You are on page 1of 9

Volume: 03, Issue: 02, December 2014

Pages: 454-462

International Journal of Data Mining Techniques and Applications


ISSN: 2278-2419

A Hybrid Approach for Ranking and


Rating of Web Based e-Learning Portal
Sumathy.K.L1, UmaShankari S2, CathreenGracia Mary. A3, Chidambaram M4
1, 2& 3

Research scholar, Department of Computer Applications, Bharathiyar University, Coimbatore.


4

Asst. Professor, Rajah serofiji College, Thanjavur.

Email: sumathyavc@yahoo.co.in, umabalajees@gmail.com


ABSTRACT:
Web based e-Learning plays a vital role among knowledge seekers, hence it is very essential to rank and rate the
e-Learning portals in an efficient manner. This rating and ranking is based on the integration of Knowledge
Management(KM) & e-Learning system framework along with multi dimensional metric based evaluation
method, which are useful in assessing any given knowledge management system. The main goal of this research
paper is to propose the methodology for ranking and rating the web based e-Learning portals, using a Multidimensional metric model, metric database and the Weighted Average Mean (WAM) method. This paper first
describes the actual implementation steps for building the e-Learning Systems metric database, using the multidimensional metric mode and assigns the weights and values generated in the metric database. Secondly this
paper attempt to demonstrate how the e-Learning portals can be ranked and rated for its effectiveness using the
proposed hybrid evaluation.
Keywords:e-Learning, Knowledge Management, Evaluation, Hybrid, WAM,Metric Database
1. INTRODUCTION
The key objectives of the web based e-Learning
portals are to make purposeful connections to the
knowledge seekers and to provide visualized
methods of e-Learning to enhance more
understanding. The e-Learning portal also helps to
enhance learning processes and knowledge access
methods by reducing unnecessary and unrelated
information. This paper has been organized in to
multiple sections. The first section gives a brief
overview about e-Learning and the framework for
web based e-Learning portals and knowledge
management system.
The second section deals with the KM metrics and
measurement process and supporting evaluation
methodology chosen for evaluating e-Learning
portals.
The third section discuss in detail about multi
dimensional metric model and steps for building a
metric database.
The fourth section contains about the required
dimensions and measures for evaluating the
eLearning portal.
The fifth section discusses about our experiment
and the ways to apply WAM method using the
derived data from the metric database for ranking
and rating the web based e-Learning portals.
The last section summarizes the methodology and
how this ranking and rating is useful for evaluating
e-Learning portal and proposes the new research
avenues in this area for further research.

Integrated Intelligent Research (IIR)

2. E-LEARNING PORTALS AND


SUPPORTING FRAMEWORKS
2.1 About e-Learning
Distance learning, sometimes called eLearning, is a
formalized teaching and learning system
specifically designed to be carried out remotely by
using electronic communication.Because distance
learning is less expensive to build and support, and
also not constrained by geographic considerations.
It offers opportunities in situations where
traditional education becomes more difficult in
operating. Anyone can benefit from eLearning
anytime, anywhere. Theres no limit to the kind of
content that we can develop into an effective
eLearning course. The reason why eLearning has
becoming the medium of choice since the direct
teaching or training methodology is becoming
expensive, due to the costs for trainer and other
costs such as travel and facilities such as training
room with supporting infrastructure. Additionally,
Interactive learning training is not always as
efficient as it needs to be, considering the high
student-to-teacher ratio. Many of the students
requests the teacher for a web portals which teach
them the concepts and the related techniques easily.
The content may be text-based or any graphical
based working demonstration. Hence E-Learning
brings usability into a shared arena, highlighting
the need for technical or design experts and
academic experts to work together more closely
than ever before to produce usable websites. The
following diagram shows the main factors affecting
the web based e-Learning systems adapted from
[5].

454

Volume: 03, Issue: 02, December 2014


Pages: 454-462

International Journal of Data Mining Techniques and Applications


ISSN: 2278-2419
and learners in collaborative discussion on
assignments
The Content management module of the eLearning
system is built

To support the content developers and content


managers in importing and exporting content
through the authoring tools.

