Indonesi
an
Journa
l
of El
ect
ri
cal Engineer
ing
an
d
Comp
ut
er
Scie
nce
Vo
l.
13
,
No.
1
,
Jan
uar
y
201
9
,
pp.
15
~
21
IS
S
N: 25
02
-
4752, DO
I: 10
.11
591/ijeecs
.v1
3
.i
1
.pp
15
-
21
15
Journ
al h
om
e
page
:
http:
//
ia
es
core.c
om/j
ourn
als/i
ndex.
ph
p/ij
eecs
The patt
er
ns
of accessin
g learnin
g mana
gement s
ystem
amon
g stud
ents
Ak
ibu
Mahm
ou
d
Abdull
ah
i, M
ok
h
airi M
ak
h
ta
r
, Suh
ailan Sa
fie
Facul
t
y
of
Infor
m
at
ic
s a
nd
Com
puti
ng,
Univer
sit
i
Sulta
n
Z
ai
n
al
Abidin,
Te
r
engg
anu,
Ma
lay
si
a
Art
ic
le
In
f
o
ABSTR
A
CT
Art
ic
le
history:
Re
cei
ved
Sep
1
8
, 201
8
Re
vised N
ov 19
, 2
018
Accepte
d
Nov
3
0
, 201
8
Le
arn
ing
Mana
g
ement
S
y
st
em
(
LMS)
is
an
on
line
software
th
at
was
hosted
on
a
serve
r
and
designe
d
spec
if
i
ca
l
l
y
to
m
ana
g
e
le
arn
ers’
informati
on
,
cour
se
reg
istration,
l
ea
r
ning
cont
ent,
an
d
assessment
tool
.
Educat
ion
al
dat
a
m
ini
ng
is
a
wa
y
of
eva
l
uat
ing
and
using
m
et
hods
for
exam
ini
ng
the
uniq
ue
and
l
arg
e
dat
ase
t
tha
t
co
m
e
from
educ
at
iona
l
fi
el
d
,
and
apply
ing
those
in
orde
r
to
under
stand
how
student
s
l
ea
rn
and
the
settings
in
which
they
le
arn
.
M
a
n
y
student
s
use
to
m
iss
so
m
e
of
th
e
a
ct
iv
it
i
es
poste
d
b
y
th
ei
r
instru
ct
ors,
du
e
to
the
short
de
adl
i
ne,
and
they
are
not
acce
ss
ing
t
he
LMS
reg
ula
r
l
y
or
e
v
e
r
y
da
y
.
Th
e
purpose
of
thi
s
pape
r
i
s
to
expl
ore
th
e
wa
y
on
how
student
acce
s
s
LMS
and
which
da
y
is
th
e
m
ost
fre
quent
a
ccess
ed.
Th
e
findi
ngs
show
tha
t,
the
tot
a
l
num
ber
of
ac
ce
ss
ing
LMS
among
33
student
s
is
160
60,
and
the
m
ea
n
is
486.
67
,
S16
rec
orde
d
the
highe
st
num
ber
of
acce
ss
ing
th
e
LMS
(965
ac
c
ess),
while
S
24
as
the
l
ea
st
n
um
ber
of
ac
c
ess
(275).
And
the
cor
relati
o
n
bet
wee
n
Tu
esda
y
s
is
signifi
c
ant
,
positi
v
e
a
nd
strong
cor
rel
a
ti
on
with
W
edne
sda
y
s
(0
.
546),
and
posi
ti
ve
,
but
wea
k
with
Thursda
y
s
(0.
292),
Frida
y
s
(0.
244)
,
Saturday
s
(0
.
334
),
and
Sunda
y
s (
0.
291).
Ke
yw
or
ds:
Data m
ining
Ed
ucati
on
al
da
ta
m
ining
Learn
i
ng
m
anag
em
ent
syst
e
m
(LMS)
Copyright
©
201
9
Instit
ut
e
o
f Ad
vanc
ed
Engi
n
ee
r
ing
and
S
cienc
e
.
Al
l
rights re
serv
ed.
Corres
pond
in
g
Aut
h
or
:
Ak
i
bu Mahm
ou
d A
bdullahi
,
Faculty
of In
form
atics and
C
om
pu
ti
ng
,
Un
i
ver
sit
i S
ultan Zai
nal Abid
in,
Tereng
ganu,
Ma
la
ysi
a.
Em
a
il
:
akibu
19
89@
ho
tm
ai
l.c
om
1.
INTROD
U
CTION
Learn
i
ng
Ma
na
gem
ent
Syst
e
m
,
wh
ic
h
was
fam
ou
sly
known
as
LM
S
is
an
onli
ne
s
of
t
war
e
platfo
rm
that
was
creat
ed
f
or
the
purpose
of
distri
bu
ti
ng
of
in
form
ation
an
d
c
omm
un
ic
at
ion
betwee
n
le
ar
ner
s
,
instru
ct
or
s
,
a
nd
a
dm
inist
rator
s.
LM
S
has
beco
m
e
the
m
os
t
sta
lwa
rt
pl
at
fo
rm
for
m
a
nag
i
ng
an
e
-
le
arn
i
ng
env
i
ronm
ent
[1
]
.
Un
i
ver
sit
ie
san
d
insti
tuti
on
s
are
us
i
ng
L
MS
to
prop
up
te
aching
,
le
ar
ning,
an
d
sup
pl
e
m
ent
tradit
ion
al
te
a
chin
g
(
face
-
to
-
face
)
dist
rib
ut
ion
wh
e
re
in
structo
rs
a
re
able
to
s
ha
re
m
a
te
rial
s
thr
ough
internet
[
2].
