A MODEL FOR IMPROVING ENTERPRISE’S PERFORMANCE
BASED ON COLLABORATIVE E-LEARNING
Camelia Delcea
Department of Cybernetics, University of Economics, Bucharest, Romania
Maria Dascălu, Cristian Ciurea
Department of Informatics,University of Economics, Bucharest, Romania
Keywords: Collaborative e-Learning, Enterprise’s Performance, Grey Systems Theory, Fuzzy Sets Theory.
Abstract: Collaborative learning and e-learning are believed to be very important to the success of enterprises. Some
qualitative and quantitative variables that characterises collaborative learning through e-learning are
depicted. The incidence degree between them and enterprise’s performance was determined through a
model. Also, the difference between enterprise’s financial and non-financial performance was underlined.
The proposed model is constructed using the facilities offered by grey systems and ϕ-fuzzy sub-set theory.
For better understand the model, we used it on two branches of the same bank. We conclude our paper by
presenting and comparing the obtained results and by giving some future work guidelines.
1 INTRODUCTION
The economic context in which firms carry out their
activities is dynamic and constantly changing.
(Delcea & Scarlat, 2009)
By identifying changes and anticipating them,
firms can take decisions to compensate or eliminate
any negative effects and leverage the positive
effects, thus facilitating the achievement of the
firm’s goals.
Also, as Nonaka pointed out, in an economy
where the only certainty is uncertainty, the one
source of lasting competitive advantage is
knowledge (Nonaka, 1991).
From this point of view, an organization that
fails to learn may be sub-optimal or even
dysfunctional (Law & Ngai, 2008).
As Slater and Narver (1995) argue, an enterprise
with a continuous tendency of learning has a better
chance to respond to customer needs, to sense the
market opportunities and to offer more appropriate
and more finely targeted products, all these leading
the enterprise to superior levels of profitability, sales
growth and customer retention.
Over the years, all the traditional learning
techniques were revised and new ones were
introduced. Internet-oriented applications and e-
learning were the revolutionary new ways through
which the workforce got the necessary needed skills
and knowledge (Tzouveli, Mylonas, & Kollias,
2008).
In an enterprise, partners may accumulate
substantial experience and lessons through learning
from each other. Some theoretical and practical
learning related to how to avoid repetitious mistakes,
how to reduce production and transaction costs, and
how to enhance the capacity of mutual
understanding, coordination, and problem solving
can be acquired by partners’ interaction (Jiang & Li,
2008) . Sometimes, when partners are faced with a
physical distance, this collaborative interaction can
be done only through computer, mainly by
discussion forums and teleconference.
Depending on enterprise’s strategy, some
components of collaborative learning through e-
learning can be identified.
Our purpose is to identify the qualitative
variables that characterise best the collaborative
learning from the point of view of e-learning and
how these components are influencing enterprise’s
performance.
We will also analyse the enterprise performance
from two directions. The first one is given by the
5
Delcea C., Dasc
ˇ
alu M. and Ciurea C. (2010).
A MODEL FOR IMPROVING ENTERPRISE’S PERFORMANCE BASED ON COLLABORATIVE E-LEARNING.
In Proceedings of the 12th International Conference on Enterprise Information Systems - Human-Computer Interaction, pages 5-12
DOI: 10.5220/0002864600050012
Copyright
c
 SciTePress

accountants’ point of view, related to the financial
perspective, while the second one is coming from
the managerial point of view.
Based on the idea that each firm is different from
another, we proposed a single firm model that will
help the managers to decide which component of
collaborative learning they should improve on their
enterprises based on their purpose. For this reason
the qualitative variables taken into account will be
ordered using grey systems theory and ϕ-fuzzy sub-
set theory as we shall see in the following.
2 COLLABORATIVE LEARNING
THROUGH E-LEARNING IN
ENTERPRISES
Over the past years, work becomes more
interdisciplinary, complicated and nevertheless
knowledge-based. In this sophisticated environment,
in which enterprises carry out their activity, e-
learning succeeded through the different interaction
tools to offer ample opportunities for learners to
collaborate with peers, experts, professionals or with
other learners.
