WtRSPersonalisationJulyReport - LKLDev

zurichblueInternet και Εφαρμογές Web

21 Οκτ 2013 (πριν από 3 χρόνια και 8 μήνες)

70 εμφανίσεις

Luckin, R., Underwood,

J. and Charlton, P. 2012

‘Knowing you, Knowing me: There is something we can do’

. Many learning theorists believe that the key to learning is that learners and their
teachers (mentors or peers) know enough about each other to know that they share a sufficiently
similar definition of the problem they are tackling. The learner needs to
be able to demonstrate
where and when they need help and the teacher needs to be able to offer that help and guidance
when and where it is required.
Learners differ physically, emotionally and cognitively, and in their
ability to understand what they know
and how they can progress. Recognising these differences can
help to ensure that everyone achieves their full potential, by working on tasks and activities that are
appropriate for them.


process of

learning and teaching
to recognise indiv
needs improves learning outcomes and can be achieved in many ways, including through helping
the learner to understand more about themselves and how to seek and use assistance from others,
as well as through teachers targeting teaching in the most ap
propriate way for the learners in their
charge. Technology can help in this process in a number of ways.

In this brief document we use
illustrative examples to indicate some of the ways in which technology can help and some of the
issues and questions that

are highlighted by work to date.
Our aim is to provoke thought and

to progress these issues further.

Technology can, for example, support

through improving the use of learner time by
enabling learners to work at their own pace, rec
eive targeted feedback, and be supported in their
learning without always relying on teacher presence. ‘Smart’ learning technology systems can
deliver such learner control but they may also employ models of learners and pedagogic strategies
to seek to enga
ge learners and push them when necessary. Throughout the last decade various
intelligent techniques that contribute to the personalisation of learning have been developed and
empirically shown to be effective (Dimitrova, 2010). Techniques can now be deploy
ed online and to
personal and portable devices within and beyond formal educational settings and consequently can
also contribute to both the flexibility of learning and to greater inclusion. Techniques include:

Modelling the learner’s cognitive states to
provide individualised learning (VanLehn, 2005);

Using tutoring dialogues to deepen learning experiences (Litman, 2009);

Using open learner models to promote reflection and self
awareness (Bull & Kay, 2007;
Dimitrova, McCalla & Bull, 2007; Mitrovic & Marti
n, 2007);

Adopting meta
cognitive scaffolding to increase learner motivation and engagement (Harris,
Bonnett, Luckin, Yuill & Avramides, 2009).

Technology can also increase the flexibility of learning to

improve the use of both learner and
teacher time. Ma
ny systems are now web
based and researchers are exploring the use of mobile
devices to deliver adaptive materials for more flexible anytime anywhere learning. Social and
collaborative aspects of learning are increasingly important research themes and syst
ems that
monitor group work and provide effective intelligent support for collaboration, both at a distance
and face
face, are currently being developed (e.g. Upton & Kay, 2009).

Technology can also increase Inclusivity by helping to engage disengaged l
. For example,
adaptive games can deliver more engaging learning experiences (Johnson, 2010) and novel user
interfaces (e.g. speech and gesture recognition), can offer opportunities to engage learners with
widely differing needs. Some ‘smart’ system
s have demonstrated strong results for disadvantaged
populations (Sarkis, 2004), and researchers are also concerned to develop methods that enable
learners, including children (Good & Robertson, 2006) and those with specific needs (Porayska

Luckin, R., Underwood,

J. and Charlton, P. 2012

Pomsta, Bernard
ini & Rajendran, 2009), to participate in the design of systems that meet these
users’ particular requirements.