L
earn
i
ng
Ma
nage
m
ent
Syst
e
m
is
an
on
li
ne
s
oft
war
e
t
hat
wa
s
ho
ste
d
on
a
serv
e
r
an
d
de
s
ign
e
d
sp
eci
fical
ly
to
m
anag
e
le
ar
ne
rs’
i
nfor
m
at
ion,
co
urse
re
gistr
at
ion
,
le
a
rn
i
ng
co
ntent,
a
nd
a
ssessm
ent
too
l
[3
]
.
LMS
al
so
al
lows
an
inte
racti
on
betwee
n
stud
e
nt
-
to
-
s
t
ud
e
nt,
stu
den
t
-
to
-
t
eachers
,
stu
de
nt
-
to
-
co
ntent
,
te
acher
-
to
-
te
ache
r,
te
a
cher
-
to
-
stu
den
t
,
te
acher
-
to
-
co
ntent,
a
nd
c
onte
nt
-
to
-
c
onte
nt,
con
te
nt
-
to
-
stu
den
t
a
nd
c
on
te
nt
-
to
-
te
acher
[
4].
LMS
was
par
ti
c
ularly
dev
el
oped
f
or
co
ntr
olli
ng
co
urses
th
at
are
of
fe
red
on
li
ne
,
transm
it
ti
ng
m
at
erial
s
as
well
as
per
m
i
tt
ing
colla
bo
rati
on
and
c
omm
un
ic
at
ion
bet
wee
n
le
arn
er
s
an
d
i
ns
tr
ucto
rs
.
LM
S
is
a
too
l t
hat
offe
rs a si
te
to
te
ach
and lea
r
n wit
hout
rely
ing o
n
t
he
ti
m
e zon
e a
nd bo
unda
ries
[5
-
6].
Data
Mi
ning
is
the
cl
ipp
i
ng
of
i
nfor
m
at
ion
from
a
gar
ga
nt
uan
m
assive
of
data.
Data
m
ining
is
t
he
stud
y
of
colle
ct
ing
,
cl
eani
ng,
processi
ng,
analy
sing
a
nd
find
i
ng
us
e
ful
inform
ation
from
the
data
[7
-
8].
Data
Mi
ning
i
s
def
i
ne
d
as
a
way
of
s
olv
in
g
pr
ob
le
m
s
by
analy
sing
the
data
that
are
al
read
y
dis
pla
ye
d
in
dataset
s.
A
nd
i
t
was
al
so
de
fined
a
s
the
way
of
fin
ding
ou
t
us
ef
ul
patte
r
ns
in
data
[9
]
.
Da
ta
Mi
nin
g
is
a
n
area
of
bri
ng
to
li
gh
t
c
urre
nt,
va
li
d,
intere
sti
ng
a
nd
util
it
arian
in
f
or
m
at
ion
from
hu
ge
a
m
ou
nt
of
da
ta
set
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N
:
2502
-
4752
Ind
on
esi
a
n
J
E
le
c Eng &
Co
m
p
Sci,
Vo
l.
13
, N
o.
1
,
Ja
nu
a
ry 20
19
:
15
–
21
16
Diff
e
re
nt
fiel
ds
are
ap
plyi
ng
data
m
ining
includi
ng
governm
ent,
bankin
g,
cy
be
rsec
ur
it
y,
entertai
nm
ent,
fina
nce, h
os
pit
al
, enginee
rin
g, bi
om
edici
ne,
edu
cat
io
n et
c. [10
-
11
]
.
Data
Mi
nin
g
m
et
ho
ds
that
are
ap
plyi
ng
in
the
fiel
d
of
edu
cat
io
n
t
o
di
scov
e
r
ed
ucat
ion
al
data
is
cal
le
d
Ed
ucati
on
al
Data
Mi
nin
g
(E
DM)
wh
i
ch
in
vo
l
ved
wi
th
est
ablishin
g,
researc
hing
a
nd
us
i
ng
data
m
inin
g
te
chn
iq
ues
t
o
disco
ver
patte
r
ns
in
vast
acc
um
ula
ti
on
s
of
e
du
cat
io
nal
data
that
w
ou
l
d
be
dif
ficult
to
a
naly
se
because
of
the
i
m
m
ense
la
rge
of
data
that
exist
in.
Ed
uc
at
ion
al
data
m
ining
was
al
so
def
ine
d
as
a
way
of
evaluati
ng
a
nd
us
in
g
m
et
ho
ds
f
or
e
xam
ining
the
uniq
ue
a
nd
la
r
ge
da
ta
set
that
com
e
from
edu
cat
ion
a
l
fiel
d,
and
a
pply
ing
t
ho
s
e
in
orde
r
to
unde
rstan
d
how
stu
de
nts
l
earn
a
nd
t
he
s
et
ti
ng
s
in
w
hi
ch
they
le
arn
[12].
Data
m
ining
m
et
ho
ds
in
ed
ucati
on
al
set
ti
ng
s
s
hows
the
way
to
new
awar
e
ness
on
le
arn
er
’s
inter
act
ion,
com
m
un
ic
at
ion
,
be
hav
i
our
a
nd
le
ar
ning
paths,
an
d
al
s
o
t
o
reh
a
bili
ta
te
te
achin
g
a
nd
le
ar
ning
[13].
E
D
M
is
t
he
com
bin
at
ion
of thr
ee
m
ai
n
fiel
ds
: c
om
pu
te
r
s
ci
ence,
sta
ti
sti
cs an
d
e
ducat
io
n.
Un
i
ver
sit
ie
s
an
d
colle
ges
are
strugglin
g
a
nd
sift
thr
ough
a
way
that
they
will
us
e
in
ord
er
to
at
tract
and
m
ake
their
stu
de
nts
to
be
m
or
e
en
gage
d,
c
ollab
or
at
e
d,
com
m
un
ic
at
ed
a
nd
a
pp
li
ed
their
unde
rstan
ding.
