=Paper=
{{Paper
|id=Vol-1628/Demo1
|storemode=property
|title=Adaptive web-based educational application for autistic students
|pdfUrl=https://ceur-ws.org/Vol-1628/Demo1.pdf
|volume=Vol-1628
|authors=Alejandro Montes García,Natalia Stash,Marc Fabri,Paul De Bra,George H. L. Fletcher,Mykola Pechenizkiy
|dblpUrl=https://dblp.org/rec/conf/ht/GarciaSFBFP16
}}
==Adaptive web-based educational application for autistic students==
https://ceur-ws.org/Vol-1628/Demo1.pdf
Adaptive web-based educational application for autistic
students
Alejandro Montes García Natalia Stash Marc Fabri
Eindhoven University of Eindhoven University of Leeds Beckett University
Technology Technology Leeds, United Kingdom
Eindhoven, the Netherlands Eindhoven, the Netherlands m.fabri@leedsbeckett.ac.uk
a.montes.garcia@tue.nl n.v.stash@tue.nl
Paul De Bra George H. L. Fletcher Mykola Pechenizkiy
Eindhoven University of Eindhoven University of Eindhoven University of
Technology Technology Technology
Eindhoven, the Netherlands Eindhoven, the Netherlands Eindhoven, the Netherlands
p.m.e.d.bra@tue.nl g.h.l.fletcher@tue.nl m.pechenizkiy@tue.nl
ABSTRACT their study. This toolkit3 is offered as an Adaptive Web-Based Ap-
Adaptive web-based applications have proven successful in reduc- plication to autistic students, but also to non-autistic students that
ing navigation and comprehension problems in hypermedia docu- might find it useful.
ments. In this paper, we describe a toolkit that is offered as an adap- The adaptive functionality differentiates in how the information
tive Web-based application to help autistic students incorporate to site presents itself to autistic and non-autistic students, but in the
high education. The toolkit has been developed using a popular end the toolkit provides the same information to everyone. The
CMS in which we have integrated a client-side adaptation library. adaptive functionality offered in the toolkit presented here is based
The toolkit described here was tried out during workshops with on learning styles and user history.
autistic students at Leeds Becketts University to gather (mostly Adaptive Hypermedia is a research field that can be traced back
qualitative) feedback on the adaptation and privacy aspects of the to the nineties [3, 4]. It has become more complex since then and
Autism&Uni platform. That feedback was later used to improve several frameworks have been developed. They aim to ease the
the toolkit. development of these kind of applications. Some good examples of
those frameworks are AHA! [6] or GALE [17].
Learning styles refer to the different ways a person can learn.
CCS Concepts There is previous research on adaptation to cognitive/learning styles
•Information systems → Web applications; •Social and profes- and how these can be incorporated into Adaptive Hypermedia Sys-
sional topics → People with disabilities; •Security and privacy tems and e-learning platforms [16, 18]. While adaptation to learn-
→ Privacy protections; ing styles is useful in every e-learning platform, this is specially im-
portant in our use case scenario with autistic students as we showed
in our previous work [5, 13]. Autistic students show problems link-
Keywords ing concepts and therefore, adapting the content to their specific
adaptation, autism, learning styles, privacy needs can be of great help.
In this demonstration we will showcase the integration of WiBAF
and WordPress in several ways. We will show how we apply adap-
1. INTRODUCTION tive hypermedia and learning styles to a toolkit targeted at helping
In this paper, we demonstrate an adaptive Web-based application autistic students succeeding in their transition from high school to
developed for the Autism&Uni1 project. It has been created with university. However during the demo session we will also show-
a tool that combines a popular CMS, namely WordPress2 , and a case some parts described in our previous work on authoring of
library called WiBAF [12] that enables client-side adaptation and adaptive web-based applications with our tool [14].
that is being developed at the Eindhoven University of Technol- The remainder of this paper is structured as follows: We describe
ogy (TU/e). Although WiBAF + WordPress integration is generic, what autism is and why adaptation to adults on the autistic spectrum
meaning that it can be used for creating adaptive applications in is important in Section 2 and then we describe the specific actions
different domains, so far we have only used it in the educational taken in our toolkit in Section 3. Section 4 measures the overhead
context. Apart from the Autism&Uni project we used it in our first that this integration causes compared to a CMS without any adap-
year course on Design-Based Learning Hypermedia for creating the tation. Finally we conclude and propose future work in Section 5.
“First Aid Kit” for students entering the university.
