ArticlePDF Available

Adaptive E-Learning


Abstract and Figures

It has long been known that differences among individuals have an effect on learning. Dick Snow's research on aptitude-treatment interactions (ATIs) was designed to investigate and quantify these effects, and more recent research in this vein has clearly established that these effects can be quantified and predicted. Technology has now reached a point where we have the opportunity to capitalize on these effects to the benefit of learners. In this article, we review some of the demonstrated effects of ATIs, describe how ATI research naturally leads to adaptive e-learning, and describe one way in which an adaptive e-learning system might be implemented to take advantage of these effects.
Content may be subject to copyright.
Adaptive E-Learning
Valerie Shute
Educational Testing Service
Princeton, NJ
Brendon Towle
Thomson NETg
Naperville, IL
It has long been known that differences among individuals have an effect on learning. Dick
Snow’s research on aptitude–treatment interactions (ATIs) was designed to investigate and
quantify these effects, and more recent research in this vein has clearly established that these ef
fects can be quantified and predicted. Technology has now reached a point where we have the
opportunity to capitalize on these effects to the benefit of learners. In this article, we review
some of the demonstrated effects of ATIs, describe how ATI research naturally leads to adaptive
e-learning, and describe one way in which an adaptive e-learning system might be implemented
to take advantage of these effects.
It is usually and rightly esteemed an excellent thing in a
teacher that he should be careful to mark diversity of gifts in
those whose education he has undertaken, and to know in
what direction nature inclines each one most. For in this re-
spect there is an unbelievable variety, and types of mind are
not less numerous than types of body. (Quintilian, ca. 90
Acknowledging the important relation between individual
differences and education has a very long history. However,
simply acknowledging versus systematically testing this rela
tion are two quite different things. Together with Lee
Cronbach, Dick Snow formalized this interaction, conse
quently revolutionizing the thinking and researching of hu
man abilities in the 1970s. Snow’s primary research agenda
focused on how individual differences in aptitudes played out
in different educational settings. This received worldwide at
tention in the classic book on aptitude–treatment interactions
(ATIs; Cronbach & Snow, 1977).
Snow was steadfast in his belief that the psychology of hu
man differences is fundamental to education. He also ac
knowledged that designers of policy and practice often ignore
the lessons of differential psychology by trying to impose a
“one-size-fits-all” solution even though individuals are dif
ferent. His work sought to change that fact—to promote edu
cational improvement for all. This quest, across the years, has
been joined by scores of supporters who have been motivated
by him, either directly—as students and colleagues—or indi-
rectly—through his writings. The first author of this article
was fortunate to have had both direct and indirect Snow influ-
ences for almost 2 decades. And his influence continues, cur-
rently manifest in a research and development stream called
adaptive e-learning.
As e-learning matures as an industry and a research
stream, the focus is shifting from developing infrastructures
and delivering information online to improving learning
and performance. The challenge of improving learning and
performance largely depends on correctly identifying char
acteristics of a particular learner. Examples of relevant
characteristics include incoming knowledge and skills, cog
nitive abilities, personality traits, learning styles, interests,
and so on (Shute, 1994; Snow, 1989, 1994). For instruction
to be maximally effective, it should capitalize on these
learner characteristics when delivering content. Instruction
can be further improved by including embedded assess
ments, delivered to the student during the course of learn
ing. Such assessments can provide the basis for diagnosis
and subsequent instruction (i.e., presenting more of the
same topic, remediating the current topic, or introducing a
new topic). In short, enhancing learning and performance is
a function of adapting instruction and content to suit the
learner (for an overview on this topic, see Shute, Lajoie, &
Gluck, 2000).
Copyright © 2003, Lawrence Erlbaum Associates, Inc.
Requests for reprints should be sent to Valerie Shute, Educational Testing
Service, Rosedale Road, Princeton, NJ 08541. E-mail:
The effectiveness of e-learning may be gauged by the de
gree to which a learner actually acquires the relevant knowl
edge or skill presented online.
This acquisition is generally
regarded as a constructive activity where the construction can
assume many forms; thus e-learning environments should be
flexible enough to accommodate various constructive activi
ties (see Shute, 1994, for more on this topic). Moreover, indi
viduals differ in how they learn as well as what they learn, and
different outcomes of learning (e.g., conceptual understand
ing) reflect differences in general learning processes (e.g., in
ductive reasoning skill), specific learning processes (e.g.,
attention allocation), and incoming knowledge and skill. The
definition of learning used here is that learning is a process of
constructing relations. These relations become more com
plex, and at the same time more automatic, with increased ex
perience and practice. Accurate evaluation of e-learning is a
nontrivial task because it requires both correct measurement
of learning processes and outcomes.
Technology has now advanced to the point where we can
begin to implement laboratory-based adaptive instructional
techniques on the Internet (e.g., differential sequencing of
knowledge and skill learning objects depending on learners’
perceived needs). That is, concurrent advances in cognitive
science, psychometrics, and technology are beginning to
make it possible to assess higher level skills (Hambleton,
1996; Mislevy, Steinberg, & Almond, 1999) and to do so ef-
fectively and efficiently. Furthermore, in contrast with pa-
per-and-pencil multiple-choice tests, new assessments for
complex cognitive skills involve embedding assessments di-
rectly within interactive, problem-solving, or open-ended
tasks (e.g., Bennett & Persky, 2002; Minstrell, 2000;
Mislevy, Steinberg, Almond, Haertel, & Penuel, 2001). This
information can then be used to build and enhance models of
cognition and learning that can further inform and guide the
assessment and instructional design processes.
The story we convey in this article illustrates the natural
evolution of Snow’s research, embodied in adaptive e-learn
ing environments. We begin laying the foundation by describ
ing ATI research. This is followed by an overview of specific
components that go into adaptive e-learning systems. We con
cludewithourthoughtsonthefutureof education and training.
Theoretical Basis
Snow approached his research with the combined perspec
tives of a differential psychologist, experimental psycholo
gist, personality psychologist, and cognitive scientist. Of par
ticular interest to Snow was the match between individual dif
ferences and learning environments and how variation in
learning environments elicited or suited different patterns of
aptitudes. Such relations are called aptitude–treatment inter
actions (ATIs), where aptitude is defined in the broadest
sense as a person’s incoming knowledge, skills, and personal
ity traits. Treatment refers to the condition or environment
that supports learning (Cronbach & Snow, 1977).
The goal of ATI research is to provide information about
learner characteristics that can be used to select the best
learning environment for a particular student to optimize
learning outcome. Although hundreds of studies have been
explicitly conducted to look for ATIs (especially during the
1960s and 1970s), it has been very difficult to empirically
verify learner by treatment interactions. In the aforemen
tioned 1977 book on this topic, Cronbach and Snow (1977)
provided an excellent review of ATI research being carried
out during that time. It is obvious from reading their book
now that a major problem with those older ATI studies con
cerned data “noisiness.” That is, experimental data obtained
from classroom studies contained plentiful, extraneous, un
controlled variables, such as differing teacher personalities,
instructional materials, and classroom environments. Re-
cently, however, there has been renewed interest in examin-
ing the ATI issue using computers as controlled learning
environments (e.g., Maki & Maki, 2002; Sternberg, 1999).