Nowa
days,
m
os
t
of
c
olleges
and
unive
rsiti
es
are
tra
ns
f
orm
ing
ed
ucati
on
f
ro
m
face
-
to
-
face
to
a
n
on
l
ine
an
d
so
m
e
to
blend
e
d
le
arn
i
ng,
wh
i
ch
is
the
m
erg
ing
of
both
face
-
to
-
face
an
d
on
li
ne
te
aching.
I
t
was
repor
te
d
that
in
20
13
the
re
wer
e
ab
out
7.1
m
il
l
ion
st
ud
e
nt
s
reg
ist
ere
d
i
n
onli
ne
c
ourses
in
higher
ed
uc
at
ion
.
LMS
ha
s
huge
a
m
ou
nt
of
dat
a
relat
ed
to
stud
e
nts’
record
,
prof
il
e,
res
ult,
interact
ion,
a
ct
ivit
ie
s,
and
f
reque
nt
of
acc
essing
LMS usi
ng
bro
wser [
14
-
15
]
.
Du
e
to
the
m
a
ssi
ve
am
ou
nt
of
su
c
h
data,
in
structo
rs
an
d
a
dm
inist
rator
s
wer
e
ye
ar
ning
to
fin
d
ou
t
a
way
on
how
to
i
m
pr
ove
te
ach
ing
a
nd
le
arn
i
ng.
“T
he
re
we
re
no
sto
rag
e
te
c
hn
i
qu
e
s
that
e
nab
le
t
he
anal
yt
ic
al
stud
y
of
the
inf
or
m
at
ion
pr
ese
nt
in
the
Lear
ni
ng
Ma
na
gem
e
nt
Syst
e
m
”
(G
arcia
&
Secade
s,
2013;
p.
313),
but
there
a
re s
o
m
a
ny
w
ay
s
a
nd
m
et
hods
t
hat
a
na
ly
sts
m
ay
us
e
to r
evie
w
a
bout
this data. Edu
cat
ion
al
d
at
a
m
inin
g
is
the
way
wh
ic
h
will
help
to
m
easur
e
and
a
naly
se
su
ch
huge
data,
it
beco
m
es
a
m
irro
r
for
instr
ucto
rs
to
se
e
thr
ough
the
m
ov
em
ent
of
the
stud
e
nts
an
d
their
act
ivit
ie
s.
But
ta
king
an
act
ion
to
s
olv
e
the
pro
blem
t
hat
w
a
s
encou
ntere
d
is
in
the
ha
nd
of
i
ns
tr
ucto
rs
[16].
The
obj
ect
ive
s
of
t
he
researc
h
a
re
t
o:
i
)
.
T
o
stud
y
t
he
patte
rs
of
acce
ssing
Lear
ning
Ma
na
ge
m
ent
S
yst
e
m
.
i
i
)
.
To
e
xplore
the
best
day
of
acce
s
sin
g
L
earn
i
ng
Ma
na
gem
ent
Syst
e
m
.
i
ii
)
.
A
nd
T
o
disco
ve
r
the
relat
io
nship
betwe
en
th
e
days
base
d
on
acce
ssi
ng
Le
arn
i
ng
Ma
na
ge
m
ent
Syst
e
m
a
m
on
g st
udents.
2.
LE
ARNING
MAN
AGE
M
ENT S
YS
TE
M (LMS
)
PL
ATFO
RMS
Kasim
and
K
ha
li
d
(
2016)
dis
cusse
d
a
nd
co
m
par
ed
bet
we
en
s
om
e
avail
able
platf
or
m
s
of
LMS
i
n
their
researc
h,
and
cat
eg
or
iz
e
d
the
se
platfo
r
m
s
into
two
ty
pes
w
hich
a
re;
(i)
ope
n
s
ourc
e
in
w
hich
t
he
cod
e
s
are
f
ree
t
o
us
e,
(ii)
c
omm
ercia
l
wh
ic
h
the
c
od
e
s
are
not
free
.
T
her
e
a
re
m
any
op
e
n
sources
LSM
pla
tfor
m
s
wh
ic
h
are
a
va
il
able
to
us
e
f
or
f
ree,
am
ong
these
op
e
n
s
ources
are
M
oodle
[
17]
,
Atut
or
[
18]
,
Sakai
[19],
School
og
y
[20]
and
Edm
od
o
[21
-
22]
.
Me
anwhil
e,
the
com
m
ercia
l
LMS
platfo
rm
s
include
Lit
Mos
,
Bl
ackboar
d,
S
uccessFact
or
s
, S
um
Total
, An
gel Lear
ni
ng, e
tc
.
3.
EDU
CA
TI
ONAL D
AT
A MI
NING TO
OL
S
Ed
ucati
on
al
da
ta
m
ining
too
l
s
can
be
div
i
de
d
into
t
wo
c
at
egories,
com
m
ercial
and
open
s
ource
.
Com
m
ercial
L
earn
i
ng
An
al
yt
ic
s too
ls are S
PSS,
Ta
bleau
, NVi
vo, S
ta
ta
, B
la
ckboard,
M
any Eye
s,
I
nfo
chim
ps
,
et
c.
Wh
il
e
O
pe
n
S
ource
e
du
cat
ion
al
data
m
ining
incl
ude
R,
W
e
ka,
S
N
AP
P
,
Netl
yt
ic
,
et
c.
S
om
e
of
the
to
ols
will
b
e
discuss
ed belo
w:
Com
m
ercial
e
du
cat
io
nal
data
m
ining
t
oo
l
s
are
s
oft
war
e
de
velo
ped
by
com
m
ercial
com
pan
ie
s
.