With more semantic
aware computing technologies, e
learning is expected to be more intelligent in
the new era of Educational Semantic Web
(Anderson & Whitelock, 2004). Roschelle and Pea (2002)

propose that Wireless Internet Learning Devices can offer further affordances that lead to learning
activities that deviate significantly from conventional classroom
based CSCL activities and in
on lead to new ways of aggregating activities coherently across many students, introducing
new ways of conducting the class. They propose that ‘act becomes artefact’. Act becoming artefact
is not just about changes in the way teacher and students engage wi
th technology in and outside
the classroom but increases the knowledge and data available to be shared, explored and

Understanding you, Understanding me

Accurate analysis and assessment can support the process of personalizing learning. The proce
ss of
gaining insight into what a learner understands is a part of effective learning and teaching. If
learners attempt tasks and activities that are too complex and remote from their current
understandings, they are likely to fail; if they attempt tasks t
hat they can complete with ease they
may not progress as they should. Teachers can gain insight into learners’ current understanding
through observation of learner behaviour and performance, through their past experiences of
working with learners and throu
gh the processes of analyzing information about learners, such as
test scores, portfolios or interaction analysis. Learners can likewise gain awareness of their own
level of understanding and learning needs and through this become more effective learners.

Technology that models learners and adapts dynamically to their needs can scaffold learning, and it
can help other people, such as teachers and parents to scaffold learning. Originally much of the
work done on ‘smart’ technologies, such as Intelligent Tut
oring Systems was done in laboratories.
However recent decades have seen a move
into real world with large
scale deployments
demonstrating significant impacts for particular subjects and setting. Furthermore, tremendous
technological advances, for example
in mobile systems and social networks, have been made and
technologies, powerful enough to support sophisticated techniques such as user modelling and
speech recognition are now pervasive throughout much of society and our daily lives. These
successes rely

increasingly upon the key task of understanding what the learner understands and
what support they therefore need.

The increased capacity for data capture, analysis and dissemination offered by modern technology
has prompted advances in e
assessment. For
example, the use of e
voting systems (Hanley and
Jackson, 2006), learner e
portfolios (Kimbell, 2008), diagnostic testing environments which offer
adaptive assessment data for teachers and students over time (Winkley, 2010, Ripley, 2007, Bull
and Kay, 2007
, Zapata
Rivera et al., 2007), the use of handheld devices to capture data (Bennett
and Cunningham, 2009), activity logs, timestamps, version tracking, target
setting (Jewitt et al.,
2010), self
guided learning (Sainsbury, 2009), learning journals, and so
on. Less well developed, but
increasingly emergent, are new forms of e
assessment, which take into account opportunities for
supported peer, collaborative, and self
guided learning (for both teachers and learners)
using online social networks an
d read
write technologies such as web 2.0. (Luckin et al., 2008,
Elliott, 2007).

Intelligent context
aware tools have now been designed to support teachers in
creating designs that includes such technology activities as part of their teaching and learning
(Charlton et al., 2012).

Luckin, R., Underwood,

J. and Charlton, P. 2012


is an emerging discipline concerned with developing methods to explore
data from educational settings and better understand students and the settings they learn in

Educational Data Mining and Learning Analytics offer the
promise to reveal new challenges and opportunities. The rich data captured by these systems could
provide researchers with new opportunities to
evaluate models of learning and develop.

The wide
and increasing range of learner interactions with or through technology and with other people can
be recorded and made available for data mining techniques. This has produced a new interest in
educational d
ata mining to ensure the development of technologies capable of taking advantage of
this increased information. Data mining techniques are used to build models from large data sets to
make predictions, for example, about the features of particular maths pr
oblem statements that
encourage learners to ‘game’ the software system (Baker et al. 2009) or about the effectiveness of
particular combinations of problem types and tutoring approaches (Feng et al. 2009).

Modelling you, Modelling me

Learner models in the

context of this paper refers to the software module within a system that
enables the system to behave in an adaptive way, offering differentiated feedback for example. The
learner model is ‘smart’ programme code that records information about learners and

updates itself as learners’ interactions with or through the technology offer greater insights into
their current understanding and/or attitudes. The precise purpose and nature of learner models
vary greatly. In some cases, such as those wher
e biometric data are used to build the learner model,
the model intends to be an accurate representation of the learner’s state on the measures selected.
For example, the AutoTutor (
) is an I
TS offering learners an animated
agent that holds a conversation with them in their native language about scientific reasoning across
a range of subjects. In other cases, learner models can be based on a learner’s own reports of their
feelings at a partic
ular moment in time (Craig et al. 2004; Beal et al. 2006). Multiple data streams
have also been used to combine both self
report and biometric data to build a learner model
(Kapoor & Picard 2005; Kapoor et al. 2005).