The evolution of knowledge-based society
involves the development of enterprises through a
collaborative learning environment. Collaboration is
an important dimension when it comes to sharing
and integrating the experiences and training courses
of different groups of learners. Supervisors,
instructors, and learners from enterprises play
different roles in the learning process. They need to
work in the same environment, collaboratively
instead of individually, to perform an adaptive
learning strategy. (Yi, Schwaninger, & Gall, 2008)
In an enterprise, the use of collaborative learning
can develop higher level thinking skills, social
interaction skills, responsibility for each other and
even promote higher achievement. (Chang & Lee,
2009)
Interaction between learners is indispensable to
collaborative learning, and learners need to do real
work together in which they promote each other's
success by sharing resources, discussing, helping,
and congratulating each other's efforts to achieve.
(Wu, Zhengbing, Yang, & Liu, 2009)
The collaborative learning process from an
enterprise may be achieved through a virtual campus
or an intranet e-learning platform. The intranet
collaborative learning system should focus on how
to instruct and stimulate learners to achieve
knowledge, and the system is to visualize traditional
classroom education and learning environment in
web. (Xiuhua & Wenfa, 2008)
The intranet collaborative learning system is a
virtual organizational structure of collaborative type
in which interact three target groups:
 The target group of learners, composed by
participants in tele-activities of training, testing,
documentation, participation in online meetings,
forums communication;
 The target group of teachers who complete
multimedia teaching materials for virtual
campus training, evaluates papers submitted
online, update databases proper evaluations;
 The target group of people outside the system,
which informs about the performance on
collaborative learning system and which allows
the selection on learners by interact and
conveying the information. (Ciurea, 2009)
Related to the idea of collaboration through
virtual knowledge spaces some systems have been
developed that insure more flexible mechanisms to
foster communication and cooperation in learning
and work processes. (Eßmann, Gotz, & Hampel,
2006)
Based on recent researches, some quantitative
and qualitative characteristics regarding the
collaborative learning through e-learning can be
identified, with a peculiar impact on enterprise’s
performance.
Some of qualitative characteristics related to the
knowledge acquisition (at individual, group and
enterprise level) and learning flow (exploration and
exploitation) are listed in the following: (Kreijns,
Kirschner, & Jochems, 2003) (Baker & Sinkula,
1999), (Prieto & Revilla, 2006) (Bodea & Dascalu,
2009)
 The degree of group cohesion gained through
collaborative learning;
 The development of critical thinking, shared
understanding, and long term retention of the
learned material;
 The capability of the collaborative learners to
resolve effectively the conflicts;
 The capacity of sharing successes and failures
within the collaborative group;
 The degree of confidence and responsibility felt
by individuals about doing their work;
 The degree to which the quality of the
enterprise’s market-oriented behaviours are
improved by collaborative learning through e-
learning;
ICEIS 2010 - 12th International Conference on Enterprise Information Systems
6

 The quality of enterprise’s learning structure
that allows working effectively;
 The quality of internal training and work
training through collaborative e-learning
provided within the organization;
 The development of social and
communicational skills;
 The degree to which the collaborative learning
through e-learning enables the development of
competencies and skills for working properly.
From the quantitative point of view, we can
identify the following variables:
 The number of qualifications that the
employees are getting in an year period;
 The number of employees that are using
collaborative learning through e-learning in
enterprise;
 Collaborative learning group size;
 The number of training sessions that the
enterprise is financing in a year period.
All these variables and other more that can be
identified at enterprise’s level can be analysed and
ranked based on their influence on enterprise’s
financial and non-financial performance, as we shall
see in the following sections.
3 FINANCIAL AND
NON-FINANCIAL
PERFORMANCE MEASURE
The importance and the impact of organizational
learning or learning orientation on financial and non-
financial performance have been recognized in the
research literature related to this field many years
ago. (Jiang & Li, 2008)
The financial performance of an enterprise can
be measured through several indicators: sales
growth, increase in overall profitability, increase in
sales resulting from new products, improvement in
work productivity, improvement in production cost,
enterprise’s market share, defect rates, earnings per
share (EPS), return on assets (ROA), return on
investment (ROI), net income after tax (NIAT) and
other more, depending on the enterprise’s goals.
As for the non-financial performance, even it has
no intrinsic value for companies’ directors, it can be
used as a leading indicator of financial performance,
especially for future financial performance that is
not yet contained in the accounting measures. (Prieto
& Revilla, 2006)
Through the indicators that are measuring the
non-financial performance we can firstly identify the
customers’ satisfaction, expressed qualitatively by
the degree of satisfaction felt by customers or
numerically by the average number of satisfied
customers or by the number of customers whose
level of satisfaction exceeds a certain level.