To interface with data repository containing


learners' personal information and other
metadata including knowledge assets created
by knowledge management modules and to
apply these data in creating personalized
sequence of content material suitable for each
learner.

Figure 1: Factors of e-Learning Systems


2.2 Framework for web based e-Learning Portal
The design of web based e-Learning is usually
derived on the basis of learning content
management system The following are four main
modules proposed in the framework (as shown in
Figure 2) based on [5]

Learning management module

Content management module

Knowledge management module

Interaction Management module

The Knowledge management module serves as


supporting module

To discover valuable knowledge assets from


the data repository containing learners'
personal data, tracked data of learners'
performance and behavior, and data related to
content sequences that were presented in the
past with the evaluation results according to
that content sequence.

To support the indexing and mapping of


knowledge assets that are discovered by the
knowledge mining engine.

The Interaction management module of the eLearning system is built

Figure 2: Framework for web based eLearning portal


The Learning management module of the
eLearning System is built

To support instructors to post syllabi, conduct


assessments,
class
schedules,
submit
assignments, lecture notes, slides along with
supplemental materials for learners to access
via Web browsing tool .

To provide profiling tool to collect personal


data of learner and tracking tool to observe
learners' actions including like and dislike
information.

To provide matchmaking tool to compare the


created profile with the available content and
also to provide additional support instructors

Integrated Intelligent Research (IIR)

To provide the Learner with different type of


e-Learnning methodlogies
like case
study,practical examples,virtual classrooms,
dicussion forum, step by step learning method,
video based trainuing.

To provide a interactive support to the learner


thru feedbak forms,reviews

To support the learner with various links and


libraray resourecs

The major component of learning management


module is learning manager which acts as a
conductor controlling and synchronizing every
component within the modules. The manager
component is also responsible for interfacing with
the storage. This is also the case for the content
manager in content management modules. The
authoring tools in content management modules
support creation of all types of digital content
materials such as word documents, spreadsheet
data, pictures in standard formats, video content,
animation and multimedia data. For the knowledge
management modules, knowledge mining engine is
responsible for the synchronizing process. Indexing
and mapping is a component for storing and
searching knowledge assets to be used in the
learning process.

455

Volume: 03, Issue: 02, December 2014


Pages: 454-462

International Journal of Data Mining Techniques and Applications


ISSN: 2278-2419

2.3 Build Metric Database for eLearning Portal


The implementation of the metric database is shown
in the figure (Figure 3) below; it was created to hold
the user and expert feedback of the considered
dimensions and measures for evaluating the
effectiveness of the KM system. The databases used
in the existing infrastructure can be considered for
storing the metrics and measurements. The volume
of data and the amount of transactions used for the
KMS measurement are less. So, there is no need for
a dedicated or high performance database and the
existing database used for infrastructure
maintenance or application database can be used to
store the schema and data. If the models and
databases are systematically developed to be
flexible, effective and scalable, surely the data can
be explored using the data mining technique or the
Weighted Average Mean Method.
The metric database can be created using any
industry specific database systems. There are four
steps in implementing the multi-dimensional metric
database:
1. Gather the evaluation factors for
assessment.
2. Decide the Quality Factor and Sub Factors
3. Create Data Objects such as Tables or
Classes or XML to hold the Quality Factor/Entities
and Attributes/measures.
4. Upon collecting the measures, store them in
the data objects
The metric database for the Web Based E-Learning
Evaluation Experiment has been implemented,
using Microsoft Sqlserver 2008 and relevant metrics
were collected through Hybrid Approaches [2],
manual feeds and customized programs. The data
was generated, based on the inputs from the user,
the expert and the system. As seen from the ER
diagram (Figure 3) below, our metric database is
designed to be flexible to hold any dimension and
metric as per the rating from the user (normal user
or expert user). The database consists of five key
tables. The KA_BASE_TBL which is the base table
that contains the knowledge asset created/modified
in the knowledge portal or repository. The
KA_USER_TBL holds the information about the
user name, user type and their details. The
KA_USER_RATING table holds the user feedback
on
the
given
measure.
The
KA_METRIC_BASE_TBL which is our main table
that holds attributes like the metric id (MID), metric
description (MDESC), metric weight (MWEIGHT)
and
the
corresponding
quality
factor
(DIMENSION).