Some models may strongly focus on a sm
all topic. For example, a model may accurately reflect a
learner's success in completing a set of mathematical calculations or physics problems only in a
particular setting. The Andes ITS developed by Van Lehn and colleagues at the University of

(Van Lehn et al, 1992; 2005) is a mature software system used by hundreds of university
physics students. It has been through a series of evaluations since 1999 to demonstrate its efficacy.

Learner modelling continues to evolve as researchers develop ne
w techniques supported by
increasingly sophisticated technologies. The increase in digital information available for some
elements of subject content in an educational system has grown enormously and has resulted in
the development of meta
tagging as a way

of describing pieces of information. There has also been
growth in approaches exploring ways in which pieces of information can be used as ‘learning
objects’. Large schemas of meta
tag descriptors have been constructed to describe these content
elements a
nd learning objects. If the descriptors are compatible, the aim is to build software
systems that can access all the content elements with compatible description formats to find those
most suitable for a learner or group of learners. The size of the conten
t elements varies from a
single word of text to a movie clip. This proliferation in digital content tagging has been
accompanied by an increased focus on ways in which a software system’s model of the learner,
sometimes now referred to as their ‘profile’,
can be constructed to match learners needs to
appropriate content elements. This work is increasingly linked to developments in the semantic
web (Aroyo et al. 2006; Brusilovsky & Peylo 2003; Brusilovsky et al. 2007).

Luckin, R., Underwood,

J. and Charlton, P. 2012

Some learner models, such as those in
AutoTutor, Andes, Ecolab and PAT, are kept private from the
learner, while others are open to the learner and even other people. Some open learner models
simply allow the learner to view the software system’s model, some allow learners to edit the
model, a
nd others allow the learner to share the model with other people. Kay (2009) recently
proposed an important extension to this open learner model approach. Kay recognized the
potential for change brought by pervasive and ubiquitous computing and offered a v
ision of a
lifelong learner model, which is controlled by the learner but exists independently of particular
applications and technologies. The author identified technical issues, such as interoperability and
the huge quantities of interaction data availab
le for analysis, as well as human concerns, such as
control, privacy, and augmented cognition, as the key challenges that need to be addressed to fulfill
this vision.

Learner modelling is not limited to modelling individual learners. There is enormous in
terest and
active research in the field of computer support for collaborative learning. The work of Soller (2002,
2007), for example offers a computer science modeling that illustrates the power of collaborative
and dynamic matching techniques supporting d
ifferent types of learning partnerships and
knowledge exchange.

Evolving with you, Evolving with me

We have computers that can fly planes, model countries’ economies, search the internet and
predict what we want to type into a text message. We’re also deve
loping computers with human
qualities such as the ability to understand language and recognise visual images. Tailor
learning is within our grasp as ‘smart’ technology empowers computers to deal with the fact that
everyone is different (
System Upgrade
, 2012
). And people learn how to use technology in ‘smart’
ways to adapt it, re
configure it and re
purpose it to meet their and others’ individual needs.

A possible vision for the future?

Teaching and learning environments, incorporating sophisticated
user models
, will provide flexible and adaptive assistance, personalised to individual learners needs.
Such, assistance will be domain independent and will include support for “soft skills, such as
creativity, critical thinking, communication, collaboratio
n, information literacy, and self
and will be open
ended and exploratory in nature, allowing learners to question and enhance their
understanding about areas of knowledge in which they are motivated to learn” (Woolf, 2010 p58).
Personalised supp
ort and feedback

will be available to learners across subjects and across formal
and informal settings and throughout their lifetimes. Open user models will prompt learners to
reflect on their learning and how they learn. Such systems, accessible ubiquitou
sly through
and distributed rich interfaces
, will improve flexibility and inclusion and help dissolve the
boundaries between sites of learning and connect learning across subjects.

