learner is embedded. The learning system’s

awareness of the learner’s context depends on its

technical capabilities; the requirements for this stem

from the desired experience – what does the learning

space need to know about the context to provide a

purposeful learning experience? It may be enough to

know the learner's location within a geographical area

(Ballagas et al., 2007), or it may be necessary to

detect parameters of the learner's body (Zhang et al.,

2012). All these approaches require technologies

ranging from wireless networking to GPS and from

bodily sensors to environmental sensors. As creating

a highly context-aware learning space requires money

and time, trade-offs are often necessary.

Burns (2002) defines learning as relatively

permanent changes in behavior, with behavior

including both observable activity and internal

processes such as thinking, attitudes, and emotions.

Following the constructivist view, learning is a

process where an individual manipulates information

to create knowledge. This knowledge creation

activity is individual as it happens in the learner’s

brain. Therefore, different learners have different

cognitive processing approaches for learning.

In recent years, the approaches to learning have

significantly changed due to technological advances.

In traditional learning environments, teachers were

the main actors who delivered knowledge to students.

In contrast, in the Internet era, vast amounts of

resources are accessible with small effort to anyone

to learn through smart devices (Dirin, Nieminen and

Kettunen, 2013). Thus, the learner becomes more

active, with a higher degree of freedom to choose

study activities; the teacher becomes a facilitator who

assists the learner in the learning process.

3 TOWARDS AN ADAPTIVE

STUDY MANAGEMENT

PLATFORM

Despite advances in learning technologies that enable

provision of learning content to students in rich

digital formats, most learning environments fail to

provide personalized assistance to students regarding

their study management, such as planning a study

path or helping with competency development

through offering an alternative solution to a

predefined course curriculum. Personalization

requires understanding of the learner’s context, which

can be achieved by applying data mining methods to

the collected data on students’ profile data. In the

following, we describe the concept of a novel

Adaptive Study Management platform, followed by

first implementations of its components.

3.1 The ASM Platform Concept

Figure 1 presents the first phases of a student’s

academic life that the ASM platform supports. In the

first phase, students receive an admission letter with

a QR code. By scanning the QR code with a

smartphone, the student downloads a virtual reality

(VR) orientation game that consists of orientation

activities related to the university premises, the

CSEDU 2018 - 10th International Conference on Computer Supported Education

434

curriculum of the Business Information Technology

(BITe) program, and MyNet, a website with essential

information about the university and studies, such as

available pre-constructed study paths.

In the second phase, the student is eligible to

select and start courses for the first semester. Each

course is divided into weeks, and each week contains

lectures, quizzes and performance reports. The

second phase also includes tools for course

registrations and management of first weeks of

student life at a new academic environment; these are

available for later phases as well.

The third phase commences after the first

semester when the system proposes a study path and

the student makes a choice accordingly. In this phase,

data mining (e.g. machine learning) algorithms are

utilized to adapt the study experience to the student’s

profile, which has been constructed during the first

two phases, and which will be updated throughout the

studies. The student’s competencies, performance

and personal preferences are inputs to the adaptation

algorithms, which then provides personalized study

management services, such as a recommendation on

which study path would be the best, links to

extracurricular courses that would be helpful for

competency development, and adaptation of course

contents to match personal preferences. More phases

(e.g. thesis authoring) can be added later. In this

paper, we merely focus on phases 1 and 2.

Figure 1: Study phases supported by the platform.

Scenario for phase 1

Eric Chan received his acceptance letter from the

HH University in June. He is a freshman student in

the BITe programme. With the letter of acceptance,

Eric also received a barcode to a link to download the

HH Orientation Game. Eric accesses the link and

loads the game to his mobile phone. He can then start

to learn about HH and BITe while playing the game.

Within a few days, Eric has gained visualized

knowledge about his the HH campus, his HH profile,

and teachers, as well as hands-on information about

using campus and online services. By playing the

Orientation Game, featuring a VR tour, Eric now

knows which the service locations (e.g. library,

computer rooms, printers, cafeteria) at the campus.

He is able to use school benefits such as M-Drive,

VDI, Office365, and student discounts. He has also

learned the process of looking for course information

and timetables, registering for courses, creating own

timetables and tracking performance by playing

minigames related to the university’s online services

(MyNet, Asio, WinhaWille).

By the end of the week, Eric has completed all

mini-games within the HH Orientation game that help

plan his studies for the first and second period of his

first semester. He also knows how to access various

services using his school items such as library card,

student credentials, and lunch card.

When the academic year starts, Eric goes to HH and

is able to easily access and use school services right

away. He knows what his planned courses offer

because he has learned about the courses'

introduction through Moodle minigames.

Scenario for phase 2

Eric participates in the User Experience course.

He learned from the course description that the

course’s lectures are compulsory. Therefore, he

checks his mobile and found the lecture room in time.