Figure 3: Web Based e-Learning Metric Database


ER Diagram
The metrics database can provide multiple benefits
for any organization and some of the key benefits
are listed below:
1. Performance Prediction of the portals
2. Identify Issues, challenges and or gaps
3. Capture measures for rewarding the workers
3 DIMENSIONS AND MEASURES FOR
WEB BASED ELEARNING PORTAL
3.1 Dimensions and measures for web-based eLearning
The following section discusses about the measures
and metrics corresponding to some of the prime
quality factors which will be given weights in the
80% category for evaluating web based e-Learning
portal. The diagram below represents the multiple
key dimensions considered for the evaluating web
based e-Learning portals using the proposed multidimensional model[3] based on [2]. The needed
dimensions and attributes can be added as per the
evaluation or prediction.

Figure 4: Multi Dimensional Metric Model for eLearning Portal

Integrated Intelligent Research (IIR)

456

Volume: 03, Issue: 02, December 2014


Pages: 454-462

International Journal of Data Mining Techniques and Applications


ISSN: 2278-2419

3.1.1. Functionality Measures

Overall User Rating on Relevance

The functionality of the Web based e-Learning


portals can be considered as an entity object in the
metric model, and its expected behavior will be
captured as the requirements or attributes of an
entity object. The following are the measures for the
functionality dimension:

Overall Expert Rating on Relevance

Module-wise Relevance rating by user

Module-wise Relevance rating by expert

Overall Functionality Rating

Requirement Verified

Requirement Validated

Requirement Severity

In context to the e-Learning Interaction measures ,


the Interaction component specifies the different
type of methodology, various links and
resources.The following are some of the Interaction
measures of the Web based e-Learning portal
components and their contents:

Tacit Category

Explicit Category

Innovative Category

3.1.2

Usability Measures

The knowledge component should be easily


understandable, learnable, and applicable. Usability
attributes are the features and characteristics of the
software/product/sites
that
influence
the
effectiveness, efficiency and satisfaction, with
which users can achieve specified goals. The
usability entity can have the following attributes:

Overall Usability Rating

Rating on Operability

Rating on Communicativeness

Rating on Accessibility

User Rating on UI

Expert Rating on UI

3.1.3

Availability Measures

In the context of the Web based e-Learning portals,


Knowledge Availability is whether (or how often) a
given knowledge asset is available for use by its
intended users. The following are some of the key
attributes for measuring the Availability of the
knowledge asset:

Overall Content Rating

Overall Structure Rating

Module wise content rating

Module wise structure rating

Availability of Portal

3.1.4

Relevance Measures

The knowledge component should state the quickest


solution with the least resource requirements. The
following are some measures which describe the
relevance of the Web based e-Learning portal
components and their contents:

Integrated Intelligent Research (IIR)

3.1.5

Interaction Measures

Rating on methodology
Rating on Links and Resources
Rating on Events
Rating on Feedback and Reviews
3.1.6 Application of WAM
The weighted mean is similar to an arithmetic
mean (the most common type of average); where
instead of each of the data points contributing
equally to the final average, some data points
contribute more than others. The weights can be
specified for the measures or metrics collected,
based on the user or implementer or evaluation
needs. For example, training organizations gives
higher weightage to the quality of the training
material, certifications obtained by the participants
and also the employability of the participants after
completing the training, which indicated its
effectiveness. In higher learning institutions like
universities and engineering colleges, the relevance
of the knowledge asset based on the syllabus or
curriculum gets more weight as it reflects the
standard. Additional weights can be given to the
academic institutions, if the knowledge asset on a
specific subject encourages students to do projects
or submit research papers or obtain higher scores in
the exams in the subjects taught and presented in
the knowledge portal or repository. The web based
e-Learning measures can be weighted either
equally or non-equally, based on the evaluation or
ranking criteria; in this case, we considered four
different aspects of the knowledge sharing, and
assigned equal weights as the measures are equally
important to provide reasonable ranking. The noncritical or supportive measures which indirectly
contribute towards web based e-Learning
measurement will be considered as non-weighted
measures for our evaluation. The 90:10 formulas
are adapted for our ranking and rating using the
weighted average mean; in these formulas, 90
indicates 90% of the allocation for critical web
based e-Learning measures and 10 indicates 10%
of the allocation for non-weighted measures such
as management, supporting infrastructure and
participants subject knowledge.