Autism&Uni is aimed at widening access to higher education for
autistic students by providing a toolkit that can help them overcome 2. ADAPTATION FOR AUTISTIC STUDENTS
the challenges they may face when going to university. The goal is Adaptation for autistic students is first and foremost concerned
to give students a taste of how higher education works and how with adapting to differences in cognitive abilities. Within this project
to cope with the physical university environment before they start in particular, we focus on comprehension between autistic and non-
1
autistic students. Autism is often described as a “spectrum disor-
http://autism-uni.org/
2 3
https://wordpress.org http://www.autism-uni.org/toolkit/
der” because the condition affects people in many different ways For this specific use-case, we also consider some factors related
and to varying degrees. In our previous work [5] we discussed the to the context namely, where the student is and what time it is. The
“spectrum” and indicated that within the project we are mainly con- reason for this is that autistic students often feel lost, they need re-
sidering students who are of average or advanced intellectual abil- minders that tell them where they have to go inside the campus. We
ities, academically capable and able to communicate effectively in are implementing a feature so that they can import events from their
most situations. Traditionally this group would have been referred Google Calendar. The tool will show a reminder when the student
to as being “high-functioning” or having Asperger syndrome [2, needs to go to a lecture and a link with the instructions to get to the
10], although these labels are both imprecise and considered offen- room where she needs to be. This is still under development and
sive by many autistic people and other stakeholders [9]. Therefore, not yet part of the generic platform, therefore we will not describe
in the remainder of this paper we will use the term “autistic stu- it further. We mention the notification feature because it needs to
dents”. be developed in order to really help autistic students.
Autism is often called a “hidden disability”, with few physical All the information written by experts on autism has been di-
signs of the student having difficulties until a crisis is reached. vided in learning objects. A learning object can be defined as a
This can make it difficult for autistic students to have their needs piece or a set of content with a specific learning goal. In order to
fully met, as they experience doubts about their condition, demands effectively display the content from our learning objects, we have
to justify their requirements from staff as well as from student broken it down into small pieces or fragments with some semantic
peers [1]. And this is in addition to the social and communication meaning, from which the student can learn something. In our case,
difficulties common to autism. we show an introduction first, we show also a comic strip or an
With the right support and encouragement, however, autistic stu- image that shows quotes of students about the topic of the learning
dents can develop their full potential at university and lead full and object, establishing a context for it. Then some background infor-
independent lives. One of the most accomplished and well-known mation is provided to justify the learning object. After that we talk
adults with autism in the world is Temple Grandin, an American about how the learning object being described is important for the
professor of animal science at Colorado State University (see her reader and what she should do. We close the learning object with
TED talk4 ), but this is just one of many more examples. some additional tips, questions to think about and some follow-on
Comprehension disturbance makes it difficult for autistic people reading. Each learning object can also have an alternative video
to make semantic connections between the topics that they study version as well as pre and post-requisites.
while generally speaking non-autistic people do not have this prob-
lem. Autistic people are good at “seeing trees in the forest”, they 3. ADAPTATION EFFECTS
can spot details but may have difficulties “seeing the whole forest”
After running workshops with autistic students at the Leeds Beck-
and developing critical thinking skills [2]. On the other hand, many
ett University, and trying different alternatives like stretchtext, or
autistic people have specific strengths such as an ability to maintain
reordering of parts that call users to do an immediate action, we
intense focus, to think rationally and logically, to adopt unconven-
have concluded that the following are the most valuable adaptation
tional angles in problem-solving or to spot errors that others may
effects.
overlook [7, 11]. All these are valuable attributes in higher edu-
cation students, and the strengths of autistic people as profession-
• If the user is more visual than verbal, the video version of
als with a high work ethic are increasingly recognized by business
the content will be shown at the top of the learning object.
world-wide, e. g. in technical and scientific areas and also in the
Otherwise it will be moved to the last (bottom) section of the
humanities and the arts5 .
learning object.
In order to provide effective adaptation, we utilize the specific
characteristics and preferences of the user in three different learn- • If the user is more global than analytical, all the sections of
ing styles [8], i. e. where is the user located in the: visual vs. verbal the learning object will be displayed on a single page. On the
axis, global vs. analytical axis and active vs. reflective axis. We other hand, if the user is more analytical than global, each
make use of the user history as well. These variables together with section will be shown sequentially in one page, in a similar
the adaptation effects provided by the toolkit, have been described way as in a slide-show.
in our previous work [5].
A secondary but also important aspect of performing adaptation • Some learning objects have pre-requisites, they require knowl-
in the presence of autistic users is the heightened awareness of (and edge of some items to be completely understood. These pre-
anxiety for) the user modelling involved, in comparison with peo- requisites are shown when the user starts to read a new learn-
ple outside the autistic spectrum. Autistic students do not only ex- ing object, unless she already fulfilled those pre-requisites.
perience anxiety when entering an unknown environment but also In that case, the pre-requisites block is not displayed in the
when they realize that their personal and possibly sensitive data are learning object.
stored on a external computer that they cannot access, when they
do not feel their data is kept private or they cannot control it. Fortu- • The learning objects from which the user has already com-
nately WiBAF stores all user data on the client side (using browser pleted are marked as visited. This is done in order to help
storage) by default. Autistic users may choose to keep this setting, users remember which items they have already read and which
thus guarding their privacy, while other users may opt to share their ones they still have to read.
data in order to enable the server side to perform group adaptation.