As soon as he arrived, the teacher asked Eric whether

he is willing to attend the course virtually. By Eric's

confirmation, the teacher asked him to point the

finger to the touchpad and take a photo. The teacher

then introduces the learning application, the course

schedule and the first teamwork assignment.

In order to join the next lecture from home, Eric

opens his laptop's camera and opens the course

webinar app. He learned that some of his team

members already participated in the lecture

physically. Eric and his other three team members

successfully managed to share the teamwork results

with the class both remotely and in-class.

The teacher in the course can see all students’

progress (e.g. answers to quizzes) by one click. He

can also upload links or files and create quizzes based

on the links or documents the students have to study.

Through the mobile app, Eric is not only able to

access learning contents and take lectures remotely,

but also trace his progress at any time. To consolidate

what Eric learned, he uses the mobile app to take

quizzes. With the quiz results, Eric and the teacher

can track his progress in the course. After the

semester, the platform recommends Eric courses that

he should and he could to take next semester.

Towards an Adaptive Study Management Platform: Freedom Through Personalization

435

3.2 Prototype Implementation

Here we describe the first implementations (phases 1

and 2) of the ASM platform. The orientation feature

(phase 1) was implemented as a 3D VR game with the

Unity 3D game engine. The game allows the player

to explore the campus, its lecture rooms, offices, and

classrooms. We used 360-degree video presentations

of the campus through which the user may interact

with the surroundings. Moreover, the phase 1

prototype includes information about the BITe

program and MyNet. The details about the concept

development process, architecture, and applied

technologies are to be presented in a different paper.

Figure 3 presents screenshots of the orientation game.

Figure 2: Samples of phase 1 prototype screenshots.

The implementation of the phase 2 prototype has two

parts: 1. teachers’ tool that enable teachers to create

activities, such as lecture notes, quizzes, and notices;

and 2. students’ application with assignments,

lectures’ activities and course performance. We

utilized a NoSQL database for storing all the data and

a NodeJs/ExpressJs server to connects the front-end

(mobile application and website) to the back-end

(database). The React Native framework was used for

the mobile application implementation. Figure 4

presents sample of screenshots of the students’

application. The database design of the mobile

application is presented in Figure 5 and the overall

architecture is given in Figure 6. Figure 7 shows the

interaction between the learner and the system in the

phase 2 prototype implementation.

Figure 3: Samples of phase 2 prototype screenshots.

Figure 4: Design of the phase 2 database.

The implementation of the system is based on a three-

tier architecture. The details of each tier are

considered to be out of the scope of this paper.

Figure 5: Phase 2 implementation architecture.

4 OPPORTUNITIES AND

CHALLENGES

The ASM platform supports truly context-aware

study management services, which provides freedom

and enhanced learning experiences to students. More,

it aims at facilitating teachers’ work, thus it is

important to discuss the opportunities from teachers’

CSEDU 2018 - 10th International Conference on Computer Supported Education

436

perspective. The opportunities from the student’s and

the teacher’s perspectives are summarized and

discussed in Table 1 and Table 2, respectively.

Table 1: Opportunities from the student’s perspective.

Opportunity Description

Freedom

The student is free to plan and

implement their studies in a

personalized manner.

Portability

Technical portability is enabled

with ubiquitous technologies.

Content of the orientation game is

portable as a story. The lectures are

accessible ubiquitously.

Increased

motivation

The ASM platform aims to be an

all-in-one study management

service where the student may join

a lecture from anywhere (remote

presence), gain ownership through

customization of the service, and

instantly communicate with peers

and teachers. These are likely to

increase student motivation.

Informal and

formal contexts

The platform supports both formal

(e.g. ordinary courses) and informal

(e.g. virtual campus tour) learning

opportunities

Adaptable

content

Services are adapted to match the

student’s profile

Quizzes

Each week the student receives a

quiz, which is based on their profile

(e.g. competence level, previous

performance) to facilitate learning

Performance

The student can follow his / her

progress

Suggestion

The student receives

recommendations from the platform

(e.g. courses to take)

Human touch

The platform provides a

combination of face-to-face and

remote teaching/learning.

Emotional engagement of the

stakeholders is a key factor in the

platform development.

Table 2: Opportunities from the teacher’s perspective.

Opportunity Description

Freedom

The ASM platform provides freedom

to teachers in many ways: 1) it frees

teachers from some parts of the

orientation week; 2)

Teachers are able to upload and

provide the lectures notes at their

convenience; 3) Compulsory presence

become optional for students, thus

making the classroom more

manageable; 4) System records and

manages students’ progress and

performance, hence, less manual

students’ performance assessment.

Portability

The ASM platform enables teachers to

follow students’ performance,

progress, and presence at any time and

any place. Furthermore, through the

ASM platform, teachers may offer

lectures regardless of time and place.