We now summarize one study where each part of an ATI is
described and measured in a controlled manner.
Empirical Support
Individuals come to any new learning task with (often large)
differences in prior knowledge and skill, learning style, moti
vation, cultural background, and so on. These qualities affect
what is learned in an instructional setting. For this example, we
focus on a particular learning style measure described in Shute
(1993), namely exploratory behavior, as evidenced during in
teraction with an intelligent tutoring system (ITS) instructing
principles of electricity. During the course of learning, a stu
dent’s main goal was to solve progressively more difficult
problems with direct current circuits presented by the ITS.
However, at any given time, he or she was free to do other
things in the environment, such as read definitions of con
cepts, take measurements on the online circuit, or change com
ponent values (e.g., voltage source, resistors). All
explorations were optional and self-initiated. To quantify an
individual’s exploratory behavior, proportions were cre
ated—the ratio of time spent engaged in exploratory behavior
divided by the total time on the tutor. This was necessary to
control for differential tutor completion times, which ranged
from 5 to 21 hr.
In addition to aptitude, the learning environment (i.e.,
treatment condition) may also influence learning outcome.
Technically and generally, e-learning can refer to any learning activity
that largely involves technology for its presentation. We more narrowly de
fine e-learning as that taking place in front of a computer that is connected to
the Internet.
One way learning environments differ is in the amount of stu
dent control supported during the learning process. This can
be viewed as a continuum ranging from minimal (e.g., rote or
didactic environments) to almost complete control (e.g., dis
covery environments). Two opposing perspectives, repre
senting the ends of this continuum, have arisen in response to
the issue of optimal learning environment for instructional
systems. One approach is to develop a straightforward learn
ing environment that directly provides information to the
learner; the other requires the learner to derive concepts and
rules on his or her own. The disparity between positions be
comes more complicated because the issue is not just which is
the better learning environment, but rather, which is the better
environment for what type or types of persons—an ATI issue.
That issue motivated this controlled experiment, and the de
sign of two environments representing the ends of this control
continuum—rule application and rule induction.
These two environments were created from an ITS that
teaches basic principles of electricity as a complex but con
trolled learning task. They differ only in the feedback deliv
ered to the student. For instance, in the rule-application
environment, feedback clearly states the variables and their
relations for a given problem. This was communicated in the
form of a rule, such as “The principle involved in this kind of
problem is that current before a resistor is equal to the current
after a resistor in a parallel net.” Learners then proceeded to
apply the rule in the solution of related problems. In the
rule-induction environment, the tutor provides feedback,
which identifies the relevant variables in the problem, but the
learner must induce the relations among those variables. For
instance, the computer might give the following comment,
“What you need to know to solve this type of problem is how
current behaves, both before and after a resistor, in a parallel
net.” Learners in the rule-induction condition, therefore, gen
erate their own interpretations of the functional relations
among variables comprising the different rules.
Four posttests measured a range of knowledge and skills
acquired from the tutor, and all tests were administered on
line after a person finished the tutor.
The first test mea
sured declarative knowledge of electrical components and
devices and consisted of both true or false and multi
ple-choice questions. The second posttest measured con
ceptual understanding of Ohm’s and Kirchhoff’s laws. No
computations were required, and all questions related to
various circuits. The third posttest measured procedural
skill acquisition. Computations were required in the solu
tion of problems. The student would have to know the cor
rect formula (e.g., voltage = current × resistance), fill in the
proper numbers, and solve. Finally, the fourth test measured
a person’s ability to generalize knowledge and skills be
yond what was taught by the tutor. These problems required
both conceptual understanding of the principles as well as
The experiment involved over 300 paid participants,
mostly men, all high school graduates, 18 to 28 years old, and
with no prior electronics instruction or training. On their ar
rival, they were randomly assigned to one of the two environ
ments (rule-application vs. rule-induction), and both versions
permitted learners to engage in the optional, exploratory be
haviors described previously. Exploratory behaviors were
monitored by the computer and later quantified for post hoc
ATI analysis. Although we hypothesized that the inductive
environment would support (if not actively promote) the use
of exploratory behaviors, results showed no differences
among environments for exploratory behavior. Within each
environment, however, there were wide individual differ
ences on the exploratory learning dimension.
Learning outcome was defined as the percentage of cor
rect scores on the four tests, combined into a single “out
come” factor score. An interaction was hypothesized—that
learners evidencing greater exploratory behavior would learn
better if they had been assigned to the inductive environment,
and less exploratory learners would benefit from the more
structured application environment. Results supported this
hypothesis, showing a significant ATI (see Figure 1).
What are the ramifications of these findings? If we were able
to map the variety of aptitudes or trait complexes (e.g.,
Ackerman, 1996, 2003) to associated learning environments
or sequences of instructional components, we would be able
to adapt and hence customize instruction for any given
learner. For instance, Ackerman (1996; Ackerman &
Heggstad, 1997) compiled ability–interest, ability–personal
ity, and interest–personality correlates to support his more
general process, personality, interests, and knowledge the
We also used four matched pretests that served as covariates in the subse
quent data analysis.
FIGURE 1 Exploratory behavior by learning environment.
ory. Analysis has refined four cross-attribute (ability–in
terest–personality) trait complexes: social, clerical–con
ventional, science–math, and intellectual–cultural. The
psychological importance of these trait complexes is simi
lar to Snow’s (1991) aptitude complexes (i.e., ability and
interest constellations for classifying educational treat
ments). In general, the result, subject to empirical verifica
tion, would undoubtedly be to enhance the effectiveness,
efficiency, and enjoyment of the learning experience. This
is the premise underlying adaptive e-learning, which we
now discuss.
The key idea to keep in mind is that the true power of educa
tional technology comes not from replicating things that can
be done in other ways, but when it is used to do things that
couldn’t be done without it. (Thornburg, as cited in National
Association of State Boards of Education Study Group
[NASBE], 2001)
Examples of e-learning on the Internet today are, too often,
little more than lecture notes and some associated links
posted in HTML format. However, as noted in the previous
quote, the true power of e-learning comes from the exploita-
tion of the wide range of capabilities that technologies afford.
One of the most obvious is to provide assessments and in-
structional content that adapt to learners’ needs or desires.
This would comprise an online, real-time application of ATI
research. Other effective technology uses include providing
simulations of dynamic events, opportunities for extra prac-
tice on emergent skills, as well as the presentation of multi
media options.
The goal of adaptive e-learning is aligned with exem
plary instruction: delivering the right content, to the right
person, at the proper time, in the most appropriate
way—any time, any place, any path, any pace (NASBE,
2001). We now focus our attention on what would be
needed to accomplish this lofty goal in an e-learning con
text. Following are the necessary ingredients in an e-learn
ing system. Each model is briefly introduced, then followed
by a more in-depth description per module.