457

Volume: 03, Issue: 02, December 2014


Pages: 454-462
4

International Journal of Data Mining Techniques and Applications


ISSN: 2278-2419

THE EXPERIMENT WEB BASED


ELEARNING PORTAL ANALYSIS

The participants were selected from multiple


departments of multiple organisations, with
moderate and frequent usage of eLearning portals
and knowledge repositories. Initially 50 candidates
were selected, but only 30 candidates, with similar
profiles, were actually used in the experiment.
Prior to conducting the actual experiment, the pilot
tests were conducted to validate the approaches and
the tasks involved.
The main aspects of the normal user profiles of the
participants were similar in the following ways:

Computing knowledge and knowledge of using


collaborative tools
such as corporate or
organizatione-Learning or knowledge systems

>= 22 years of age and < 27 years of age, with


English as their learning language for all the
subjects like Commerce, Computer Science,
etc.

The main aspects of the expert user profiles of the


participants were similar in the following ways:

Teaching or Training skills and Expert


knowledge in the subject area

Willingness to review and provide ranking of


the knowledge asset in a constructive way

<= 69 years of age and > 27 years of age with


apt qualification experience in the relevant area

For this evaluation work, we have restricted to five


important dimensions with the distribution as listed
below:

10% for the Functionality

10% for the Usability

30% for the Availability

20% for the Relevance

20% for the Interaction

10%
for
overhead
infrastructure.

rg

yaopthamology
e-Learning portal

E_L
p_3

http://www.sei.cmu.ed
u/training/elearning

Software
engineering
institute

E_L
p_4

http://ifrs.icai.org

Financial, cost
and management
accounting
eLearning portal

E_L
p_5

http://www.ilearnsmart
.com/Academic

learning content
for K-12 and
higher education
students, and
professionals

E_L
p_6

http://aditya.edu.in

Aditya
College(learning
beyond campus)

E_L
p_7

http://www.dbuglobal.
com

Donbosco
university eLearning portal

E_L
p_8

http://elearning.naarm.
ernet.in

National
academy of
agriculture
research
management eLearning portal

E_L
p_9

https://mybanklearning
.sbi.co.in/xsl-portal

State Bank of
India e-Learning
portal

The Table-2 for the functionality dimension shows


how the evaluation percentage (10%) is distributed
among multiple functionality measures.
TABLE 2: WEIGHTAGE TABLE FOR THE
FUNCTIONALITY DIMENSION

for

supporting

TABLE 1. SHOWS THE LIST OF SELECTED


PORTALS FOR THE EVALUATION
PURPOSE
Portal

p_2

eLear
ning
Port
al
No

e-Learning
link

e-Learning
Portal type

E_L
p_1

http://www.ilearnsmart
.com

School based eLearning portal

E_L

http://www.ekalavya.o

SankaraNethrala

Integrated Intelligent Research (IIR)

e-Learning
Functionality
Measure/Metric

Wei
ght
(10
%)

Capture
d
Rating(f
rom
Metric
DB)

Weight
ed
Calcula
tion

F_M1
OverallFunctionalit
yRating

20%

3.5

0.7

F_M2
RequirementVerifie
d

10%

3.2

0.32

F_M3Requirement
Validated

10%

3.6

0.36

10%

2.1

0.21

F_M4
RequirementSeverit

458

Volume: 03, Issue: 02, December 2014


Pages: 454-462

International Journal of Data Mining Techniques and Applications


ISSN: 2278-2419
TABLE 4. WEIGHTAGE TABLE FOR THE
AVAILABILITY DIMENSION

y
F_M5
TacitCategory

10%

4.1

0.41

F_M6
ExplicitCategory

10%

2.4

0.24

F_M7
InnovativeCategory

30%

3.1

0.93

100
%

Total
Score

3.17

e-Learning Dimension Score

0.371

In the Table-2, the third column contains the


captured rating, which contains aggregated value
that stored in the metric database, based on the
system, the user and the expert feed. Similarly, the
other weightage tables are populated for the
Usability, Availability, Relevance and Interaction
Dimensions. The aggregated value for every
measure is captured manually as well as
automatically from the metric database. During the
overall result calculation, the values yielding a
positive contribution are added, and the negative
contribution such as NegativeCommentsCount
found in the TABLE 4 for the Availability measure
is subtracted from the score.