Exam
ples o
f
th
ese soft
wa
re
s a
re:
a)
Tableau:
t
he
i
dea
of
init
ia
ti
ng
Ta
bleau
be
ga
n
betwee
n
1999
an
d
2002
f
ro
m
Dep
a
rtm
e
nt
of
C
om
pu
te
r
Scie
nce
in
Sta
nford
U
niv
e
rsi
ty
.
Tableau
wa
s
founde
d
by
Chris
Stolt
e
in
2003.
Tablea
u
is
an
interact
ive
data
vis
ualiz
at
ion
softwa
re,
t
he
com
pan
y
is
base
d
in
Was
hi
ng
to
n,
U
nited
Stat
e.
T
her
e
a
re
fi
ve
ways
of
acce
ssing Ta
bleau
s
of
t
war
e:
Desk
t
op, Ser
ve
r,
On
li
ne,
Publ
ic
, and
M
ob
il
e
[23].
b)
STA
T
A:
in
1985
a
gr
a
duat
e
fr
om
Un
ive
rsit
y
of
Ca
li
fo
r
nia
W
il
li
a
m
Gould
de
vel
op
e
d
a
sta
ti
stical
so
ft
war
e
cal
le
d
Stat
a.
The
so
ft
war
e
wa
s
wr
it
te
n
in
C
program
m
i
ng
la
ngua
ge,
for
ve
rsion
one,
Gould sp
ent al
m
os
t on
e ye
ar i
n wr
it
in
g
the
c
od
e
s
of
Stat
a [
24
]
.
c)
Bl
ackboar
d:
is
an
analy
ti
cal
so
ft
war
e
that
w
a
s
dev
el
oped
by
blackboa
rd
Learn
i
ng
Ma
na
gem
ent
Syst
e
m
.
This softwa
re
will
captu
re s
t
ud
e
nt d
at
a a
nd
trans
form
i
t i
nt
o
operati
on
al
infor
m
at
ion
. I
t
giv
es
detai
l abo
ut
le
arn
in
g o
utco
m
es, ev
al
uatio
n of t
ools, a
nd
patte
rn of
us
a
ge
[25
]
.
d)
SPSS:
in
1975
Be
nt,
Nie
an
d
H
ull
gr
a
duat
ed
stude
nts
from
Un
iversit
y
of
Stan
for
d
dev
el
op
e
d
S
P
SS
sta
ti
sti
cal
so
ftwar
e
.
S
PSS
sta
nd
f
or
Stat
ist
ic
al
Packa
ge
for
the
S
ocial
S
ci
ences.
In
2009
IBM
ac
quir
ed
SPSS.
The
sta
ti
sti
cs
that
inclu
de
s
in
S
PSS
are
t
-
te
st,
Des
cripti
ve,
C
ro
s
s
ta
bu
la
ti
on
,
A
NOV
A,
Cl
us
te
r
Evaluation Warning : The document was created with Spire.PDF for Python.
Ind
on
esi
a
n
J
E
le
c Eng &
Co
m
p
Sci
IS
S
N:
25
02
-
4752
Th
e
patt
erns of
a
ccess
i
ng lear
ning
man
ag
e
m
ent system
am
ong st
ude
nts
(
Aki
bu
Ma
hmo
ud
Abd
ullah
i
)
17
An
al
ysi
s, Li
ne
ar Reg
ressi
on, M
eans, N
onpa
ram
et
ric te
st etc.
The o
pen sou
r
ce ed
ucati
onal
data m
ining
to
ols ar
e
d
e
velo
pe
d
m
ai
nly fo
r
re
search
and
f
or f
ree
, th
ey
are
no
t
well
d
e
velo
ped com
pa
red to c
omm
er
ci
al
so
ftwa
re.
The o
pen ED
M t
oo
ls a
re
d
is
cusse
d br
ie
fly
belo
w:
a)
SNAPP:
sta
nd
for
S
ocial
Net
works
Ad
a
ptin
g
Pe
da
gogical
Pr
act
ic
e,
is
a
n
op
e
n
s
ource
,
f
r
ee
softwar
e
tha
t
is
us
e
fo
r
data
visu
al
iz
at
ion
and
so
ci
al
ne
twork
analy
si
s
of
disc
us
sio
n
for
um
act
ivit
y
in
Learn
in
g
Ma
nag
em
ent
Syst
e
m
.
It
give
s
inf
or
m
at
ion
about
le
arn
e
r
s’
en
ga
gem
ent
who
pa
rtic
ip
at
ed
in
a
f
orum
discuss
i
on
an
d
interact
ion
be
tween
them
.
SN
A
PP
de
velo
pe
d
by
gro
up
of
researc
he
rs
who
pa
rtic
ipate
d
from
diff
ere
nt
unive
rsiti
es
a
rou
nd
the
w
orl
d,
T
he
Un
i
ve
rsity
of
Q
ue
enslan
d,
Mu
rdoch
U
ni
ver
sit
y
,
Un
i
ver
sit
y o
f Wollo
ngon
g,
RM
IT
U
niv
e
rs
it
y, and
U
niv
e
r
sit
y of
Brit
ish
Colum
bia [
25]
.
b)
Wek
a:
is
an
othe
r
open
s
ource
EDM
to
ol
that
was
de
velo
pe
d
by
New
Z
eal
and’s
Un
i
ver
sit
y
of
W
ai
kato.
I
t
was
w
ritt
en
usi
ng
Ja
va
pro
gra
m
m
ing
la
ngua
ge.