Components of E-Learning
The content model houses domain-related bits of knowledge
and skill, as well as their associated structure or interdepen
dencies. This may be thought of as a knowledge map of what
is to be instructed and assessed, and it is intended to capture
and prescribe important aspects of course content, including
instructions for authors on how to design content for the
model. A content model provides the basis for assessment, di
agnosis, instruction, and remediation. In relation to the ATI
study described earlier, the content model may be likened to
the hierarchical array of knowledge and skills associated with
Ohm’s and Kirchhoff’s laws.
The learner model represents the individual’s knowledge
and progress in relation to the knowledge map, and it may in
clude other characteristics of the learner as a learner. As such,
it captures important aspects of a learner for purposes of indi
vidualizing instruction. This includes assessment measures
that determine where a learner stands on those aspects.
The instructional model manages the presentation of ma
terial and ascertains (if not ensures) learner mastery by
monitoring the student model in relation to the content
model, addressing discrepancies in a principled manner,
and prescribing an optimal learning path for that particular
learner. Information in this model provides the basis for de
ciding how to present content to a given learner and when
and how to intervene.
Finally, the adaptive engine integrates and uses informa
tion obtained from the preceding models to drive presentation
of adaptive learning content.
Content Model
The requirements for any content model fall into two catego-
ries: requirements of the delivery system and requirements of
the learning content that is to be delivered. On the delivery
side of the equation, we need a system that is content inde-
pendent, robust, flexible, and scalable. Content independent
means that the system can serve any content that is designed
within the content requirements detailed later in this article.
Robust means that it lives on the Internet and should be capa-
ble of delivering instruction to multiple users concurrently.
Flexible implies adaptivity, requiring different types and se
quences of content. And scalable means the system can adjust
to increased demands, such as accommodating more compo
nents, more users, and so on.
On the content side of the equation, the content must be
composed in such a way that the delivery system can adapt
it to the needs of the particular learner. Each content aggre
gation will need to be composed of predictable pieces, so
that the delivery system can know what to expect. This
means that all of the content served by this delivery system
will have to be built to the same specification. Issues such
as grain size will vary, depending on the purpose or use of
the content.
Learning objects.
Fortunately, the need for content to
be built to the same specifications dovetails nicely with cur
rent industry research and development associated with
learning objects (e.g., see IEEE LTSC, 2003; IMS Global
Learning Consortium, 2001). What are learning objects? Like
Lego blocks, learning objects (LOs) are small, reusable com
ponents—video demonstrations, tutorials, procedures, sto
ries, assessments, simulations, or case studies. However, rather
than use them to build castles, they are used to build larger col
lections of learning material. LOs may be selectively applied,
either alone or in combination, by computer software, learning
facilitators, or learners themselves, to meet individual needs
for learning or performance support. For example, all of
Thomson NETg’s currently delivered educational content
takes the form of LOs that have been assembled into courses,
where each LO addresses a coherent subset of the educational
objectives of the course.
In current industry practice, LOs are assembled into
courses before the time that they are delivered. The arrange
ment of these LOs to achieve instructionalgoals is doneduring
this assembly. These collections can be specified using the
Sharable Content Object Reference Model (SCORM; Ad
vanced Distributed Learning, 2001) specification for defining
courses. Among other things, this specification defines a way
to define the structure of a course in a simple, easy-to-author
manner. Because SCORM is agnostic to the nature of the con
tent,we can easily define the collectionsdescribed previously.
Although current practice is to assemble the LOs before
the collection is delivered, there is no reason why the LOs
could not be assembled into a structure that would allow an
intelligent adaptive system to reassemble them on the fly to
meet the needs of the particular learner. The rest of this sec-
tion will describe how an LO collection could be specified
such that an adaptive system could present it according to
the needs of the learner. The basic idea involves dividing
the LO collection such that it contains subcollections, each
of which teaches a particular skill or knowledge type. Each
of the subcollections thus contains all of the instructional
components necessary to teach that skill. Using this hierar-
chy, the adaptive system can first decide what needs to be
taught and then decide how to teach it, as we describe in the
following pages.
Knowledge structures.
The purpose of establishing a
knowledge structure as part of the content model in any
e-learning system is that it allows for dependency relations to
be established. These, in turn, provide the basis for the follow
ing: assessment (What’s the current status of a particular topic
or LO?), cognitive diagnosis (What’s the source of the prob
lem, if any?), and instruction or remediation (Which LOs need
to be taught next to fix a problem area or present a new topic?).
Each element (or node) in the knowledge structure may be
classified in terms of different types of knowledge, skill, or
ability. Some example knowledge types include
Basic knowledge (BK): This includes definitions, exam
ples, supplemental links (jpgs, avis, wavs), formulas, and so
on, and addresses the What part of content.
Procedural knowledge (PK): This defines step-by-step
information, relations among steps, subprocedures, and so
on, and addresses the How part of content.
Conceptual knowledge (CK): This refers to relational
information among concepts and the explicit connections
with BK and PK elements, draws all into a “big picture” and
addresses the Why part of content.
Restricting a node in the knowledge structure (again, note
that each node has an associated collection of LOs) to a single
knowledge type helps ensure the course is broken down to an
appropriate grain size, by limiting the scope of what can be in
any single node. This restriction also suggests different strat
egies for the authoring of instruction and assessment: Differ
ent knowledge types require different strategies. We suggest
the following guidelines (for more on this topic, see Shute,
1995): BK instruction should involve the introduction of new
definitions and formulas in a straightforward, didactic man
ner, whereas BK assessment relates to measuring the
learner’s ability to recognize or produce some formula, basic
definition, rule, and so on. PK instruction should occur within
the context of experiential environments where the learner
can practice doing the skill or procedure (problem solving),
whereas PK assessment relates to the learner’s ability to actu
ally accomplish some procedure or apply a rule, not simply
recognize those things. Finally, CK instruction typically oc-
curs after the learner has been presented with relevant base in-
formation (BK–PK), and then the big picture may be
presented, either literally or via well-designed analogies, case
studies, and so on. CK assessment refers to a learner being
able to transfer BK and PK to novel areas, explain a system or
phenomenon, predict some outcome, or strategize. The out-
come tests described earlier in relation to the electricity tutor
study exemplify each of these outcome types.
A simplified network of nodes and associated knowledge
types is shown in Figure 2. Each node has an associated col
lection of LOs that teach or assess a certain component of a
concept or skill. In summary, we posit different knowledge
types associated with their own special way of being in
structed and assessed. So now the questions are: How do we
optimally assess and diagnose different outcome types, and
what happens after diagnosis? Before answering those ques
tions, we now present the learner model—the repository of
information concerning the learner’s current status in relation
to the various LOs (i.e., domain-related proficiencies).
Learner Model
The learner model contains information that comes from as
sessments and ensuing inferences of proficiencies. That in
formation is then used by the system to decide what to do
next. In the context of adaptive e-learning, this decision re
lates to customizing and hence optimizing the learning expe
rience. Obviously, a critical component here is the validity
and reliability of the assessment. One idea is to employ what
is called the evidence-centered design approach (e.g.,
Mislevy, Steinberg, & Almond, 1999) to assessment. This al
lows an instructional designer (or whomever) to (a) define the
claims to be made about the students (i.e., the knowledge,
skills, abilities, and other traits to be measured), (b) delineate
what constitutes valid evidence of the claim (i.e., student per
formance data demonstrating varying levels of proficiency),
and (c) create assessment tasks that will elicit that evidence.