Future intelligent teaching and learning environments may be
, using

techniques to learn about students and improve their own performance by evaluating how they are
used and associated with learning outcomes. However, such environments will not aim to replace
teachers but rather work with teac
hers both being informed by teachers’ input and informing
teachers’ decisions and actions. These environments will take into account the needs and interests
of learners and will employ
novel interfaces

and techniques from games to deliver highly engaging
nd accessible learning experiences.

will augment the real world with interactive
representations that support learning through interaction with
tangible physical world and mixed
reality interfaces

while making perceptible, phenomena that are too large
, too small, too quick and
too slow to observe in the real environment. Simulations and micro
worlds will support learning
through exploration and will provide appropriate and personalised feedback. These environments
will enable learners to move seamlessl
y between real and virtual worlds and will span formal and

Luckin, R., Underwood,

J. and Charlton, P. 2012

informal activities and will better connect learning across these worlds. Intelligent teaching and
learning environments will also use
networking tools

to better support social and collaborative
arning, introducing suitable collaborators, guiding learners towards effective collaboration and
helping teachers to monitor and support group work. Such
networking tools

“will facilitate
individuals to learn within communities, communities to construct kn
owledge, and communities to
learn from one another” (Woolf, 2010 p 51.). In these communities, learner roles will be more fluid,
with teachers often acting as facilitators and opportunities for learners to participate as producers
and teachers as appropria
te to their knowledge and interests. Ubiquitous access to such
communities will contribute to diminishing boundaries between formal and informal learning.


techniques will be used to discover patterns in the vast amounts of data

become available from such integrated intelligent learning environments and will support
identification of success factors and problems. These analyses will inform and guide stakeholders,
including teachers, parents and policy makers. Teachers and learner
s will be supported with easily
accessed, more accurate and timely information and analysis of individual and group learning. This
information will support teachers in making strategic decisions and providing appropriate guidance,
and in the continuous ass
essment of learning. Appropriate information may also be shared with
parents enabling them to provide additional help and motivation.

Appendix I

Table 1 Example ‘Mainstream’ Intelligent Learning Environments

For Learning Foreign Culture & Language

Tactical Language & Culture Training System


Alelo’s Tactical Language and Culture Training System
uses a virtual game based environment and interactive lessons to provide foreign language and culture
training. TLCTS employs AI techniques to process learners’ speech, engage in dialogue and evaluate
erformance and has been used by more than 40,000 learners worldwide with independent evaluations
showing significant gains in learners’ knowledge of language and culture and greater self
confidence in
communicative ability (Johnson & Valente, 20009). See

for more information.

For Learning Maths

Cognitive Tutors

Carnegie Learning’s Cognitive Tutors use AI techniques to
provide learners of Maths with
individualized attention and tailored material based on continual assessments (Carnegie Learning, Applying
Cognitive Science to Education). Cognitive Tutors aim to act like human tutors constantly monitoring learner
actions a
nd guiding learners towards correct solutions, providing help on demand and in response to common
mistakes and giving meaningful feedback to students on their acquisition of skills (Carnegie Learning, The
Cognitive TutorTM: Successful Application of Cognit
ive Science). Cognitive Tutors are used in many schools in
the US and elsewhere and several evaluations of Cognitive Tutors have been conducted (see Carnegie
Learning, 2010). Evaluations have demonstrated that Cognitive Tutors can improve problem solving a
critical thinking skills (Koedinger, Anderson, Hadley & Mark, 1997), improve performance on exams (Sarkis,
2004), improve student attitudes to mathematics (Morgan & Ritter, 2002), and show strong results for
disadvantaged populations (Sarkis, 2004). See


for more information.