Some of these effects are hard-coded in our adaptation and mod-
(We currently do not offer group adaptation but we do offer the user
elling files, as they refer to the general structure of the content and
model sharing option.)
they are independent of the number of learning objects and their
4
http://www.ted.com/talks/temple_grandin_the_world_needs_all_ content. Other effects are created dynamically by our framework,
kinds_of_minds when new learning objects are created.
5
see http://goo.gl/71YG14 accessed last time on Tue 16th February, Figure 1 shows two learning object with two different versions
2016 of each one. The first learning object is shown on the top-left, the
Figure 1: Versions of two different learning objects for different types of students (top images), or with different prior knowledge
(bottom images).
version for a global-visual student is depicted and the same learn- several pages of different types (learning objects, the home page,
ing object for an analytic-verbal student is shown on its right. On etc.). We did so by using a plugin called P36 . Then we compared
the bottom part of the image, a learning object with pre-requisites it to an unmodified WordPress with the default theme, without any
is shown. On the left, the student has not read the pre-requisites plugins (except P3).
yet, on the right, the student has fulfilled these pre-requisites, and The adaptive version of WordPress takes 176 ms to load the
therefore they are not shown again. site, while the not adaptive version takes 167 ms, that is an over-
head of just 9 ms. In the detailed analysis we see that indeed the
WiBAF plugin is executed in 9.1 ms while the theme is handled
4. TECHNICAL PERFORMANCE slightly more efficiently in our WordPress than the default Word-
Technical performance (speed) is often a problem with adaptive Press theme.
hypermedia systems, which is rarely reported. Some initiatives, We also measured the time the client code uses (for user mod-
including the general-purpose adaptation engine GALE developed elling and adaptation). We used the Google Chrome profiler to
at the Eindhoven University of Technology [17] pay special atten- measure the total JavaScript execution time with our custom Word-
tion to efficiency and can withstand a stress test using hundreds Press. In this measurements we include not only WiBAF but also
of simultaneous users. Most of the performance problems stem JQuery7 , a popular JavaScript library that is used to manipulate the
from the adaptation that needs to be computed in the split second DOM structures and it is required by WiBAF. and compared that to
between the user clicking on a link and the browser presenting the the default WordPress (not performing any user modelling or adap-
“next” page. Since WiBAF performs user modelling and adaptation tation). The execution time of the JavaScript code in our WordPress
inside the browser it does not face a performance problem because was 487 ms, against 304 ms for the non-adaptive version. There-
of large numbers of simultaneous users. However there is still a bit fore the overhead we introduce in the client is 183 ms. More than
of overhead in the server because in the WiBAF+WordPress com- one half of that time (69 ms) is caused by the use of the Indexed
bination WordPress has to serve (and sometimes generate) code for DB to store and retrieve data from the user model.
the browser to execute. We are interested in seeing how both tasks In total, we quantify that making a WordPress adaptive costs
affect the overall performance of the modified WordPress. 192 ms per request. The page will be served with a delay of 9 ms
We ran a performance test on a MacBook Air laptop together and adapted in 183 ms. In total the page is served and adapted in
with an Apache Server and a MySQL database. The server was 663 ms. According to a study in 2004 [15], users consider a wait-
running WordPress version 4.4.2. While this is not the most realis- ing time of around 2 seconds acceptable. Since then people may
tic setup, it gives us an intuition on what the performance could be
6
in a bad scenario (a single machine with limited capabilities) We https://wordpress.org/plugins/p3-profiler/
7
have measured the time it takes for our modified WordPress to load https://jquery.com/
have grown more impatient. But when considering these perfor- [5] P. De Bra, A. Montes García, and N. Stash. Novel adaptive
mance numbers you should consider that we ran an unlikely sce- features of the Autism&Uni toolkit for students on the
nario where the web server with WordPress, the mySQL database autism spectrum. In Proceedings of the INTED 2016
and the (Chrome) browser with adaptation code were all running Conference. IATED, 2016.
on the same (relatively slow) computer. [6] P. De Bra, D. Smits, and N. Stash. The design of AHA! In
Proceedings of the seventeenth conference on Hypertext and
hypermedia, pages 133–134. ACM, 2006.