Evidence is what ties the assessment tasks back to the
proficiencies, and the entire process is theory driven, as op-
posed to a more common data- or item-driven manner.
Assessing the learner.
The first issue concerns just
what is to be assessed. There are actually two aspects of learn-
ers that have implications for adaptation: (a) domain-depend-
ent information—this refers to knowledge assessment via
pretest and performance data to allow the system to initialize
a learner model in relation to content and LOs, eliminate
those already “known,” and focus instruction or assessment
(or both) on weak areas; and (b) domain-independent infor
mation—this relates to learner profile data (e.g., cognitive
abilities or personality traits) and allows the system to pick
and serve optimal LO sequences and formats.
Assessing specific learner traits indicates particular kinds
of content delivery in relation to either differential sequenc
ing of topics or providing appropriate, alternative formats and
media. In relation to differential sequencing, a typical, valid
instructional system design sequence consists of these steps:
(a) Present some introductory material, (b) follow with the
presentation of a rule or concept, (c) provide a range of illus
trative examples, (d) give liberal practice opportunities, and
(e) summarize and call for reflection. Thus, across topics, one
general sequencing rule may be to serve easier topics before
more difficult ones. And within a topic, a general rule may be
the default delivery of certain LOs: introduction, body (rule
or concept, followed by examples), interactivity (explora
tions, practice, and explicit assessments of knowledge or
skill), and reflection (summary).
Alternatively, suppose you knew that an individual was
high on an inductive reasoning trait. The literature (e.g.,
Catrambone & Holyoak, 1989) has suggested that those
learners perform better with examples and practice preceding
the concept. On the other hand, learners with low inductive
reasoning skills perform better when the concept is presented
at the outset of the instructional sequence. This has direct im
plications for the sequencing of elements within a given topic.
Now, consider a learner assessed as possessing low work-
ing memory capacity. One instructional prescription would
be to present this individual with smaller units of instruction
(Shute, 1991). And going back to our example at the begin-
ning of this story (depicted in Figure 1), an individual pos-
sessing an exploratory learning style suggests a less
structured learning experience compared to a person with a
less exploratory learning style (Shute, 1993).
In Figure 3, we can see how the parts come together (modi-
fied from Quinn, 2001). The bottom row of the figure shows
the typical way of serving content based on inferred gaps in a
learner’s knowledge structure. This is also known as
microadaptation, reflecting differences between the learner’s
knowledge profile and the expert knowledge structure em
bodied in the content model. “Instructional rules” then deter
mine which knowledge or skill element should be selected
next (i.e., selecting from the pool of nonmastered objects).
The top row shows an additional assessment, representing an
other way to adapt instruction based on learners’ cognitive
abilities, learning styles, personality, or whatever else is
deemed relevant. This is also known as macroadaptation and
provides information about how to present the selected
knowledge or skill chunk.
Instructional Model
There are several general and specific guidelines for system
atic approaches to instructional design, such as those de
scribed by Robert Gagné. But how do we progress from
guidelines to determining which LOs should be selected, and
why? To answer this question, after delineating the guide
lines presented in Gagné’s (1965) book entitled The Condi
FIGURE 2 Sample knowledge hierarchy.
tions of Learning, we describe a student modeling approach
that implements some of these instructional ideas within the
context of an ITS.
The following represents an abridged version of Gagné’s
“events of instruction” (see Kruse, 2000), along with the cor
responding cognitive processes. These events provide the
necessary conditions for learning and serve as the basis for
designing instruction and selecting appropriate media
(Gagné, Briggs, & Wager, 1992). We include them here as
they offer clear, obvious guidelines for designing good
e-learning environments.
1. Gain the learner’s attention (reception).
2. Inform the learner of the objectives (expectancy).
3. Stimulate recall of prior learning (retrieval).
4. Present the learning stimulus (selective perception).
5. Provide learning guidance (semantic encoding).
6. Elicit appropriate performance (responding).
7. Provide feedback (reinforcement).
8. Assess the learner’s performance (retrieval).
9. Enhance retention and transfer (generalization).
Applying Gagné’s (Gagné, Briggs, & Wager, 1992)
nine-step model to an e-learning program is a good way to fa-
cilitate learners’ successful acquisition of the knowledge and
skills presented therein. In contrast, an e-learning program
that is replete with bells and whistles, or provides unlimited
access to Web-based documents, is no substitute for sound in-
structional design. Although those types of programs might
be valuable as references or entertainment, they will not max-
imize the effectiveness of information processing or learning.
In addition to the specific prescriptions mentioned previ-
ously, there are a few key presumptions and principles for in
structional design that should be considered when designing
an e-learning system. In general, these include the following:
Knowledge is actively constructed, multiple representations
for a concept or rule are better than a single one, problem-solv
ing tasks should be realistic and complex, and opportunities
for learners to demonstrate performance of activities promot
ing abstraction and reflection should be provided.
In terms of the relevant features of the adaptive system,
this means several things. First, the activities presented to the
student should involve the creation and manipulation of rep
resentations. If the student is expected to have a mental model
that corresponds to the representation, he or she needs to be
actively involved in the creation or manipulation of the repre
Second, the content should be designed with multiple rep
resentations for a concept or a rule. This serves two purposes:
It allows the adaptive engine (described later) to provide the
student with the single representation that best matches the
student’s aptitude profile, while simultaneously giving the
engine additional representations to present in the event that
the student fails to master or acquire the topic the first time.
These multiple representations should include different vi
sual representations (textual vs. graphical, or different graph
ical representations of the same concept) as well as different
styles of conceptual explanation.
Third, the student should be provided with a final learning
activity that encourages reflection and integration of the
knowledge learned into the body of knowledge as a whole.
Finally, the system should incorporate enough support and
help so that the student can spend time learning the material
and not the system. This is simply to ensure that as much of
the student’s cognitive effort as possible goes into learning
the material being presented, and not into learning the system
that is doing the presenting.
How do we move from these general and specific guide
lines to determining which learning object or objects should
be selected, and why? One solution is to employ something
FIGURE 3 Learning management system framework including two types of assessments.
like Student Modeling Approach to Responsive Tutoring
(SMART; Shute, 1995), a principled approach to student
modeling. It works within an instructional system design
where low-level knowledge and skill elements are identified
and separated into the three main outcome types previously
mentioned (i.e., BK, PK, CK). As the student moves through
an instructional session, LOs (i.e., the online manifestations
of the knowledge and skill elements) are served to instruct
and assess. Those knowledge elements showing values below
a preset mastery criterion become candidates for additional
instruction, evaluation, and remediation, if necessary.
Remediation is invoked when a learner fails to achieve mas
tery during assessment, which follows or is directly embed
ded within the instructional sequence.