Wayang Outpost

Wayang Outpost is an intelligent tutoring system that helps learners pr
epare for maths tests
and helps teachers in their assessment of students’ strengths. Wayang can provide interactive hints leading to
the solution for a problem. As the student progresses through problems the system adjusts instruction using

Luckin, R., Underwood,

J. and Charlton, P. 2012

strategies that are effective for each student. An evaluation of Wayang (Beal, Walles, Arroyo,
Woolf, 2007) shows significant improvements on pre to post
tests and suggests the greatest benefits are for
weaker students and those who make most use of the mu
ltimedia help features. For more information and to
register to try the system out see


ActiveMath is an adaptive
learning environment for Mathematics that applies AI techniques to
automatically assemble individualised courses. ActiveMath can generate courses adapted to the learner’s
curriculum, language and field of study, as well as to her cognitive and educational
needs and preferences
such as learning goals, preferred style of presentation, goal
competencies, and mastery
level (Melis &
Siekmann, 2004). ActiveMath includes interactive exercises that can provide feedback and hints of different
kinds in response to le
arner input. The ActiveMath system has been used and evaluated in classrooms and
universities in various European countries for several years (see
). A Europe
wide formative and summative evaluation
investigated usability and learners’ opinions of automatically generated courses; results indicated that
learners appreciated the generated courses, felt these were personalized and that the ge
nerated courses
helped learners to find their own way of learning (Ullrich & Melis, 2010). For more information about the
ActiveMath system, research and access to a demonstration version see

For Learning Physics

Andes Physics Tutors

Andes is an intelligent homework helper for Physics. Students enter steps in solving a
problem, such as drawing vectors, drawing coordinate systems, definin
g variables and writing equations and
Andes provides feedback after each step (VanLehn et al, 2005). Andes encourages learners to use good
problem solving strategies, provides immediate feedback on learner input and offers different kinds of
assistance depending on the kinds of error learners make. Andes has been used successfully
since 2000 in the US Naval Academy and is in use elsewhere at college and high school level (see

for more information). Evaluations in real classrooms over five years show that
Andes is significantly more effective than doing pencil and paper homework and at a low cost, with students
spending no extra time doing homework, and with no need f
or teachers to revise their classes in order to
obtain these benefits (VanLehn et al, 2005). The Andes Physics Tutor is in use on an
Open Fr
ee Physics course

provided through the
Open Learning Initiative

For Learning Programming and Database skills

Database Place


SQLTutor provides adaptive individualized instruction that helps learners’
master key concepts in database courses using student and pedagogical models. SQLTutor has been in large
scale use with several thousand users (Mitrovic et al., 2006), evaluated on
numerous occasions and refined
for more than a decade (see
SQLTutor Evaluations
). Evaluations of SQLTutor have demonstrated the need for
feedback to b
e personalized to individual students’ needs (Martin & Mitrovic, 2006) the value of both
negative and positive feedback, as opposed to only negative feedback, with students receiving both forms of
feedback requiring significantly less time to solve the sam
e number of problems, in fewer attempts and
learning the same number of concepts as students in the control group (Barrow, Mitrovic, Ohlsson, & Grimley,
2008). SQLTutor is one of a number of constraint
based Intelligent Tutoring Systems (ITSs) produced by
Intelligent Computer Tutoring Group (ICTG) at University of Canterbury (New Zealand). These ITSs have
proven effective not only in controlled studies but also in real classrooms, and some of them have been
commercialized (Mitrovic et al, 2009). SQLTuto
r and other adaptive tutors for database skills are available
through Addison
Database Place
. ICTG are also working towards making it easier for teachers and
domain exper
ts to develop ITSs. ASPIRE (Authoring Software Platform for Intelligent Resources in Education)
assists users in developing and delivering online constraint
based tutors and is freely available to all New
Zealand Government
owned Tertiary Institutions. For

more information about Intelligent Tutors developed by


: Episodic Learner Model

The Adaptive Remote Tutor
ART is an intelligent interactive system
that supports learning to programme in
ART provides all learning material online in the form of an