T
he
W
e
ka
includes
to
ol
s
l
ike
cl
assifi
cat
ion
,
cl
us
te
rin
g,
visu
al
iz
at
ion,
da
ta
p
re
-
pr
ocess
ing
,
r
e
gr
e
ssio
n, et
c. [9].
c)
Netl
yt
ic
:
is
a
so
ci
al
netw
ork
so
ft
war
e
t
hat
su
m
m
arizes
huge
am
ou
nt
of
data
from
le
arn
ers
’
interact
i
on,
eng
a
gem
ent in c
hat,
foru
m
d
is
cussion,
twit
te
r
, Yo
utube etc
.
4.
R
ESE
A
R
CH MET
HO
D
In
this stu
dy quan
ti
ta
ti
ve
rese
arch
app
ro
ac
h i
s g
oing to
be use
d
wh
ic
h
“evo
l
ves
the co
ll
ect
ion
of d
at
a
so
t
hat
in
form
at
ion
ca
n
be
qu
a
ntifie
d
an
d
sub
j
ect
ed
t
o
sta
ti
sti
cal
treatm
ent
in
order
to
s
uppo
rt
or
refut
e
al
te
rn
at
e
knowle
dge
cl
aim
s”
(
W
i
ll
iam
s,
2007;
p.
66).
Tw
o
resea
rch
desig
ns
,
desc
riptive
an
d
in
fe
ren
ti
al
sta
ti
sti
cs
will
be
us
e
d.
Desc
riptive
sta
ti
sti
cs
is
use
d
to
i
nvest
igate
the
c
onditi
on,
a
nd
i
ts
curre
nt
sit
ua
ti
on
.
Infer
e
ntial
sta
ti
sti
cs
throu
gh
correla
ti
on
al
is
us
e
d
t
o
fin
d
out
the
re
la
ti
ons
hip
bet
ween
two
or
m
or
e
va
riables
in
the
stu
dy
[
29]
.
I
n
this
stu
dy
,
the
EPD2
12
Pr
od
uct
Desi
gn
&
Dev
el
op
m
ent
is
chosen
.
A
total
of
33
stud
e
nts
reg
ist
eri
ng
i
n
this
co
ur
se
will
be
in
vo
l
ved
as
the
researc
h
s
a
m
ple.
The
se
m
est
er
has
17
weeks
f
or
eac
h
cour
se
to
be
c
om
pleted
.
T
he
co
urse
is
offer
e
d
bo
t
h
on
li
ne
a
nd
offl
ine.
I
n
onli
ne,
the
instr
ucto
r
use
s
Moodle
le
arni
ng
m
anag
em
ent
syst
e
m
to
up
loa
d
the
m
at
erial
s
,
an
d
assi
gn
m
ent,
as
well
as
create
f
orum
s
that
the
stu
de
nt
will
us
e, a
nd
pa
rtic
ipate
. While
in of
fli
ne,
the i
ns
t
ru
ct
or
delivers t
he
le
ct
ur
e to t
he
stu
de
nt f
ace
-
to
-
face in
t
he c
la
ss.
The
st
ud
e
nts
ha
ve
c
om
pu
te
r
s
kill
s.
The
resou
rces
us
e,
a
nd
act
ivit
ie
s
are
ext
racted
f
ro
m
the
uni
ver
sit
y’s
e
-
le
ar
n.
T
he
univer
sit
y
is
us
in
g
Moodle
platfo
r
m
.
The
Moo
dl
e
platfor
m
pr
ovide
d
a
plugin
s
cal
le
d
LOG
S
.
The
Lo
gs
is
pl
ugged
int
o
the
LMS
for
the
pur
po
se
of
recor
ding
the
act
ion
s
or
m
ov
e
m
ents
of
the
stud
e
nts
in
the
LMS
and
to
store
it
.
The
Figur
e
1,
2
a
nd
3
s
ho
w
the
th
ree
pro
cesses t
hat
fo
ll
ow
e
d w
hen col
le
ct
ing
the
d
at
a
.
The
F
i
gure
1
i
s
the
L
ogs
plugins
t
hat
al
lo
ws
in
struct
or
or
a
dm
inist
rator
t
o
c
hoos
e
wh
ic
h
lo
gs
he
wan
ts
t
o
ap
pe
ar
or
do
wn
l
oa
d.
In
t
his
stu
dy
,
the
co
ur
s
e,
al
l
par
ti
ci
pan
ts
,
al
l
days,
al
l
act
ivit
ie
s,
al
l
a
ct
ion
s,
and all
ev
e
nts
are c
ho
se
n.
Ther
e a
re two
t
ypes o
f
le
vels i
n
the all
ev
ents
, (
i) tea
chin
g
le
vel, and
(ii) p
a
rtic
ipati
ng
leve
l as sho
w
n
in
Fig
ure
2.
In
this
stu
dy,
pa
r
ti
ci
pating
is
c
hose
n
to
do
wn
l
oad
the
pa
rtic
ipant/st
ude
nts
a
ct
ivit
ie
s.
Af
te
r
GET
THESE
LO
GS
is
clicked
,
ty
pes
of
file
s
popp
e
d
up,
a
nd
excel
fi
le
is
c
ho
s
en
to
sto
re
the
act
ivit
ie
s
and
the
par
ti
ci
pa
nt lo
gs fil
es.
The
Fig
ur
e
3
is t
he
excel fil
e t
hat ap
pe
ars,
ho
m
e w
as cli
cked
and cli
ck
sav
e as to
save th
e
d
at
a.
Af
te
r
the
data
we
re
e
xtracted
into
e
xcel,
Ta
bleau
s
of
t
war
e
is
us
e
d
to
se
par
at
e
t
he
le
vels
as
s
how
n
in
F
ig
ur
e
2
wh
ic
h
are
Tim
e,
us
er
f
ull
nam
e,
effe
ct
ed
us
er
,
e
ve
nt
co
nte
xt,
c
om
po
nen
t,
eve
nt
nam
e,
descr
i
ption,
or
i
gin
,
a
nd
I
P
address
.