Knowing that satisfied customers are more likely to
buy a greater volume of enterprise’s products or
services, or even to recommend those
products/services to other potentially customers, the
cost of attracting new customers is lower, the failure
costs are reduced and the financial performance is
increased.
Another performance indicator, non-financial by
its nature, can be enterprise’s reputation. Having a
high reputation, an enterprise can easily introduce
new products and services, by reducing the buyer’s
risk of trial. (Anderson, Fornell, & Lehman, 1994)
Also, a good reputation can lead to a good
maintenance of the relationships with key suppliers,
distributors and potential allies. (Anderson, Fornell,
& Lehman, 1994)
Without expanding, other variables that succeed
in measuring non-financial performance can be
taken into account: employee satisfaction or morale,
employee efficiency, quality of products and
services, growth of number of customers, on-time
delivery, long term relation with suppliers and
customers response time.
Even the enterprise’s management is giving a
higher importance to the financial performance, the
non-financial performance is also extremely
important by the fact that it leads to the achievement
of a better financial performance, through a higher
reduction of production costs, an increasing in
productivity, an improving the yield or reducing the
material consumption and nevertheless a higher
level of sales growth over time.
Because all the two components of enterprise’s
performance are important, in the proposed model
we will analyse the impact that collaborative
learning through e-learning has on both financial and
non-financial performance.
4 THE RESEARCH MODEL
The model proposed in this paper is a hybrid one,
obtained by fusion between grey systems theory and
fuzzy theory. While fuzzy theory has the methods
A MODEL FOR IMPROVING ENTERPRISE'S PERFORMANCE BASED ON COLLABORATIVE E-LEARNING
7

and techniques for treating the quantitative variables,
but especially the qualitative ones, grey systems
theory manages to achieve good performance in
analysis conducted on a small range of data and on a
large number of variables.
4.1 Preparation
In this section we will present some definitions and
formula related to grey arithmetic and grey
incidence which we will use in the proposed model.
4.1.1 Grey Systems Theory Arithmetic
Definition: A grey number is a number whose exact
value is unknown but a range within the value lies is
known. (Liu & Lin, 2005)
In applications, a grey number in general is an
interval or a general set of numbers.
Assume that
1
⊗
and
2
⊗
are two grey numbers,
defined as follows:
baba <∈⊗ ],,[
1
and dcdc <
∈
⊗ ],,[
2
The following operations between them can be
done (Liu & Lin, 2005):
 Sum:
],[
21
dbca +
+
∈⊗+⊗
(1)
 Difference:
],[)(
2121
cbda −−∈⊗−+⊗=⊗−⊗
(2)
 Reciprocal: The reciprocal of
],[
1
ba∈⊗
with
ba <
and
0>ab
, noted
1
1
−
⊗
is defined as:
]
1
,
1
[
1
1
ab
∈⊗
−
(3)
 Product:
}],,,max{
},,,,[min{
21
bdbcadac
bdbcadac∈⊗•⊗
(4)
 Quotient:
1
21
2
1
−
⊗•⊗=
⊗
⊗
(5)
 Scalar multiplication: Assume that k is a
positive real number, the scalar multiplication
of k and
1
⊗
is defined as follows:
],[
1
kbkak ∈⊗•
(6)
Theorem: Interval grey numbers cannot in
general be cancelled additively or multiplicatively.
More specifically, the difference of any two grey
numbers is generally not zero, except in the case that
they are identical. And the division of any two grey
numbers is generally not 1 except in the case when
they are identical. (Liu & Lin, 2005)
4.1.2 Relative Degree of Grey Incidence
From the grey systems theory (Liu & Lin, 2005) we
will use in this paper only de items related to the
construction of the relative degree of grey incidence
and its calculation.