Luckin, R., Underwood,

J. and Charlton, P. 2012

adaptive interactive textbook… …ELM
ART provides adaptive navigation support, course sequencing,
individualized diagnosis of student solutions, and example
based problem
solving support
.” (Weber &
Brusilovsky, 2001, p.351). Provision of the system online was found to greatly contribute to flexibility and
efficiency of learning with students accessing the system from both home and university locations, with many
students completing the co
urse in very short periods of time and achieving very good results in the final
programming task (Weber & Brusilovsky, 2001). One AIED approach employed in ELM
ART is adaptive link
annotation. Adaptive annotations augment hyperlinks with personalised hints

that can help guide learners to
the most personally appropriate learning content at any given moment. Adaptive annotation has been
adopted by many systems and “(e)mpirical studies of adaptive annotation in the educational context have
demonstrated that it

can help students to acquire knowledge faster, improve learning outcomes… (and)
…significantly increase student motivation to work with non
mandatory educational content” (Brusilovsky,
Sosnovsky & Yudelson, 2006, p.51). ELM
ART has been used over many yea
rs by hundreds of students to
support delivery of a university course. You can try out ELM
ART at

KnowledgeSea II
Knowledge Sea II is a mixed corpus C programming resource that bridges the gap between
closed corpus materials in the form of lecture notes and open
corpus materials in the form of links to online
resources f
or C programming. Knowledge Sea II helps users navigate from lectures to relevant online tutorials
by providing links to online material related to search keywords. Search is adapted to the user by taking into
account both the past interactions of the indi
vidual user and the user’s group (other learners). KnowledgeSea
prompts learners to access material related to the user’s search by providing traffic and annotation based
social navigation support. Social navigation support is realised by marking links to
material with icons and
colour codes that indicate the amount of traffic (time spent reading the linked material by other learners) and
positive and negative individual and group annotations of the linked material (Brusilovsky, Farzan, & Ahn,
2006). Evalua
tions of KnowledgeSea II show that pages automatically predicted as important for a learner
were actually rated as important by students and that the adaptive link annotations successfully influenced
learner behaviour, with learners preferentially accessin
g more highly ranked pages and those with link
annotations that indicate higher traffic (Brusilovsky, Farzan, & Ahn, 2006). For more about KnowledgeSea see
. You can register to try the system at

When computational intelligence is used in the design and development of


The use of computers to do reasoning, pattern recognition, learning, or some other form of


A focus on problems that do not respond to algorithmic solutions. This underlies the reliance on
heuristic search as an AI problem
solving technique;


A co
ncern with problem solving using inexact, missing, or poorly defined information and the use of
representational formalisms that enable the programmer to compensate for these problems;


Reasoning about the significant qualitative features of a situation;



attempt to deal with issues of semantic meaning as well as syntactic form;


Answers that are neither exact nor optimal, but are in some sense "sufficient". This is a result of the
essential reliance on heuristic problem
solving methods in situations where
optimal or exact results
are either too expensive or not possible;


The use of large amounts of domain
specific knowledge in solving problems. This is the basis of
expert systems;


The use of meta
level knowledge to effect more sophisticated control of prob
lem solving strategies.
Although this is a very difficult problem, addressed in relatively few current systems, it is emerging as
an essential area of research;



Luckin, R., Underwood,

J. and Charlton, P. 2012



Understanding you, Understanding me

Modelling you, Modelling me

Evolving with you,
Evolving with me


Language and culture

Engage in dialogues with students.

Provides performance feedback

Cognitive tutors


Contextual monitoring and appropriate

Feedback and guidance require



Interactive hints to help prepare for tests

Assists tutors in assessment of students strengths



Build appropriate individual courses based
on different types of knowledge and

Adapts feedback and hints of different kinds of
response to learner input.

Andes Physics


Supports problem solving and promotes
d learning strategies

Offers different kinds of instructional assistance
depending on the kinds of error learners make

Database place

Programming and
database skills

Adaptive individual instructions uinsg both
student and pe
dagogical models

Provides both positive and negative feedback


LISP programming

Using adaptive links to create
individualised diagnosis of the student

Provides personalised hints


C programming

Contextual search
model to support
matching of context.