Figure
1. Mo
odle
lo
gs
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N
:
2502
-
4752
Ind
on
esi
a
n
J
E
le
c Eng &
Co
m
p
Sci,
Vo
l.
13
, N
o.
1
,
Ja
nu
a
ry 20
19
:
15
–
21
18
Figure
2. Mo
odle
lo
gs
(p
a
rtic
ipati
ng
)
Figure
3. Mi
cr
os
oft
e
xcel scr
een
5.
RESU
LT
A
N
D ANALY
SIS
In
this
r
esearc
h
three
obj
ect
i
ves
are
to
be
di
scusse
d,
the
fi
rst
obj
ect
ives
a
re:
To
stu
dy
th
e
pa
tt
ers
of
accessin
g
Lear
ning
M
anage
m
ent
Sy
ste
m
.
Th
e
pa
rtic
ipants
are
33
stu
den
ts
from
Faculty
of
En
gin
ee
rin
g
w
ho
reg
ist
ere
d
in
t
he
sub
j
ect
Pr
oduct
Desi
gn
&
De
velo
pm
e
nt.
T
he
Stu
de
nts
sta
rted
ac
cessi
ng
t
he
L
earn
i
ng
Ma
nag
em
ent
Syst
e
m
on
14
Februa
ry
to
11
J
un
e
20
17,
wh
ic
h
is
a
rou
nd
4
m
on
ths.
The
E
ducat
iona
l
Dat
a
Mi
nin
g
to
ol
th
at
was
us
ed
for
visu
al
iz
ing
th
e
data
is
Ta
ble
au
.
I
n
the
fo
ll
owin
g
F
ig
ur
e
4,
we
can
vis
ualiz
e
the
m
os
t
acce
ss
st
ud
e
nt
an
d
the
lowest
as
well
as
the
aver
a
ge
based
on
acc
essing
LM
S
usi
ng
pack
e
d
bubble
s.
Figure
4
in
dica
te
s
the
patte
rn
s
of
acce
ssin
g
LMS
a
m
on
g
t
he
33
stu
de
nts,
the
total
nu
m
ber
of
acce
s
sin
g
LMS
is
1606
0,
a
nd
the
m
ean
is
486.6
7,
S
16
rec
orde
d
the
hi
ghest
num
ber
of
acce
ssin
g
t
he
LMS
(96
5
ac
cess)
,
wh
il
e S
24 as
th
e lea
st n
um
ber
of access
(27
5).
Figure
4. Patt
ern
s
of
acce
s
sin
g
LMS
The
seco
nd
obj
ect
iv
e
is
to
explore
the
best
day
of
ac
cessi
ng
Le
arnin
g
Ma
nage
men
t
Sy
ste
m
.
The
pur
pose
is
to
disco
ver
da
y
is
the
m
os
t
acce
ssed
day
a
m
on
g
stu
de
nts.
W
e
ca
n
vis
ualiz
e
the
di
ff
e
rence
s
i
n
the foll
owin
g Fi
gure
5 usin
g box
-
an
d
-
w
hiske
r plots,
w
hile i
n
the
Table
1
t
he deta
il
w
as
di
sp
la
ye
d
.
In
the
Ta
ble
1,
T
uesd
ay
is
the
m
os
t
fr
e
qu
ent
acce
ss
by
the
stu
de
nts
w
it
h
454.0
0,
m
e
anwhil
e,
th
e
m
ean
is
306.909
1,
an
d
t
he
le
ast
of
acce
ss
is
227.0
0.
The
t
hir
d
a
nd
la
st
ob
j
ect
ive
is
to
disc
ove
r
the
rel
ation
s
hip
be
tw
een
the
da
ys
base
d
on
accessin
g
Le
arnin
g
Ma
nage
men
t
Syste
m
amo
ng
stu
de
nts
.
T
he
fo
ll
owin
g
Ta
bl
e 2
dis
play
ed
t
he rel
at
ion
s
hip betwee
n
t
he d
ay
s.
Evaluation Warning : The document was created with Spire.PDF for Python.
Ind
on
esi
a
n
J
E
le
c Eng &
Co
m
p
Sci
IS
S
N:
25
02
-
4752
Th
e
patt
erns of
a
ccess
i
ng lear
ning
man
ag
e
m
ent system
am
ong st
ude
nts
(
Aki
bu
Ma
hmo
ud
Abd
ullah
i
)
19
Figure
5. The
m
os
t acc
eses
da
ys am
on
g
stu
den
ts
Table1
. T
he D
ay
s o
f
A
cce
ssing LM
S
N
Mini
m
u
m
Maxi
m
u
m
Mean
Std
.
Dev
iatio
n
Mon
d
ay
33
9
.00
2
1
3
.00
4
9
.93
9
4
4
8
.58
0
4
4
Tues
d
ay
33
2
2
7
.00
4
5
4
.00
3
0
6
.9091
5
0
.56
0
2
1
W
ed
n
esd
ay
33
.00
8
3
.00
2
2
.75
7
6
2
0
.80
2
6
9
Thu
rsd
ay
33
.00
7
5
.00
1
8
.12
1
2
1
7
.44
4
1
2
Friday
33
.00
5
2
.00
1
4
.54
5
5
1
5
.82
9
3
5
Satu
rday
33
.00
7
3
.00
2
0
.24
2
4
2
1
.18
6
7
2
Su
n
d
ay
33
3
.00
1
6
9
.00
5
3
.66
6
7
4
8
.13
0
4
7
Valid
N
(listwise)
33
Table
2.
T
he
Corr
el
at
ion
b
et
w
een
the
D
ay
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N
:
2502
-
4752
Ind
on
esi
a
n
J
E
le
c Eng &
Co
m
p
Sci,
Vo
l.