SMART includes capabilities for both micro- and
macroadaptation of content to learners, mentioned earlier,
and is based on a distinction originally made by Snow (1989).
Basically, microadaptation relates to the domain-dependent
learner model (i.e., the individual knowledge profile in Figure
3) and is the standard approach, representing emerging
knowledge and skills. In this case, the computer responds to
updated observations with a modified curriculum that is mi
nutely adjusted, dependent on individual response histories
during instructional sessions. Macroadaptation refers to the
domain-independent learner model (i.e., the individual
learner profile in Figure 3), representing an alternative ap-
proach. This involves assessing students prior to as well as
during their use of the system, focusing mainly on general,
long-term aptitudes (e.g., working memory capacity, induc-
tive reasoning skill, exploratory behavior, impulsivity) and
their relations to different learning needs.
An alternative approach to student modeling includes us-
ing Bayesian inference networks (BINs) to generate estimates
of learner proficiencies in relation to the content (e.g.,
Mislevy, Almond, Yan, & Steinberg, 1999). Both theSMART
and BIN approaches are intended to answer the following
questions: (a) What is the learner’s current mastery status of a
topic, and (b) what is the nature and source of the learner’s
problem, if any? Typical ways of evaluating success (e.g., pass
or fail, or correct solution of two consecutive problems) do not
offer the degree of precision needed to go beyond assessment
into cognitive diagnosis. Both SMART and BINs provide
probabilistic mastery values associated with nodes or topics
(regardless of grain size). With regard to the instructional deci
sion about what should subsequently be presented, the knowl
edge structure, along with an indication of how well a learning
objective is attained, informs the adaptive engine of the next
recommended bit or bits of content to present.
Adaptive Engine
Given the content model, the learner model, and the instruc
tional model, the fundamentals of the adaptive engine are
fairly simple. The first step involves selecting the node (topic)
to present, based on a diagnosis of the student’s knowledge
needs. The next step involves deciding which LO or LOs
within that node to present, sequenced or flavored according
to the characteristics and needs of the particular learner. The
presentation of LOs is continued until the student has mas
tered the topic or node, and the node selection process is then
repeated until all nodes have been mastered.
Although this is a fairly simple overview, the actual pro
cess is obviously more complicated. We will examine each
part of the process (selecting a node, and then presenting the
content within the node) separately.
In our solution, selecting a node, in the general case, is a
fairly simple exercise; the engine can simply choose from the
pool of nodes that have not been completed and whose pre
requisites have been mastered. However, one additional fea
ture of our structure is that a pretest can be generated on the
fly, and assessment can incorporate a sequencing algorithm.
Recall that the LOs in each node have been categorized by
their role in the educational process, and the authoring guide
lines have restricted each learning object to a single role only.
Because of this, for any collection of nodes, the system can
create another collection of nodes that contains only the as
sessment tasks from the original collection. Presenting this
new collection functions as a pretest. If the student passes the
assessment without any presentation, he or she is presumed to
have already mastered the associated content.
When the engine is presenting objects relating to a particu-
lar node, it uses a set of rules to drive the selection of individ-
ual LOs for presentation to the student. These rules examine
the information contained in the student model, the student’s
interaction within the node so far, and the content model of
each individual LO contained within the node. Using this in-
formation, the rules assign a priority to each LO within the
node. Once the priority of every LO has been calculated
(which occurs almost instantly), the LO with the highest pri
ority is delivered to the student.
As an example of how this works for instructional objects,
consider the following. An initial arbitrary weighting is as
signed to every LO in the node. One rule states that if the stu
dent’s interaction with the node is empty (i.e., the student is
just beginning the node), then decrease the priority of every
LO except those which fulfill the role of “introduction.” This
rule ensures that the default sequence provides for an intro
duction-type LO to be presented at the beginning of an in
structional sequence. On the other hand, consider a learner
who prefers a more contextualized learning experience, such
as a learner characterized as very concrete and experiential.
To handle that case, there is a rule that states that if the learner
is “highly concrete” and “highly experiential,” and if the
learner’s interaction with the node is empty, then increase the
priority of associated assessment-task LOs. If the learner is
not concrete and experiential, then the second rule has no ef
fect; however, if he or she is, then the second rule overrides
the first, and the learner sees an assessment task at the begin
ning of the instructional sequence.
The remaining rules work in an analogous fashion. That is,
each one examines a set of conditions that has an associated
instructional prescription and adjusts priorities on the appro
priate LOs. Working together, all of the rules serve to provide
the instructionally correct learning object for the student at
every point of the student’s interaction with the node.
One issue that should be addressed concerns the accuracy
of the rule set: designing it such that it provides a natural and
effective learning experience regardless of learner
characteristics. One way to accomplish this is by using the
techniques of genetic programming (GP; Koza, 1992) to im
prove the performance of the rule set. Research has shown
that this technique is applicable to the design of rules for
rule-based systems (e.g., Andre, 1994; Edmonds, Burkhardt,
& Adjei, 1995; Tunstel & Jamshidi, 1996). The general idea
is to treat each individual rule set as a single individual in the
population of algorithms; the rule sets can then be evolved ac
cording to standard GP methods.
For our purposes, the interesting feature of GP is that it
turns a design task (create a rule set that treats learners effec
tively) into a recognition task (determine how well a given
rule set performs at treating learners). We believe that a large
sample of learner data can be used to evaluate a learner’s po-
tential experience with a given rule set, and this can be used as
the basis of the evaluation function that drives the GP ap-
proach. Further, we believe that the combination of hu-
man-designed rules with computer-driven evolution gives us
a high likelihood of success and avoids many of the risks in-
herent in rule-based systems.
There are many reasons to pursue adaptive e-learning. The
potential payoffs of designing, developing, and employing
good e-learning solutions are great, and they include im
proved efficiency, effectiveness, and enjoyment of the learn
ing experience. In addition to these student-centered instruc
tional purposes, there are other potential uses as well, such as
online assessments. Ideally, an assessment comprises an im
portant event in the learning process, part of reflection and
understanding of progress. In reality, assessments are used to
determine placement, promotion, graduation, or retention.
We advocate pursuing the ideal via online diagnostic assess
ments. As Snow and Jones (2001) pointed out, however, tests
alone cannot enhance educational outcomes. Rather, tests can
guide improvement—presuming they are valid and reli
able—if they motivate adjustments to the educational system.
There are clear and important roles for good e-learning pro
grams here.
However, and as mentioned earlier, the current state of
e-learning is often little more than online lectures, where edu
cators create electronic versions of traditional printed student
manuals, articles, tip sheets, and reference guides. Although
these materials may be valuable and provide good resources,
their conversion to the Web cannot be considered true teach
ing and learning. Instead of the page-turners of yesterday, we
now have scrolling pages, which is really no improvement at
all. Adaptive e-learning provides the opportunity to dynami
cally order the “pages” so that the learner sees the right mate
rial at the right time.