Prompts learners to access to related material by
providing traffic and annotation based social
navigation support

Supports a potential
path progression by
using past interactions
and user group

Table 1:

ools at a glance

Luckin, R., Underwood,

J. and Charlton, P. 2012


Anderson, T. & Whitelock, D. (2004). The educational semantic web: visioning and practicing the
future of education. Journal of Interactive Media in Education, 2004 , 1, 1


Aroyo, L., Dolog, P., Houben,

J., Kravcik, M., Naeve, A.
, Nilsson, M. & Wild, F. (2006)
'Interoperability in personalized adaptive learning',

Technology & Society
, 9(2):


Baker, R.S.J.d., Yacef, K. (2009) The State of Educational Data Mining in 2009: A Review and F
Visions. Journal of Educational Data Mining, 1 (1), 3

Beal, C. R., Walles, R., Arroyo, I., and Woolf, B. P. (2007). On
line tutoring for math achievement
testing: A controlled evaluation.
Journal of Interactive Online Learning
, 6 (1), pp. 43

Bennett, K. R. & Cunningham, A. C. 2009. Teaching Formative Assessment Strategies to Preservice
Teachers: Exploring the Use of Handheld Computing to Facilitate the Action Research
Process. Journal of Computing in Teacher Education, 25, 99

y, A. Kobsa & W. Nejdl (2007)
The Adaptive Web
, LNCS 4321, Berlin Heidelberg: Springer

Bull, S. & Kay, J. (2007). Student Models that Invite the Learner In: The SMILI Open Learner
Modelling Framework,
International Journal of Artificial Intelligenc
e in Education
, 17(2), pp.

Craig, S.D., Graesser, A.C., Sullins, J. & Gholson, B. (2004) 'Affect and learning: an exploratory look
into the role of affect in learning with AutoTutor',
Journal of Educational Media
, 29: 241


Charlton P., Magoula
s G., Laurillard, D. Enabling Creative Learning Design through Semantic Web
Technologies, Journal of Technology, Pedagogy and Education, Special Issue: The Semantic
Web in Education, July 2012, pp 231

Dimitrova, V (2010). ImREAL project:

Dimitrova, V., McCalla, G., and Bull, S. (2007). Open Learner Models: Future Research Directions

Special Issue of the IJAIED (Part 2).
International Journal of Artificial Intelligence

in Education
17, 3, pp. 217

Elliott, B. 2007. Assessment 2.0: Assessment in the age of web 2.0. Scottish Qualifications Authority
[Online], 28.

Feng, M., Heffernan, N.T., Beck, J. (2009). 'Using learning decomposition to analyze instructional
iveness in the ASSISTment system', in Dimitrova, V., Mizoguchi, R., du Boulay, B. &
Graesser, A. (eds.).
Proceedings of the 14th International Conference on Artificial Intelligence
in Education
. Brighton, UK, pp. 523


Good, J., & Robertson, J. (2006). C
ARSS: A Framework for Learner
Centred Design with Children.
International Journal of Artificial Intelligence in Education
, 16 (4) pp. 381

Hanley, J. & Jackson, P. 2006. Making it click. Technology & Learning, 26, 11

Harris, A., Bonnett, V., Luckin, R., Yuill, N., Avramides, K. (2009). Scaffolding effective help
behaviour in mastery and performance oriented learners. In V. Dimitrova, R. Mizoguchi, B. du
Boulay, A. C. Graesser (Eds.), AIED 2009, IOS Press.
iers in Artificial Intelligence and
, 200, pp. 425

Jewitt, C., Hadjithoma
Garska, C., Clark, W., Banaji, S. & Selwyn, N. 2010. School use of learning
platforms and associated technologies. Coventry: Institute of Education.

Johnson, W.L. (2
010). Serious Use of a Serious Game for Language Learning.

International Journal of
Artificial Intelligence in Education
, 20 (2) pp. 175

Kimbell, R. 2008. e
assessment in project e
scape. Design and Technology Education: an
International Journal, 12.