Increased

motivation

The ASM platform aims to be an all-in-

one study management service where

the teacher may provide lectures from

anywhere (remote presence), gain

ownership through customization of

the service, and instantly communicate

with students. Teachers receive visual

feedback on students’ performance and

are therefore able to improve the course

further.

Informal and

formal

contexts

The platform supports both formal (e.g.

ordinary courses) and informal (e.g.

virtual campus tour) learning

opportunities. Hence teachers may

utilize their preferred pedagogical

approaches for course implementation.

Adaptable

content

The platform features are provided as

services. These services are compatible

and adaptable with the existing

Learning Managements System (LMS)

when required. Additionally, the

platform services are adapted to match

the student’s profile

Quizzes

Teachers can create a quiz bank from

which the system picks quizzes to the

student based on their profile (e.g.

competence level, previous

performance) to facilitate learning.

Teachers receive update on the

students’ performance on quizzes.

Performance

The teachers can follow students’

progress and accordingly adjust the

course content and quizzes to gain the

better results.

Suggestion

The teacher receives recommendations

from the system (e.g. additional

content or suitable pedagogical

approaches to use)

Human touch

The ASM platform provides a

combination of face-to-face and remote

teaching and learning. Emotional

engagement of the stakeholders is

among the key factors in the platform

development

There remains challenges to be solved in the

development process, as Table 3 illustrates.

Towards an Adaptive Study Management Platform: Freedom Through Personalization

437

Table 3: Development challenges.

Challenge Description

Content

creation and

sharing

Development of an easy-to-use and

feature-rich content editing system is

challenging in terms of resources. To

alleviate this, an existing content

framework could be adopted.

Novelty effect

Novelty of VR technology and

freedom of participation in

classroom is likely to motivate

students and teachers but it will not

last forever.

Encouraging

performance

indicator

Continuous performance evaluation

may result in disappointment for

students who are not doing well in

the classroom. Moreover, teachers

ignore the indicators in a long run.

Usability and

user experience

The concept is a unique experience

for students and teachers.

Adaptation to the new learning and

teaching environment in the

beginning can be challenging.

Heterogeneous

components

The current prototype components

were implemented separately. It is a

technical challenge to combine these

in a seamless way whilst supporting

extensibility.

Human touch

To make a system that engages the

students emotionally in an efficient

manner is a challenging task.

5 CONCLUSION

The potential of technology is not being fully utilized

in educational processes. In contemporary classroom

and lecture setups, the participation in the lecture is

still often compulsory, and students have to follow

dictated degree program curricula and study paths.

The existing tools such as Moodle mainly help for

durable content management and does not provide

students with freedom to personalize their studies.

The aim of this study was to develop an adaptive

study management platform that efficiently utilizes

various technologies to such freedom to students. The

motivation is to overcome traditional educational

constraints, such as place, time and connectivity. The

platform supports students, teachers and§ educational

institutes from the time that the student receives an

acceptance letter up to their graduation ceremony.

The platform enables the student to take part in a

lecture at any time any place. Furthermore, it helps

the student personalize their study path and courses

based on their individual profile and performance.

The ASM platform enables the teacher to follow

up the student's performance records and activities in

each lecture. The current prototype comprises a main

mobile learning application for students and teachers,

and an orientation game for students.

The proposed concept is a demonstration of

changing requirements for learning and teaching

environments. Consequently, education must be

aligned with students’ expectations. Smart devices

have become parts of our lives, and utilizing these

devices in learning processes is a pedagogical asset.

Learning happens on the student’s own device in a

familiar environment. Soon any device can be

transformed into a learning platform that interacts

with the surroundings for pedagogical purposes.

In the following months, we aim to implement a

phase 3 prototype of the ASM platform with

adaptation features using data mining (e.g. machine

learning algorithms). Afterwards, we plan to evaluate

the implemented prototype components in the BITe

degree program. This evaluation will help us assess

the students’ performance and evaluate the impact of

the ASM platform on their learning processes.

REFERENCES

Acevedo, J. M. and Yancey, G. B. (2011) ‘Assessing new

employee orientation programs’, Journal of Workplace

Learning, 23(5), pp. 349–354. doi: 10.1108/13665621

111141939.

Almazroui, Y. A. (2013) ‘A survey of Data mining in the

context of E-learning’, International Journal of Infor-

mation Technology & Computer Science, 7, pp. 8–18.

Anderson, T. and Dron, J. (2011) ‘Three generations of

distance education pedagogy’, International Review of

Research in Open and Distance Learning, 12(3), pp.

80–97.

Ballagas, R. A. et al. (2007) ‘REXplorer: a mobile,

pervasive spell-casting game for tourists’, CHI’07

extended abstracts on Human factors in computing

systems, p. 1934. doi: 10.1145/1240866.1240927.