There are currently a handful of companies attempting to
provide adaptive e-learning solutions (e.g., see,, and Learning
Machines, Inc.). Further, adaptive e-learning has become a
rather hot topic in the literature recently (Nokelainen, Tirri,
Kurhila, Miettinen, & Silander, 2002; Sampson,
Karagiannidis, & Kinshuk, 2002). However, many of these
are not concerned with adaptive instruction at all; rather, they
are concerned with adapting the format of the content to meet
the constraints of the delivery device, or adapting the inter
face to the content to meet the needs of disabled learners. Of
those that are concerned with adaptive instruction, most tend
to base their “adaptivity” on assessments of emergent content
knowledge or skill or adjustments of material based on
“learner styles”—less suitable criteria than cognitive abilities
for making adaptive instructional decisions.
We believe that the time is ripe to develop e-learning sys-
tems that can reliably deliver uniquely effective, efficient,
and engaging learning experiences, created to meet the needs
of the particular learner. The required ingredients in such a
personalized learning milieu include rich descriptions of con-
tent elements and learner information, along with robust,
valid mappings between learner characteristics and appropri-
ate content. The result is adaptive e-learning, a natural exten-
sion of Snow’s considerable contributions to the field of
educational psychology.
We thank Aurora Graf, Jody Underwood, Irv Katz, and sev
eral anonymous reviewers for their helpful comments on this
Ackerman, P. L. (1996). A theory of adult intellectual development: Process,
personality, interests, and knowledge. Intelligence, 22, 227–257.
Ackerman, P. L. (2003). Aptitude complexes and trait complexes. Educa
tional Psychologist, 38, 85–93.
Ackerman, P. L., & Heggestad, E. D. (1997). Intelligence, personality, and
interests: Evidence for overlapping traits. Psychological Bulletin, 121,
Advanced Distributed Learning. (2001). SCORM (version 1.2). Re
trieved April 10, 2003, from
Andre, D. (1994). Learning and upgrading rules for an OCR system us
ing genetic programming. In Proceedings of the First IEEE Confer
ence on Evolutionary Computation (Vol. 1, pp. 462–467).
Piscataway, NJ: IEEE.
Bennett, R. E., & Persky, H. (2002). Problem solving in technology-rich en
vironments. In Qualifications and Curriculum Authority (Ed.), As
sessing gifted and talented children (pp. 19–33). London, England:
Qualifications and Curriculum Authority.
Catrambone, R., & Holyoak, K. J. (1989). Overcoming contextual limita
tions on problem-solving transfer. Journal of Experimental Psychol
ogy: Learning, Memory, and Cognition, 15, 1147–1156.
Cronbach, L. J., & Snow, R. E. (1977). Aptitudes and instructional methods:
A handbook for research on interactions. New York: Irvington.
Edmonds, A. N., Burkhardt, D., & Adjei, O. (1995). Genetic programming of
fuzzy logic rules. In Proceedings of the Second IEEE Conference on
Evolutionary Computation (Vol. 2, pp. 765–770). Piscataway, NJ:
Gagné, R. M. (1965). The conditions of learning. New York: Holt, Rinehart
& Winston.
Gagné, R. M., Briggs, L. J., & Wager, W. W. (1992). Principles of instruc
tional design (4th ed.). Fort Worth, TX: Harcourt Brace.
Hambleton, R. K. (1996). Advances in assessment models, methods, and
practices. In D. C. Berliner & R. C. Calfee (Eds.), Handbook of educa
tional psychology (pp. 889–925). New York: American Council on Ed
IEEE LTSC. (2003). Learning object metadata. Retrieved April 10, 2003,
IMS Global Learning Consortium. (2001). Learning resource metadata (ver
sion 1.2.1). Retrieved April 10, 2003, from
Koza, J. (1992). Genetic programming. Cambridge, MA: MIT Press.
Kruse, K. (2000). Web rules. (20000. Retrieved April 10, 2003, from
Maki, W. S., & Maki, R. H. (2002). Multimedia comprehension skill predicts
differential outcomes of web-based and lecture courses. Journal of Ex-
perimental Psychology: Applied, 8, 85–98.
Minstrell, J. (2000). Student thinking and related instruction: Creating a
facet-based learning environment. In J. Pellegrino, L. Jones, & K.
Mitchell (Eds.), Grading the nation’s report card: Research for the
evaluation of NAEP. Washington, DC: National Academy Press.
Mislevy, R. J., Almond, R. G., Yan, D., & Steinberg, L. S. (1999). Bayes nets in
educational assessment: Where do the numbers come from? In K. B. Laskey
& H. Prade (Eds.), Proceedings of the Fifteenth Conference on Uncertainty
in Artificial Intelligence (pp. 437–446). San Francisco: Kaufmann.
Mislevy, R. J., Steinberg, L. S., & Almond, R. G. (1999). On the roles of task
model variables in assessment design (CSE Tech. Rep. No. 500). Los
Angeles: University of California, Center for the Study of Evaluation,
Graduate School of Education & Information Studies.
Mislevy, R. J., Steinberg, L. S., Almond, R. G., Haertel, G., & Penuel, W.
(2001). Leverage points for improving educational assessment (CSE
Tech. Rep. No. 534). Los Angeles: University of California, Center for
Studies in Education/CRESST.
National Association of State Boards of Education Study Group. (2001). Any
time, any place, any path, any pace: Taking the lead on e-learning pol
icy. Retrieved April 10, 2003, from
Nokelainen, P., Tirri, H., Kurhila, J., Miettinen, M., & Silander, T. (2002).
Optimizing and profiling users online with Bayesian probabilistic mod
eling. In Proceedings of the Networked Learning 2002 Conference
(Berlin, Germany, May 2002). The Netherlands: NAISO Academic
Quinn, C. (2001). Framework for a learning management system [Slide].
Unpublished PowerPoint presentation,,
Emeryville, CA.
Sampson, D., Karagiannidis, C., & Kinshuk. (2002). Personalised learning:
Educational, technological and standardisation perspectives, interac
tive educational multimedia (on-line journal ISSN 1576–4990), Special
Issue on Adaptive Educational Multimedia, 4 (invited paper), April
Shute, V. J. (1991). Who is likely to acquire programming skills? Journal of
Educational Computing Research, 7(1), 1–24.
Shute, V. J. (1993). A comparison of learning environments: All that
glitters. In S. P. Lajoie & S. J. Derry (Eds.), Computers as cognitive
tools (pp. 47–74). Hillsdale, NJ: Lawrence Erlbaum Associates,
Shute, V. J. (1994). Learning processes and learning outcomes. In T. Husen
& T. N. Postlethwaite (Eds.), International encyclopedia of education
(2nd ed., pp. 3315–3325). New York: Pergamon.
Shute, V. J. (1995). SMART: Student Modeling Approach for Respon
sive Tutoring. User Modeling and User-Adapted Interaction, 5,
Shute, V. J., Lajoie, S. P., & Gluck, K. A. (2000). Individualized and group
approaches to training. In S. Tobias & J. D. Fletcher (Eds.), Training
and retraining: A handbook for business, industry, government, and the
military (pp. 171–207). New York: Macmillan.
Snow, C. E,. & Jones, J. (2001, April 25). Making a silk purse. Education
Week Commentary.