5. DEMONSTRATION SCENARIO AND FU- [7] K. P. Grant and G. Davis. Perception and apperception in
TURE OUTLOOKS autism: rejecting the inverse assumption. Philosophical
In this demo we showcase an adaptive web-based application de- Transactions of the Royal Society of London B: Biological
veloped with a framework consisting on a CMS and an adaptation Sciences, 364(1522):1393–1398, 2009.
library. This application is aimed at supporting autistic students in [8] J. W. Keefe. Learning style: An overview. Student learning
higher education, but it is available to everyone. The application styles: Diagnosing and prescribing programs, 1:1–17, 1979.
takes advantage of the use of learning styles and user history, but [9] L. Kenny, C. Hattersley, B. Molins, C. Buckley, C. Povey,
extra functionality can be added, such as notifications or a progress and E. Pellicano. Which terms should be used to describe
bar e. g. “you have studied only 5% of the material and there are autism? perspectives from the UK autism community.
only 2 days left before the exam”, etc. . . Extra adaptive features Autism, page 1362361315588200, 2015.
can include adaptive testing or selection of navigation tools - more [10] A. Klin, D. Pauls, R. Schultz, and F. Volkmar. Three
independent students (with field-independent learning style) can be diagnostic approaches to asperger syndrome: Implications
provided with a search option while less independent students (with for research. Journal of Autism and Developmental
field-dependent style) can be provided with a “Next” button that at Disorders, 35(2):221–234, 2005.
each step will be bringing them to the most suitable material. While [11] T. Lorenz and K. Heinitz. Aspergers–different, not less:
in the current version we support other media, like videos, those are Occupational strengths and job interests of individuals with
yet scarce and we expect that content providers make more in the asperger’s syndrome. PloS one, 9(6):e100358, 2014.
future. This will give us more adaptive capabilities.
[12] A. Montes García. WiBAF: Within Browser Adaptation
It is important that concepts of privacy, information sharing and
Framework. In Extended Proceedings of the 22nd
storage locations are communicated in a clear, non-technical and
Conference on User Modeling, Adaptation, and
unambiguous way. Initial usability tests of the settings screen were
Personalization. CEUR-WS, 2014.
carried with autistic students. Trial participants did not understand
[13] A. Montes García, N. Stash, and P. De Bra. Adaptive
the control these settings offered them. Inadequately implemented
applications to assist students with autism in succeeding in
privacy settings, are likely to increase anxiety rather than alleviate
higher education. In Proceedings of the 23 rd conference on
it for the students that participated in our trials. Therefore we need
User Modeling, Adaptation and Personalization, 2015.
to find a way to improve the scrutability of our user profile.
[14] A. Montes García, N. Stash, M. Fabri, P. De Bra,
G. H. L. Fletcher, and M. Pechenizkiy. WiBAF into a CMS:
6. ACKNOWLEDGMENTS Personalization in learning environments made easy. In 6th
This research is supported by the WiBAF project and the Life- International Workshop on Personalization Approaches in
long Learning Programme (project no. 10018300 Authew 539031- Learning Environments, 2016.
LLP-2013-1-UK). This publication reflects the views only of the [15] F. F.-H. Nah. A study on tolerable waiting time: how long
authors, and the Commission cannot be held responsible for any are web users willing to wait? Behaviour & Information
user, which may be made of the information contained therein. The Technology, 23(3):153–163, 2004.
authors thank the Autism&Uni project team, TU/e psychologists [16] M. d. P. Paule Ruiz, M. J. Díaz Fernández, F. O. Soler, and
specialising in autism, TU/e students with autism who participated J. R. Pérez Pérez. Adaptation in current e-learning systems.
in interviews with us, Stichting Handicap+Studie8 and Autastic!9 Computer Standards & Interfaces, 30(1):62–70, 2008.
for their valuable input. [17] D. Smits. Towards a Generic Distributed Adaptive
Hypermedia Environment. PhD thesis, Eindhoven University
of Technology, adaptive version:
7. REFERENCES http://gale.win.tue.nl/thesis/, ISBN 978-90-386-3115-8,
[1] K. S. Adams and B. E. Proctor. Adaptation to college for 2012.
students with and without disabilities: Group differences and [18] N. Stash. Incorporating Cognitive/Learning Styles in a
predictors. Journal of Postsecondary Education and General-Purpose Adaptive Hypermedia System. PhD thesis,
Disability, 22(3):166–184, 2010. Eindhoven University of Technology, ISBN
[2] T. Attwood. The Complete Guide to Asperger’s Syndrome. 978-90-386-1050-4, 2007.
Jessica Kingsley Pub., 2014.
[3] P. Brusilovsky. Methods and techniques of adaptive
hypermedia. In Adaptive hypertext and hypermedia.
Springer, 1996.
[4] L. Calvi and P. De Bra. Improving the usability of hypertext
courseware through adaptive linking. In Proceedings of the
eighth ACM conference on Hypertext. ACM, 1997.
8
http://www.handicap-studie.nl/
9
http://royhoutkamp.nl/