Assume that X
0
and X
j
, j=1...n, are two
sequences of data with non-zero initial values and
with the same length, with t = time period and n =
variables:
),,,,,,(
0,0,40,30,20,10 t
xxxxxX …=
(7)
),,,,,,(
,
,4,3,2,1
jt
jjjj
j
xxxxxX …=
(8)
The initial values images of X
0
and X
j
are:
),,,(),,,(
0,1
0,
0,1
0,2
0,1
0,1
'
0,
'
0,2
'
0,1
'
0
x
x
x
x
x
x
xxxX
t
t
…… ==
(9)
),,,(),,,(
,1
,
,1
,2
,1
,1
'
,
'
,2
'
,1
'
j
jt
j
j
j
j
jtjjj
x
x
x
x
x
x
xxxX …… ==
(10)
The images of zero-start points calculated based
on (3) and (4) for X
0
and X
j
are:
),,,(
),,,(
0'
0,
0'
0,2
0'
0,1
0,1
'
0,
'
0,1
'
0,2
'
0,1
'
0,1
''0
0
t
t
xxx
xxxxxxX
…
…
=
−−−=
(11)
),,,(
),,,(
0'
,
0'
,2
0'
,1
,1
'
,
'
,1
'
,2
'
,1
'
,1
''0
jtjj
j
jt
jjjj
j
xxx
xxxxxxX
…
…
=
−−−=
(12)
The relative degree of grey incidence is given by:
jj
j
j
ssss
ss
r
'
0
'''
0
'
0
'
0
1
1
−+++
++
=
(13)
where
0
'
s and
j
s
'
are computed as follows:
∑
−
=
+=
1
2
0'
0,
0'
0,
0
'
2
1
t
k
tk
xxs
(14)
∑
−
=
+=
1
2
0'
,
0'
,
'
2
1
t
k
jtjk
j
xxs
(15)
The relative degree of grey incidence represents
a numeric characteristic for the relationship of
closeness between the two sequences.
In practical numerical examples, the numerous
degree of grey incidence developed in the literature
ICEIS 2010 - 12th International Conference on Enterprise Information Systems
8

were used to measure the incidence between two
quantitative variables. In our paper, we include some
qualitative variables related to collaborative learning
and we try to determine their influence on enterprise
performance. For a better work with qualitative
variables we will use some “expertons” built as it
can be seen from the following section.
4.1.3 Expertons
Fuzzy logic offers the suitable tools for the treatment
of uncertainty and subjectivity. Because in our
model, we will work with qualitative variables, we
will use the ϕ-fuzzy sub-set theory and some
exertons.
The main characteristic of fuzzy sub-sets is that
the function characteristic of membership is taking
its values from [0; 1] instead of {0; 1}. For a better
representation of reality, we will consider that those
values are intervals and not numbers, situated in [0;
1]. (Gil-Lafuente, 2005)
Once with the idea of ϕ-fuzzy sub-set comes
even the idea that the opinion of a single expert is
being insufficient. That is the reason why it is
preferred to gather several experts’ opinion and even
to construct an experton.
Expertons are in fact intervals built using the ϕ-
fuzzy sub-set and the opinion of several experts over
a certain problem. For a complete reading on how
these expertons are built, see (Gil-Lafuente, 2005).
4.2 The Research Model
The proposed model combines the advantages
offered by grey systems theory and ϕ-fuzzy sub-set.
Figure 1 summarises the steps involved.
We shall mention that in first stage of the model
construction we will use some experts for the
selection of the collaborative e-learning variables
that are the most important at enterprise’s level.
Also, the team of experts will establish the
performance indicators that will be measured and
used, one for the financial performance and another
one for the non-financial performance. Depending
on the manager’s will, it can be taken into account
only the performance or only the non-performance
indicator.
In the next step, the quantitative variables,
including the quantitative performance indicators are
measured. In some cases, enterprise’s financial
statement or other enterprise’s documents can be
used.
The qualitative variables are also measured. For
this, each expert from the team will give his opinion
Figure 1: The proposed model.
on the values of qualitative variables through a
number or an interval between 0 and 1 in the
following manner: if an expert is absolutely sure
about the level of the considered variable, he will
note that value through a number; otherwise, he will
record an interval. Also, if the expert has no clue
about the values among which the variable can be
found, he will simply record the whole [0; 1]
interval.
After gathering all experts’ opinions, an experton
will be build for each variable.
Having all the variables measured, we will apply
the grey arithmetic on intervals presented at 4.1.1 to
the relative degree of grey incidence.
By computing, the collaborative e-learning
variables taken into account are ordered based on the
value of the relative degree of grey incidence.
Acting on them, the financial and the non-financial
situation of a company can be improved.
5 REAL NUMERICAL
APPLICATION
In period July 2008 – October 2009 we conducted a
study on two branches of Raiffeisen bank. Our
A MODEL FOR IMPROVING ENTERPRISE'S PERFORMANCE BASED ON COLLABORATIVE E-LEARNING
9

purpose was to detect which of the qualitative or
quantitative characteristics of collaborative
e-learning through learning identified in the two
branches are influencing the performance of each of
them. By comparing the findings we can establish
some similarities and some differences as we will
see further.