Luckin, R., Underwood,

J. and Charlton, P. 2012

Kapoor, A. & Picard, R. (2005). 'Multimodal affect recognition in learning environment',
Conf. on Multimedia
, pp. 677


Kapoor, A., Ahn, H.I., Picard, R.W. (2005) 'Mixture of Gaussian Processes for Combining Multiple
Modalities', in
gs of Multiple Classifier Systems, Oza, N. C. Polikar, R. Kittler, J. &
Roli, F. (eds). 6th International Workshop, MCS 2005, June 2005, Seaside, CA
, pp. 86


Kay, J. (2009) 'Lifelong Learner Modelling for Lifelong Personalized Pervasive Learning',
Transactions on Learning Technologies
, 1(4): 215


Koedinger, K. R., Anderson, J. R., Hadley, W. H., and Mark, M. A. (1997). Intelligent tutoring goes to
school in the big city.
International Journal of Artificial Intelligence in Education
, 8, 30


tman, D. (2009).
The Evolution of Natural Language Processing in AIED: Successes and Challenges
Panel on the Evolution of AIED @ AIED09, July, 2009, Brighton, UK

Luckin, R. (2010).
designing Learning Contexts: Technology
rich, Learner
centred Ecologies
Routledge, London.

Luckin, R., Logan, K., Clark, W., Graber, R., Oliver, M. & Mee, A. 2008. KS3 and KS4 learners' use of
Web 2.0 technologies in and out of school

Summary. Coventry: Becta.

Martin, B., Mitrovic, A. The effect of adapting feedback genera
lity in ITS. In V. Wade, H. Ashman,
and B. Smyth (Eds.):
AH 2006
, LNCS 4018, pp. 192
202, 2006.

Pomsta, K. Bernardini S., Rajendran, G. (2009) Embodiment as a means for Scaffolding
Young Children’s Social Skill Acquisition. In
Proceedings of the W
orkshop on Children and
Embodied Interaction: Seeking Common Ground
, 8th International Conference on Interaction
Design and Children (IDC’09), Como, Italy, 2009

Roschelle, J.,

Pea, R. (2002) A walk on the WILD side: how wireless handhelds may change CSCL

Proc. Conf. on Computer Support for Collaborative Learning: Foundations for a CSCL
Community, CSCL '02, pp. 51

Ripley, M. 2007. E

an update on research, policy and practice. Bristol: Futurelab.

Sainsbury, M. 2009. E
assessment for schools:

from innovation to integration. Association for
Educational Assessment. Malta: National Foundation for Educational Research.

Sarkis, H. (2004).
Cognitive Tutor Algebra 1 Program Evaluation: Miami

Dade County Public
. Lighthouse Point, FL: The Relia
bility Group.

Soller, A. (2002)
Computational analysis of knowledge sharing in collaborative distance learning
Doctoral dissertation. University of Pittsburgh, Pittsburgh, PA.

Soller, A. (2007) Adaptive Support for Distributed Collaboration.
The Adaptive
Web. Methods and
Strategies of Web Personalization
, Springer. pp. 573


System Upgrade, 2012. TEL research programme report

Upton, K., & Kay, J. (2009)
. Narcissus: Group and Individual Models to Support Small Group Work.
User Modeling, Adaption, and Personalisation
. LNCS, Vol. 5535/2009, pp. 54

VanLehn, K., Lynch, C., Schultz, K., Shapiro, J. A., Shelby, R. H., Taylor, L., Treacy, D., Weinstein, A.,
and Wintersgill, M. (2005). The Andes physics tutoring system: Lessons learned.
Journal of Artificial Intelligence and Education
, 15(3), pp. 147

Van Lehn, K., Jones, R.M., & Chi, M.T.H. (1992) 'A model of

the self
explanation effect',
The Journal
of the Learning Sciences

2(1): 1


Winkley, J. 2010. E
assessment and innovation. Emerging Technologies. Coventry: Becta.

Woolf, B. (2010).
A Roadmap for Education Technology
. GROE Available online at

checked 31/01/11

Rivera, D., Hansen, E., Shute, V., Underwood,
J. & Bauer, M. 2007. Evidence
based approach
to interacting with open student models. International Journal of Artificial Intelligence in
Education, 17, 273