BLOOM, B. S. (1984) ‘The 2 Sigma Problem: The Search

for Methods of Group Instruction as Effective as One-

to-One Tutoring’, Educational Researcher, 13(6), pp.

4–16. doi: 10.3102/0013189X013006004.

Briefing, T. and Series, P. (2002) ‘Learning and Teaching

Briefing Papers Series’, Development, pp. 2–4.

Chen, C. M., Hsieh, Y. L. and Hsu, S. H. (2007) ‘Mining

learner profile utilizing association rule for web-based

learning diagnosis’, Expert Systems with Applications,

33(1), pp. 6–22. doi: 10.1016/j.eswa.2006.04.025.

Chen, T. S. et al. (2008) ‘Context-aware writing in

ubiquitous learning environments’, in Proceedings - 5th

IEEE International Conference on Wireless, Mobile,

and Ubiquitous Technologies in Education, WMUTE

2008, pp. 67–73. doi: 10.1109/WMUTE.2008.12.

CSEDU 2018 - 10th International Conference on Computer Supported Education

438

Dirin, A. (2016) ‘From Usability to User Experience in

Mobile Learning Application’, p. 316. Available at:

https://aaltodoc.aalto.fi/bitstream/handle/123456789/2

3561/isbn9789526071732.pdf?sequence=1&isAllowe

d=y.

Dirin, A., Nieminen, M. and Kettunen, M. (2013) ‘Student

capabilities to utilize m-learning service in new smart

devices’, in Proceedings of the 2013 International

Conference on Advanced ICT. Sanya, China: Atlantis

Press. doi: 10.2991/icaicte.2013.89.

Ghahramani, Z. (2004) ‘Unsupervised Learning BT-

Advanced Lectures on Machine Learning’, Advanced

Lectures on Machine Learning, 3176(Chapter 5), pp.

72–112. doi: 10.1007/978-3-540-28650-9_5.

Gómez, S. et al. (2014) ‘Context-aware adaptive and

personalized mobile learning delivery supported by

UoLmP’, Journal of King Saud University - Computer

and Information Sciences, 26(1), pp. 47–61. doi:

10.1016/j.jksuci.2013.10.008.

James, G. et al. (2013) An Introduction to Statistical

Learning. New York, NY: Springer New York

(Springer Texts in Statistics). doi: 10.1007/978-1-4614-

7138-7.

De La Guia, E. et al. (2016) ‘Introducing IoT and Wearable

Technologies into Task-Based Language Learning for

Young Children’, IEEE Transactions on Learning

Technologies, 9(4), pp. 366–378. doi: 10.1109/

TLT.2016.2557333.

Murphy, C., Hawkes, L. and Law, J. (2002) ‘How

International Students Can Benefit from a Web-Based

College Orientation’, New Directions for Higher

Education, 117(117), pp. 37–44. doi: 10.1002/he.45.

Njeru, A. M. et al. (2017) ‘Using IoT technology

to improve online education through data mining’,

in 2017 International Conference on Applied

System Innovation (ICASI), pp. 515–518. doi:

10.1109/ICASI.2017.7988469.

Romero, C. and Ventura, S. (2013) ‘Data mining in

education’, Wiley Interdisciplinary Reviews: Data

Mining and Knowledge Discovery, 3(1), pp. 12–27. doi:

10.1002/widm.1075.

Sagiroglu, S. and Sinanc, D. (2013) ‘Big data: A review’,

in 2013 International Conference on Collaboration

Technologies and Systems (CTS), pp. 42–47. doi:

10.1109/CTS.2013.6567202.

Schmidt, A. (2005) ‘Potentials and Challenges of Context-

Awareness for Learning Solutions’, in Challenges, pp.

63–68.

Schultz, B. (2013) ‘Big data in big companies’, Baylor

Business Review, 32(1), pp. 20–21.

Wassan, J. T. (2015) ‘Discovering Big Data Modelling

for Educational World’, Procedia - Social and

Behavioral Sciences, 176, pp. 642–649. doi:

10.1016/j.sbspro.2015.01.522.

Weiser, M. (1999) ‘The computer for the 21st century’,

SIGMOBILE Mob. Comput. Commun. Rev. New York,

NY, USA: ACM, 3(3), pp. 3–11.

Xu, F., Ye, M. and Destech Publicat, I. (2015) ‘The Coming

Storm of the IoT in the Field of Education’,

International Conference on Advanced Education and

Management (Icaem 2015), pp. 305–309.

Zhang, M. et al. (2012) ‘Virtual network marathon with

immersion, scientificalness, competitiveness,

adaptability and learning’, Computer & Graphics,

36(3), pp. 185–192.

Towards an Adaptive Study Management Platform: Freedom Through Personalization

439