e-Learning
Availability
Measure/Metr
ic

Wei
ght
10%
)

U_M1
OverallUsability_Ratin
g

Capture
d
Rating(
from
Metric
DB)

Weight
ed
Calcul
ation

3.8

0.76

20%

(30%)

Captured
Rating(fro
m Metric
DB)

Weighted
Calculatio
n

A_M1
Content
Rating

30%

3.2

0.96

A_M2
Structure
Rating on
Operability

30%

3.9

1.17

A_M3
Content
Rating

20%

3.2

0.64

A_M4 Rating
on Strategy

10%

4.2

0.42

A_M5
Availability
Of Portal

10%

1.0

0.1

100%

Total
Score

3.29

eLearing Dimension Score

0.987

TABLE 3: WEIGHTAGE TABLE FOR THE USABLITY


DIMENSION

e-Learning Usability
Measure/Metric

Weigh
t

TABLE

5. WEIGHTAGE TABLE FOR INTERACTION


DIMENSION

e-Learning
Efficiency
Measure/Metri
c

Weigh
t
(20%)

Capture
d Rating

I_M1 Rating on
methodology

20%

3.9

0.78

20%

3.5

0.7

(from
Metric
DB)

Weighted
Calculatio
n

U_M2
RatingOnOperability

20%

0.8

U_M3RatingOnComm
unicativeness

10%

2.9

0.29

I_M2 Rating on
Links
and
Resources

0.7

I_M3 Rating on
Events

30%

4.1

1.23

I_M4 Rating on
Feedback and
Reviews

30%

3.6

1.08

100%

Total
Score

3.79

U_M4
RatingOnAccessibility

20%

3.5

U_M5
UserRatingOnUI

20%

0.8

U_M6
ExpertRatingOnUI

10%

3.6

0.36

100
%

Total
Score

3.71

e-Learning Dimension Score

Integrated Intelligent Research (IIR)

e-Learning Dimension Score

0.758

0.37

459

Volume: 03, Issue: 02, December 2014


Pages: 454-462
TABLE

6.

WEIGHTAGE TABLE FOR

e-Learning
Efficiency
Measure/Metri
c

R_M1 Overall
User Rating on
Relevance
R_M2 Overall
Expert Rating
on Relevance
R_M3 Modulewise relevance
rating by user
R_M4 Modulewise relevance
rating by expert

Weigh
t
(10%)

Capture
d Rating
(from
Metric
DB)

International Journal of Data Mining Techniques and Applications


ISSN: 2278-2419

RELEVANCE
Weighted
Calculatio
n

Total Non Weight Value


Average

2.2

10 % of Non Weighted
Dimension Group Score

3.9

90%

0.78

10%
20%

3.5

0.22

TABLE 7. OVERALL EFFECTIVENESS

Allocation
20%

11.0

0.7

Type

Derived
Score

Weighted Dimension
Group

2.866

Non Weighted
Dimension Group

0.22

Overall KM System Score


3.086
30%

4.1

1.23

TABLE 8. RANKING AND RATING TABLE

Rank
30%

3.6

1.08

100%

Total
Score

3.79

Category

Rating

Outstanding

Extremely
Effective

Effective

DIMENSION

Below Effective

As mentioned in the earlier sections, for evaluation


purposes, we have also considered non-weighted
measures and added 10% to our overall calculation.
We have taken the feedback on the required
parameters for the non-weighted measures and
added to the metric database and populated in
Table 6. The Table 7 shows the overall
effectiveness summary which includes both
weighted dimension group and non-weighted
dimension group. The captured ratings are
aggregated values, which are stored in the database
through system feed, user and expert feed.