For this purpose, a number of four specialists in
the field helped us. Based on the interviews with the
managers of the two branches we established the
performance indicators. For the financial
performance we measured the sales growth (noted
X
0
P
), while for the non-financial performance: the
average number of satisfied customers (X
0
NP
). The
period of time of almost 15 month was divided into
five equal periods, each of them having three
months.
The qualitative and quantitative characteristics
identified related to the knowledge acquisition and
learning flow that are gained through the
collaborative learning held in the branches’ that are
more appropriate to influence their performance are
listed below: the development of social and
communicational skills (X
1
), the increase of
competences as a result of the collaborative learning
process made through e-learning (X
2
), the
development of critical thinking, shared
understanding and long term retention of the learned
material (X
3
), the average size of collaborative
learning group (X
4
) and the number of employees
that are using collaborative learning through e-
learning (X
5
).
For the qualitative variables (X
1
, X
2
and X
3
),
whose values were expressed by each one of the four
experts through intervals or numbers between 0 and
1, we have built three expertons for each branch.
The values of all the variables, including the
expertons, were gathered in two tables as they can
be seen in Figure 2 and Figure 3.
Next, we apply the relative degree of grey
incidence. In the qualitative variables case,
expressed through expertons, we will use some grey
arithmetic on intervals presented at 4.1.1.
Figure 2: The values of performance indicators and
qualitative and quantitative variables collected at Branch
1.
Figure 3: The values of performance indicators and
qualitative and quantitative variables collected at Branch
2.
After computing, the following results were
found. Figure 4 summarizes the values of the
relative degree of grey incidence for the case when
we are interested on financial performance, while
Figure 7 summarizes the values of the relative
degree of grey incidence for the case of non-
financial performance.
Figure 4: The values of the relative degree of grey
incidence on financial performance obtained in the two
branches.
For the first branch, from r
05
P
> r
02
P
> r
03
P
> r
01
P
>
r
04
P
it can be seen that
41325
XXXXX  .
This is equivalent to say that the most influencing
factor in this case is the number of employees that
are using collaborative e-learning, while the factor
with the less influence is the average size of the
collaborative learning group. As for the second
branch, it can easily be seen that the factor with the
most and the less influence remains the same, with
the only difference that the order of the qualitative
factors is
321
XXX  .
Graphically the values obtained in the two
branches cases are represented in Figure 5 and
Figure 6 below:
Figure 5: The values of the relative degree of grey
incidence for each variable on financial performance
indicator - Branch 1.
ICEIS 2010 - 12th International Conference on Enterprise Information Systems
10

Figure 6: The values of the relative degree of grey
incidence for each variable on financial performance
indicator - Branch 2.
For the non-financial performance case, the
values of the relative degree of grey incidence are
presented in the following figure:
Figure 7: The values of the relative degree of grey
incidence on non-financial performance obtained in the
two branches.
In the case of non-financial performance, the
order of the variables identified at first branch’s
level according to their relative degree of grey
incidence is:
24351
XXXXX  . That is
equivalent to say that the average number of
satisfied customers depends most on the
development of social and communicational skills of
the employees. For the second branch, the increase
of competences as a result of collaborative learning
process is the most influencing variable on non-
financial performance, followed by X
4
, X
1
, X
3
and
X
5
. This can also be seen from Figure 8 and 9.
Figure 8: The values of the relative degree of grey
incidence for each variable on non-financial performance
indicator - Branch 1.
Figure 9: The values of the relative degree of grey
incidence for each variable on non-financial performance
indicator - Branch 2.
6 CONCLUSIONS
In the analize of enterprise’s performance a peculiar
attention should be given to the variables that are
influencing it. From this cathegory, the variables that
undeline the level of collaborative e-learning
represent an important cathegory.
Starting from idea that each enterpise is unique,
we propose a single-enterprise model, built using
grey systems theory and ϕ-fuzzy sub-set theory.
By simulating the model on the data collected in
the two branches, it was easy to see that the results
obtained in the two cases were different. From this
point, based on each manager’s purpose, the
manager can decide whether to act on the variables
that are influencing financial or to the ones that are
influencing the non-financial performance. For our
numerical example, in the first branch case, if the
manager wants to improve the financial
performance, he/she should try to increase primary
the number of the employees which are using the
collaborative e-learning by offering the possibility of
studying through intra/internet and through
collaboration to a large number of employees. Or,
contrary, if the non-financial performance is aimed,
the manager should concentrate on the
communicational skills, which can be acquired
through some training sessions.