13
, N
o.
1
,
Ja
nu
a
ry 20
19
:
15
–
21
20
The fin
dings s
how
that t
he
c
orrelat
ion bet
we
en
Mo
nday
s is
sign
ific
a
nt, po
s
it
ive b
ut
weak
correla
ti
on
with
T
ues
days
(0.38
0),
Wednes
days
(
0.2
74),
T
hurs
days
(
0.350
),
F
riday
s
(
0.420),
a
nd
a
sig
nificant
posit
ive
and
st
ron
g
rel
at
ion
with
Sund
ay
s
(0.57
5)
.
The
c
orrelat
ion
betwee
n
T
ues
days
is
a
po
sit
ive
a
nd
s
tro
ng
correla
ti
on
wit
h
We
dn
es
days
(
0.546),
a
nd
po
sit
ive
,
bu
t
weak
wit
h
T
hurs
days
(0.29
2),
F
ridays
(
0.2
44),
Satur
days
(
0.3
34),
a
nd
Sun
da
ys
(0
.
291).
T
he
co
rr
el
at
io
n
betwee
n
W
e
dn
esdays
is
posit
ive
an
d
wea
k
with
Th
ur
s
days
(0.4.3
2),
F
ridays
a
nd
Sat
urdays
(
0.312
),
a
nd
S
undays
(
0.1
51).
The
c
orrelat
io
n
betwee
n
Th
ursdays
is
po
sit
ive
and
str
ong
with
Fr
iday
s
(
0.6
21),
Sat
urda
ys
(0
.
597),
but
weak
with
Su
nday
s
(
0.295
).
The
c
orrelat
ion
bet
ween
Fr
i
da
ys
is
sign
ific
a
nt
b
ut
wea
k
with
Satu
rd
ay
s (
0.3
26)
a
nd
Sun
da
ys
(0
.
245). And
t
he
betwee
n
Sat
urdays is si
gn
ific
ant,
posit
ive w
i
th S
undays
(0.
380).
The
pur
pose
of
this
pap
e
r
is
to
fin
d
out
w
hic
h
day
is
the
m
os
t
an
d
fr
e
que
nt
acce
ssed
by
the
stud
e
nts,
and
we
f
ound
ou
t
t
hat
Tues
da
y
s
is
the
m
os
t
con
ti
nues
da
y
of
acce
s
s,
th
e
33
stu
de
nts
wer
e
rec
orded
that
in
Tues
days
they
acce
ss
the
LM
S
the
m
os
t
com
par
ed
to
the
rem
ai
nin
g
day
s.
Ma
ny
stu
dent
s
us
e
to
m
iss
s
om
e
of
the
act
ivit
ie
s
po
ste
d
by
their
instru
ct
or
s
,
du
e
to
the
dea
dline
is
m
a
y
be
s
hort,
an
d
they
are
not
acce
ssing
t
he
LMS
re
gu
la
rly
or
eve
ry
day.
By
exp
lo
rin
g
t
he
way
stu
dent
acce
ss
LMS
will
help
t
he
i
ns
tr
ucto
rs
to
fi
nd
the
best
day to
pos
t t
heir
act
ivit
ie
s for
stu
den
t i
n o
rd
e
r
to
avoid
m
issi
ng
acti
viti
es b
y st
ud
e
nts.
6.
CONCL
US
I
O
N
Ed
ucati
on
al
D
at
a
Mi
nin
g
(E
DM)
is
a
cl
arifica
ti
on
of
gather
e
d
an
d
pro
du
ce
d
data
ab
ou
t
le
ar
ner
s
i
n
order
to
asses
s,
evaluate
th
ei
r
le
arn
in
g
pro
gr
e
ss,
presa
ge
an
d
pro
gnos
ti
cat
e
their
fu
t
ur
e
pe
rform
ance.
The
pur
pose
of
EDM
is
to
ta
ke
an
act
io
n
after
data
ha
ve
been
c
ollec
te
d,
m
easur
ed
and
a
naly
sed
f
or
th
e
pur
po
se
of
im
pr
ovem
ent
to
produce
a
qu
al
it
at
ive
te
achin
g
and
le
a
rn
i
ng.
“
Ba
sic
al
ly
,
analy
sis
without
act
ion
is
no
t
analy
ti
cs,
or
one
co
uld
even
say
anal
yt
i
cs
witho
ut
act
ion
is
j
us
t
analy
sis”.
Learn
i
ng
a
naly
ti
cs
is
no
t
occurri
ng
on
ly
in
a
s
umm
at
i
ve
ass
essm
ent
sta
ge,
it
is
al
so
ha
pp
e
ning
in
a
f
or
m
at
ive
assessm
ent
w
hich
instru
ct
or
s
m
ay
us
e
to
ov
e
rs
ee
and
detect
t
he
pro
gr
e
ssive
per
f
orm
ance
of
thei
r
le
arn
e
r
s
wh
il
e
the
co
ur
se
or
su
bject
is
ta
kin
g
place.
Th
r
ough
E
DM,
ins
tructo
rs
are
a
bl
e
to
fo
retel
l
and
pr
e
dict
wh
i
ch
stu
den
t
is
f
aci
ng
academ
ic
diff
ic
ulti
es
or
is
on
le
arn
in
g
nee
ds.
Lear
ning
A
na
ly
ti
cs
serv
e
as
a
fu
ndam
ental
fo
r
tra
ns
f
orm
at
ion
that
giv
es
a
quic
k
an
d
ne
w
way
fo
r
uni
ver
sit
ie
s
an
d
colle
ges
to
im
pr
ov
e
their
processes
of
te
achin
g
and lea
r
ning.