Snow, R. E. (1989). Toward assessment of cognitive and conative structures
in learning. Educational Researcher, 18, 8–14.
Snow R. E. (1991). The concept of aptitude. In R. E. Snow & D. Wiley (Eds.),
Improving inquiry in social science (pp. 249–284). Hillsdale, NJ: Law
rence Erlbaum Associates, Inc.
Snow, R. E. (1994). Abilities in academic tasks. In R. J. Sternberg & R. K.
Wagner (Eds.), Mind in context: Interactionist perspectives on hu
man intelligence (pp. 3–37). New York: Cambridge University
Sternberg, R. J. (1999). Thinking styles. New York: Cambridge University
Tunstel, E., & Jamshidi, M. (1996). On genetic programming of fuzzy
rule-based systems for intelligent control. International Journal of In
telligent Automation and Soft Computing, 2, 273–284.
... Adaptivity is used to help learners reach a desired level of mastery at their own pace [Ca20]. In order to create adaptive learning environments, a model of the domain to be learnt is required [ST03], describing the competencies that are to be developed and the relationships between them. ...
... In order to assess the learner's needs and adapt the instruction accordingly, AL environments make use of various models: most importantly learner, domain, instructional and assessment model. The domain model "houses domain-related bits of knowledge and skill, as well as their associated structure or interdependencies" [ST03]. The learner model is used for capturing what a person knows and does, the learner characteristics, e g. knowledge, learning style, goals, or demographics [VDC11]. ...
Conference Paper
Full-text available
Adaptive learning environments that follow a competency-based learning approach require granular, domain-specific competency frameworks (models) for the continuous assessment of a learner's knowledge and skills as well as for the subsequent personalization of instruction. This case-study describes the iterative creation process for a competency framework in the domain of Naïve Bayes classifiers, including the design principles that led to the framework and the tools used for making it publishable as linked, open data.
Процесс цифровизации образования, активно проводимый в нашей стране и по всему миру, позволил более широко применить в учебном процессе современные приемы преподавания, перенося часть педагогической нагрузки с очного формата на дистанционный. Проектируемые и используемые цифровые образовательные платформы уже сейчас включают в себя не только оцифрованный лекционный видеоматериал и электронные формы учебников, но и элементы автоматизации проверки выполненных учащимися заданий. Расширение области применения автоматической проверки решенных учащимися задач и выполненных упражнений является объективной необходимостью, в противном случае при дистанционных формах образовательного процесса резко возрастает нагрузка на педагога, который должен выделять значительное время на проверку увеличившегося самостоятельной работы школьников и студентов. Кроме того, при дистанционном преподавании снижается эффект личного присутствия педагога, когда учитель и ученики разделены экранами компьютеров. Существенной помощью может стать использование интеллектуальных помощников преподавателя и автоматизированных систем проверки, построенных методами машинного обучения и технологии нейронных сетей. В настоящей статье рассмотрены подходы к решению поставленных задач по автоматической проверке графических заданий и выявлению заимствований в текстовом виде. Показаны возможные варианты реализации этих функций с использованием технологий искусственного интеллекта. The digitalization of education in Russia and worldwide enables a more extensive introduction of advanced teaching methods through a partial switch from offline to online teaching. The existing and coming e-learning platforms feature not only digital lecture videos and e-textbooks, but some automated assessment/grading tools. There is a need to expand the coverage of such tools to avoid the extreme burden of online teaching as the educator has to allocate significant time for assessing the increased amount of high school/university student assignments. Also, distant learning diminishes the effect of the educator personal presence since the teacher and the student are separated by their computer screens. Smart educator assistants and automated assessment tools based on machine learning and neural networks can significantly alleviate the problem. This study offers some strategies for automated assessment of graphic assignments and checks for plagiarism. Possible AI-based implementations of such features are presented.
Full-text available
Feedback is a key factor in helping individuals to self-regulate their learning behavior. Informative feedback, as a very basic form of feedback informing learners about the correctness of their answers, can be framed in different ways emphasizing either what was correct or what must be improved. The regulatory focus theory describes different strategic orientations of individuals towards goals, which may be associated with different effects of different informative feedback types. A promotion orientation describes the preference for approaching positive outcomes, while a prevention orientation describes the preference for avoiding negative ones. Applied to the context of informative feedback in self-regulated e-learning environments, we predict that regulatory fit, defined as the congruence of individuals’ regulatory orientations and framed feedback, positively affects learning persistence and performance. In two experiments, we assessed individuals’ regulatory orientations and experimentally varied framed feedback in samples of university students preparing for exams with an e-learning tool (N = 182, experiment 1; N = 118, experiment 2) and observed actual learning behaviors. Using different operationalizations of regulatory-framed feedback, we found statistically significant regulatory fit effects on persistence and performance in both experiments, although some remain insignificant. In experiment 2, we additionally tested ease of processing as a mechanism for regulatory fit effects. This way, we expand the literature on regulatory fit effects and feedback on actual learning behavior and provide evidence for the benefits of adaptive learning environments. We discuss limitations, especially regarding the stability of regulatory fit, as well as future directions of research on regulatory-framed feedback.
Full-text available
Scientific reasoning helps children understand the world around them. Teaching scientific reasoning can be challenging because not all component scientific reasoning skills develop at the same age and not all children learn these skills at the same pace. Adaptive support thus seems called for. We designed two types of adaptive instruction, based on children’s standardised test scores (macro-adaptive; n = 58) or their performance in the previous lesson (micro-adaptive; n = 46), and tested their effectiveness against a non-adaptive control condition (n = 49). Analysis of pre- and post-test scores showed comparable improvements in all three instructional conditions. As many children in both adaptive conditions received medium support, additional analyses were done on children in the macro-adaptive condition who received high or low-support worksheets, and their control group counterparts. Learning gains for these groups were similar. Children’s overall task performance during the lessons also improved, and this improvement interacted with condition. These results suggest that more specific information on children’s performance and more frequent and precise adaptations might lead to better learning outcomes. As this was not possible in this study, future research should explore hybrid solutions that enable children to practice scientific reasoning with physical materials while receiving adaptive support via their computers.
Full-text available
In this study, it was aimed to implement and evaluate an adaptive learning environment (ALE) designed according to the learner characteristics of 4th grade primary school students and integrate educational hypermedia environments with face-to-face teaching. Via a preliminary study carried out in accordance with this purpose, the variables that affect the academic achievement of the students in the primary school social studies course were analyzed, and as a result of this analysis, the design, application, and evaluation criteria of ALE were determined. In our study, which was modeled as an embedded-experimental mixed method, quantitative and qualitative data were obtained using different tools. The analysis of the data revealed that the designed learning environment had a positive effect on students' academic achievements, collaborative learning skills, and, partially, independent learning skills, and it was also effective in closing the achievement gap due to learning and cognitive styles.