Not Effective

e-Learning Dimension Score

0.379

TABLE 6. NON WEIGHTED MEASURES


e-Learning Non Weighted
Measure/Metric (10%)

Captured
Rating(from Metric
DB)

NW_M1 Supporting eLearning Infrastructure

3.0

NW_M2 Management
Support

2.0

NW_M3 Condusive
Environment

1.0

NW_M4 Particpants
Subject or Domain
Knowledge

2.0

NW_M5Participants Thrust
for Knowledge Collabration

3.0

Integrated Intelligent Research (IIR)

TABLE 9. RANKING AND RATING TABLE

eLea
rnin
g
Por
tal
No

e-Learning Portal
link

e-Learning
Portal type

eLea
rnin
g
rate
d
sco
re

E_
Lp_
1

http://www.ilearns
mart.com

School based
e-Learning
portal

3.0
86

E_
Lp_
2

http://www.ekalav
ya.org

SankaraNethr
alayaopthamol
ogy

2.9
6

e-Learning
portal
E_
Lp_
3

http://www.sei.cm
u.edu/training/elea
rning

Software
engineering
institute

3.3
85

E_
Lp_
4

http://ifrs.icai.org

Financial, cost
and
management
accounting eLearning

3.5
67

460

Volume: 03, Issue: 02, December 2014


Pages: 454-462

International Journal of Data Mining Techniques and Applications


ISSN: 2278-2419

portal
E_
Lp_
5

http://www.ilearns
mart.com/Academi
c

learning
content for K12 and higher
education
students, and
professionals

E_Lp_1
E_Lp_3
E_Lp_5
E_Lp_7
E_Lp_9

5
4
3
Rank
2
1
0

3.6
56

e-Learning
rated
score

e-Learning portals
Figure 5. shows the graph which demonstrates the
ranking of web based e-Learning portal based on
table 9
The Table 7 contains the summary values for both
weighted and non-weighted scores for the first
sample presented in Table 1.. The weighted
dimension group score is 2.866 which is derived by
adding all the five quality dimension scores and the
non-weighted dimension group was given 0.22 and
both the derived scores were added to make up the
overall web based e-Learning portal Effectiveness
Score of 3.086. The portal which was evaluated by
the users and experts with the score of 3.086 and
hence it is considered to be effective. The
dataobtainedforthisexperimentconcerned with the
effectiveness of the web based e-Learning portal is
presented in Table 9. for different organizations.
From the graph fig 5, it is very clear that all the
considered samples are ranked and rated as either
effective or below effective.
5. CONCLUSION
By referring to table 7 and the guideline table 8 for
ranking and rating, Table 9 is generated based on
the calculation measures provided in the Table
2,3,4,5,6, it is clear that the evaluated web based eLearning portal is effective as the overall evaluation
rating is 3.086 for the first sample. The same
procedure is followed for the other web based eLearning portals and the results are presented in
Table 9.In this research work, we have attempted to
use the metric database and a proven statistical
technique, the weighted average mean to validate
the effectiveness of the e-Learning process and the
portal using ranking and rating. This proves that the
combination of the metric database with a statistical
technique such as the WAM could be useful to
predict the usefulness and effectiveness of the e-

Integrated Intelligent Research (IIR)

Learning portals. For our experiment, we have


taken only a five dimensional metric model and
database, to validate the effectiveness which may
not be adequate enough to measure the overall
effectiveness and performance of the web based eLearning portal considering the nature of web
especially in the cloud. so there are multiple
research avenues to enhance the dimensional model
as well as the structure of the metric databases, to
use multi-dimensional data cubes instead of tables
to gather additional quality factors and measures for
measuring the effectiveness of e-Learning portals
and its process. in order to compare the proposed
ranking and rating methodology, appropriate
hypothesis can be set to validate the significance of
the results obtained from the metric database. In this
paper, we attempt to develop a measureable system
to analyze and evaluate how user is accessing the
materials provided in e-Learning environment.
further research works can be conducted towards
identification of pattern of search in the e-Learning
portals with a index structure and to provide
individual-learning and evaluation approach unique
to user or to a group of people (e.g. regional). this
will yield to a better web based e-Learning system
to facilitate the best ways of learning or displayed
paths of accessing to another related group of users.
REFERENCES
DayanandanVenkata Subramanian, Angelina
Geetha (2011), Guidelines and Effectiveness of
Using Social Media Tools For Knowledge Sharing
Communities, National Conference on Knowledge
Intelligence and Telematics, Gujarat, India
[1]