The research can be extended to include facilities
offered by other theories, such as case based
reasoning, which is similar to the human way of
thinking. Also, a soft procedure can be created in
order to aggregate easier the identified variables and
the experts’ opinions. In order to bring future
improvement to the proposed model, the number of
variables can be extended by taking into account
other variables unrelated to the collaborative e-
learning.
A MODEL FOR IMPROVING ENTERPRISE'S PERFORMANCE BASED ON COLLABORATIVE E-LEARNING
11

ACKNOWLEDGEMENTS
This article is a result of the project „Doctoral
Program and PhD Students in the education research
and innovation triangle”. This project is co funded
by European Social Fund through The Sectorial
Operational Program for Human Resources
Development 2007-2013, coordinated by The
Bucharest University of Economics.
REFERENCES
Anderson, E., Fornell, C., & Lehman, D. (1994).
Customer Satisfaction, Market Share, and
Profitability: Findings from Sweden. Journl of
marketing .
Baker, W., & Sinkula, J. (1999). The Synergistic Effect of
Market Orientation and Learning Orientation on
Organizational Performance. Journal of the Academy
of Market Science , 411-427.
Bodea, C. N., & Dascalu, M. I. (2009). Designing Project
Management Tests on Semantic Nets and Concept
Space Graph. The 12th International Business
Information Managemnet Association Conference,
(pp. 1232-1236). Kuala Lumpur.
Chang, C.-K., & Lee, C.-S. (2009). Using Computer-
Assisted Test to Harmlessly Improve the Efficiency of
Heterogeneous Grouping in Collaborative Learning.
International Conference on Advanced Computer
Control, (pp. 129-133).
Ciurea, C. (2009). A Metrics Approach for Collaborative
Systems. Informatica Economica Journal , 41-49.
Delcea, C., & Scarlat, E. (2009). The Diagnosis of Firm's
"Disease" Using the Grey Systems Theory Methods.
IEEE Grey Systems and Intelligent Services, (pp. 755-
762). Nanjing, China.
Eßmann, B., Gotz, F., & Hampel, T. (2006). Collaborative
Visualisation in Rich Media Environments. Enterprise
Information Systems, 8
th
International Conference,
ICEIS, (pp. 375-387). Paphos, Cyprus
Gil-Lafuente, A. M. (2005). Fuzzy Logic in Financial
Analysis. Berlin Heidelberg New-York: Springer.
Jiang, X., & Li, Y. (2008). The relationship between
organiyational learning and firms' financial
performance in strategic alliance: A contingency
approach. Journal of World Business , 365-379.
Kreijns, K., Kirschner, P., & Jochems, W. (2003).
Indentifying the pitfalls for social interaction in
computer-supported collaborative learning
environments: a review of the research. Computers in
Human Behaviour , 335-353.
Law, C., & Ngai, E. (2008). An empirical study of the
effects of knowledge sharing and learning behaviours
on firm performance. Expert Systems with
Applications , 2342-2349.
Liu, S., & Lin, Y. (2005). Grey Information. Theory and
Practical Applications. London: Springer-Verlang.
Nonaka, I. (1991) The knowledge creating company,
Harward Business Review 69, 96-104.
Prieto, I., & Revilla, E. (2006). Learning Capability and
Business Performance: a Non-financial and Financial
Assessment. The Learning Organization.
Slater, S., & Narver, J. (1995). Market orientation and the
learning organization. Journal of Marketing, 63-74
Tzouveli, P., Mylonas, P., & Kollias, S. (2008). An
intelligent e-learning system based on learner profiling
and learning resources adaptation. Computers &
Education , 224-238.
Wu, J., Zhengbing, H., Yang, Z., & Liu, Y. (2009). Design
of Collaborative Learning in Cyber-Schools. First
international Workshop on DatabaseTechnology and
Applications, (pp. 703-706).
Xiuhua, H., & Wenfa, H. (2008). An Innovative Web-
Based Collaborative Learning Model and Application
Structure. International Conference on Computer
Science and SOftware Engeneering.
Yi, G., Schwaninger, A., & Gall, H. (2008). An
Architecture for an Adaptive Collaborative Learning
Management System in Aviation Security. 17th IEEE
Workshop on Enabling Technologies: Infrastructure
for Collaborative Enterpises, (pp. 165-170).
ICEIS 2010 - 12th International Conference on Enterprise Information Systems
12