Full-text available
Performance evaluation is based on comparison standards. Results can either be contrasted to former results (temporal comparison) or results of others (social comparison). Existing literature analyzed potential effects of teachers’ stable preferences for comparison standards on students’ learning outcomes. The present experiments investigated effects of learners’ own preferences for comparison standards on learning persistence and performance. Based on research and findings on person-environment-fit, we postulated a fit hypothesis for learners’ preferences for comparison standards and framed feedback on learning persistence and performance. We tested our hypotheses in two separate experiments ( N = 203 and N = 132) using different manipulations of framed feedback (temporal vs. social) in an e-learning environment, thus establishing high ecological validity and allowing objective data to be collected. We found first evidence for beneficial effects of receiving framed feedback towards own preferences on learning persistence and performance in our experiments. We tested fluency as a possible underlying psychological mechanism in our second experiment and observed a larger fit effect on learning persistence under disfluency. The results are discussed regarding a new theoretical perspective on the concept of preferences for comparison standards as well as opportunities for adaptive e-learning.
Owing to the rapid development of information and communication technologies, online or mobile learning content is widely available on the Internet. Unlike traditional face-to-face learning, online learning exhibits a critical limitation: real-time interactions between learners and teachers are generally not feasible in online learning. To overcome this issue, we implemented an online learning system based on electroencephalography (EEG)-based passive brain-computer interface (pBCI) technology referred to as the “adaptive neuro-learning system (ANLS).” It monitors the current mental states of learners seamlessly using EEG signals. Then, it adaptively provides natural and interactive video feedback rather than simple alarms or pop quizzes following the current mental conditions of a learner. In this study, a total of 60 university students were assigned randomly to one of four groups: two experimental groups, for which either ANLS based on attention state estimation or ANLS based on both attention and comprehension states estimation was tested, and two control groups, the students in which were taught using either the conventional online lecture without feedback or an online course with randomized video feedbacks. Each member of these groups attended a 53 min open courseware video lecture. Then, the educational effects of the proposed system were evaluated quantitatively via a written examination. Our results revealed a significantly higher learning performance for the experimental group (average test score of the experimental groups = 83.83 and that of the control groups = 56.67), demonstrating the feasibility of the proposed education strategy.
The digital age in which we live today is witnessing technological development and an information revolution in various fields. This technological development has been imposed on education and it has become important to recognise adaptive e-learning systems as one of the most interesting research areas in online distance education. This area of research allows developers to build a distinct learning environment that meets the needs of each learner separately, in order to adapt learning to their needs and characteristics. This paper aims to give an overview of state-of-the-art adaptive and intelligent e-learning systems by describing their features and architecture, as well as the actual implementations. the authors also highlight some prospects for future work by reviewing, discussing and analysing existing systems. In addition, the authors propose an overall architecture with the system components that will be used to run our mobile application.
In enterprise context, companies constantly aim to optimize their human resources and acquire new ones. Employees, also called talents, are required to achieve new skills for the company to stay competitive in the business. The talents’ ability to productively improve is a crucial factor for the success of a company. We propose Adaptive Talent Journey, a novel method for optimizing the growth path of talents within a company. The ultimate goal of Adaptive Talent Journey is to hold talent back inside the company. It exploits the notion of “digital twin” to define a digital representation of the talent, namely Talent Digital Twin, built on the basis of skills level and personal traits. Given a target company’s role, Adaptive Talent Journey proposes the most suitable path of work experiences (journey) to improve the skills of a talent so to achieve the target role requirements. Such a mechanism resonates with the Reinforcement Learning paradigm, and specifically with Deep Q-Learning. Specifically, the proposed method exploits: (i) two double Deep Q-Networks (DDQNs) for selecting the work experiences to be made; (ii) a transition module to support the DDQNs training and ensure good performance despite the limited availability of data. We implemented and deployed Adaptive Talent Journey in an intuitive Web application, namely ATJWeb. We evaluated both the effectiveness and efficiency of our proposal and the users’ satisfaction in using it, adopting, as a testbed, an IT company with its employees. Results proved that the Adaptive Talent Journey can optimize the growth path of talents, and that ATJWeb is pleasant and useful.
Full-text available
Abstract Advances in cognitive psychology,deepen our understanding of how students gain and use knowledge. Advances in technology make it possible to capture more complex performances in assessment settings, by including, for example, simulation, interactivity, collaboration, and constructed response. The challenge is in knowing just how to put this new knowledge,to work. Familiar schemas,for designing and analyzing tests produce assessments that are useful because they are coherent, within the constraints under which they evolved. Breaking beyond the constraints requires not only the means for doing so (through the advances mentioned above) but schemas for producing assessments that are again coherent; that is, assessments that may indeed gather complex data to ground inferences about complex student models, to gauge complex learning or evaluate complex,programs—but,which build on a sound chain of reasoning from what we observe to what we infer. This presentation first reviews an evidence-centered framework,for designing and analyzing assessments. It then uses this framework,to discuss and to illustrate how advances in technology and in education and psychology can be harnessed to improve educational assessment.
Full-text available
The purpose of this study was to investigate the relationship between programming skill acquisition and various measures of individual differences, including: 1) prior knowledge and general cognitive skills (e.g., word knowledge, information processing speed); 2) problem solving abilities (e.g., ability to decompose a problem into its constituent parts); and 3) learning style measures (e.g., asking for hints versus solving problems on one's own). Subjects ( N = 260) received extensive Pascal programming instruction from an intelligent tutoring system. Following instruction, an online battery of criterion tests was administered measuring programming knowledge and skills acquired from the tutor. Results showed that a large amount (68%) of the outcome variance could be predicted by a working-memory factor, specific word problem solving abilities (i.e., problem identification and sequencing of elements) and some learning style measures (i.e., asking for hints and running programs). Implications of the findings for the development of a theoretical framework on which to base programming instruction are discussed.
In this paper, IEEE Learning Technology System Architecture (LTSA) for LMS software has been analyzed. It has been observed that LTSA is too abstract to be adapted in a uniform way by LMS developers. A high level design that satisfies the IEEE LTSA standard has been proposed for future development of efficient LMS software. A hybrid model of learning fitting into LTSA model has also been proposed while designing.
New conceptions of aptitude, learning, development, and achievement, both cognitive and conative, are identified and some new ideas about their assessment are reviewed. A rough table of these constructs is provided. It is argued that much construct validational research is needed to understand the new constructs and place them in a reasonable and useful network. Also needed is a recognition that different purposes for educational assessment require different levels and models of assessment. A plea for research on teacher understanding and use is included, because no improvements in school level assessment can be reached without it.
The origins and development of the concept of aptitude complexes are reviewed. Initial empirical success in demonstrating interactions between aptitude complexes and instructional complexes by Richard E. Snow and his students is followed by an inductive approach to finding broader trait complexes. Three empirical studies of college students and adults up to age 62 are described, where trait complexes were correlated with domain knowledge and ability measures. Differentiated profiles of trait complex-knowledge-ability correlations were found and replicated across the 3 studies. Evidence for trait complexes that are supportive or impeding for the development of domain knowledge is reviewed. The aptitude complex-trait complex approach is viewed as an important means toward researching and reevaluating the nature of aptitude-treatment interactions.