Venkata
S
Dayanandan,
Angelina
Geetha(2011), Adaptation of Goal Question Metric
Technique For Evaluation of Knowledge
Management Systems, Review of Knowledge
Management Journal, Volume 1, Jan-June 2011,
ISSN:2231-5845
[2]

Venkata S Dayanandan, Angelina Geeteha,


Mohammed Hussain(2011), Measurement Process
and Multi-dimensional Model For Evaluating
Knowledge Management Systems, International
Conference on Research and Innovation in
Information
Systems,
International Islamic
University,
Malaysia
(IIUM)
and
UniversitiTeknologi Malaysia(UTM), Indexed by
IEEE & SCOPUS, November 2011
[3]

Diwakar Krishnamurthy, Jerry Rolia, and Min


Xu1(2011), WAM The Weighted Average
Method for Predicting the Performance of Systems
with Bursts of Customer Sessions, University of
Calgary,
Calgary,
AB,
Canada,
IEEE
TRANSACTIONS
ON
SOFTWARE
ENGINEERING, 0098-5589/11
[4]

NittayaKerdprasop, and KittisakKerdprasop,


World Academy of Science Engineering and
[5]

461

Volume: 03, Issue: 02, December 2014


Pages: 454-462

International Journal of Data Mining Techniques and Applications


ISSN: 2278-2419

Technology 39 2008 Knowledge Mining in Webbased Learning Environments


S. George and H. Labas, E-Learning standards
as a basis for contextual forums design, Computers
in Human Behavior, 24, pp. 138-152, 2008.
[6]

S. George and H. Labas, E-Learning standards


as a basis for contextual forums design, Computers
in Human Behavior, 24, pp. 138-152, 2008.
[7]

B. Chapman and B. Hall, Learning Content


Management System. Brandonhall.com, New York,
2005.
[8]

L. Davis, R.F. Gamble, and S. Kimsen, A


patterned approach for linking knowledge-based
systems to external resources, IEEE Transactions
on Systems, Man and Cybernetics, Part B, 34(1),
pp. 222-233, 2004.
B. Martens and W. Jabi, Knowledge Portal as
a new paradigm for scientific publishing and
collaboration, IT conference, 2004
[9]

A.C.M. Fong, S.C. Hui, and C.T. Lau, On-demand


learning for a wireless campus, IEEE Multimedia,
11(4), pp. 50-60, 2004.
J. Ismail, The design of an e-Learning system
beyond the hype, The Internet and Higher
Education, 4, pp. 329-336, 2002.
[10]

C.P. Ruppel and S.J. Harrington, Sharing


knowledge through intranets: A study of
organizational culture and intranet implementation,
IEEE Transactions on Professional Communication,
44(1), pp. 37-51, 2001.
[11]

A.E. Saddik, S. Fischer, and R. Steinmetz,


Reusable multimedia content in Web based
learning systems, IEEE Multimedia, 8(3), pp. 3038, 2001.
[12]

A. Satyadas, U. Harigopal, and N.P. Cassaigne,


Knowledge management tutorial: An editorial
overview, IEEE Transactions on ystems, Man and
Cybernetics, Part C, 31(4), pp. 429-437, 2001.
[13]

O. Gunther, R. Muller, P. Schmidt, H.K.


Bhargava, and R. Krishnan, MMM: A web-based
system for sharing statistical computing modules,
IEEE Internet Computing, 1(3), pp. 59-68, 1997.
[14]

Nielsen, J. and R. Molich (1990), Heuristic


Evaluation of User Interfaces, New York, NY:
ACM Press
[15]

Integrated Intelligent Research (IIR)

462

You might also like