ACKN
OWLE
DGE
MENT
This
wor
k
is
pa
rtia
ll
y supported
by RM
IC
U
niSZ
A
(
Grant
R002
3
CR
IM/
2018/0
3).
REFERE
NCE
S
[1]
Sricha
n
y
a
chon,
N.
(2014).
“
EFL
le
arn
ers’
per
c
ept
ions
of
using
LMS”.
Tur
ki
sh
Online
Journal
of
Educ
ati
ona
l
Technol
ogy
,
13
(
4),
30
–
35
.
[2]
Scla
t
er,
N.,
Pea
sgood,
A.,
&
Mulla
n
,
J.
(2016).
“
Le
arn
ing
ana
l
y
t
ic
s
in
highe
r
educ
a
ti
on :
A
re
vie
w
of
UK
an
d
int
ern
at
ion
al
p
ra
ct
i
ce
Full
r
epor
t
”,
(April)
,
40.
Ret
ri
eve
d
from
htt
ps://
ww
w.j
is
c
.
ac.uk/
sit
es/de
f
a
ult
/files/lear
n
ing
-
ana
l
y
t
ic
s
-
in
-
he
-
v
2_0.
pdf
[3]
Kasim
,
N.
N.
M.,
&
Khal
id,
F.
(2016).
“
Choosing
the
right
l
ea
rning
m
ana
g
e
m
ent
s
y
stem
(L
MS
)
for
the
highe
r
educ
a
ti
on
insti
tu
ti
on
c
onte
x
t:
A
s
y
stematic
rev
i
e
w”
.
Inte
rnationa
l
Journal
of
Eme
rging
Technol
o
gie
s
in
Learning
,
11(6),
55
–
61
.
ht
t
ps://
doi.
or
g/10.
3
991/i
jet.
v11
i06.5644
[4]
Adzha
ruddin,
N.
A.,
&
Li
ng,
L
.
H.
(2013).
“
Le
ar
ning
m
ana
gement
s
y
stem
(LMS)
among
unive
rsit
y
stud
ent
s:
Does
It
W
ork
?
”
Inte
r
nati
onal
Journal
of
E
-
Edu
cat
io
n,
E
-
Busine
ss
,
E
-
Manage
ment
and
E
-
Learning
,
3(3)
,
248
–
252
.
htt
ps://
do
i.
org/1
0.
7763/IJEEEE
.
2013.
V3.233
[5]
Epi
gnosis
LLC.
(2014).
“e
-
learni
ng
Co
nce
pts,
Tr
ends,
Applic
a
ti
ons.
Book”
,
5.
Ret
rie
v
ed
from
htt
p://ww
w.t
alen
tl
m
s.c
om
/e
learni
ng/e
l
ea
rning
-
10
1
-
ja
n2014
-
v1.
1
.
pdf
[6]
Sharm
a,
A.,
&
Vatt
a
,
S.
(2013)
.
“
Role
of
Learni
ng
Mana
gement
S
y
stems
in
Edu
ca
t
ion”
.
Inte
rnat
ional
Journal
o
f
Adv
anc
ed Re
sea
rch
in
Comput
er
Scienc
e
and
Sof
tware
Eng
ine
eri
ng
,
3(6)
,
2277
–
1
28.
[7]
Aggarwal
,
C
.
C.
(2015)
.
“
Data
Mini
ng:
The
Textbook”.
Springer
Inte
rnati
onal
Publishi
ng
.
htt
ps://
do
i.
org/1
0.
1007/978
-
3
-
31
9
-
14142
-
8
[8]
Du,
S.
D.
and
X.
(2011). “
Data
Mining
MA
chi
n
e
L
ea
rn
ing
in
C
yber
sec
uri
t
y
”
.
[9]
W
it
te
n,
I
.
H.
,
Frank,
E
.
,
&
Hall,
M.
a.
(2011)
.
“
Data
Mining:
Prac
t
ic
a
l
Mac
h
ine
Le
arn
ing
Tool
s
and
Techni
ques
”
(Google
eBook)
.
Com
ple
m
ent
ar
y
li
t
erature None.
htt
ps://
do
i.
org/0
120884070,
978
0120884070
[10]
Chen,
C.
-
T.,
&
Chang,
K.
-
Y.
(2
017).
“
A
Stud
y
on
the
Rar
e
Fac
t
ors
Expl
ora
t
ion
of
Le
arn
ing
Eff
e
ct
iv
ene
ss
b
y
Us
i
ng
Fuzz
y
Data
Mi
ning”
.
Eurasia
Journal
of
Mat
hemati
cs,
S
cien
ce
and
Te
chnology
Educ
a
ti
on
,
13(6),
2235
–
22
53.
htt
ps://
do
i.
org/1
0.
12973/e
ur
asia.
2017.
01223a
[11]
Pere
ira,
B
.
A.
,
Pai,
A.
,
&
Fern
and
es,
C
.
(2017
).
“
A
Com
par
ative
Ana
l
y
s
is
of
Dec
ision
Tr
ee
Algorit
hm
s
for
Predic
ti
ng
Stude
nt
’
s
Perform
anc
e”,
7(4)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
Ind
on
esi
a
n
J
E
le
c Eng &
Co
m
p
Sci
IS
S
N:
25
02
-
4752
Th
e
patt
erns of
a
ccess
i
ng lear
ning
man
ag
e
m
ent system
am
ong st
ude
nts
(
Aki
bu
Ma
hmo
ud
Abd
ullah
i
)
21
[12]
Vahda
t,
M.,
Ghio,
A.
,
One
to,
L.
,
Anguita,
D
.
,
Funk,
M.,
&
Raut
erb
erg
,
M.
(2015).
“
Adva
nce
s
in
Learni
n
g
Anal
y
tics
and
Educ
a
ti
ona
l
Dat
a
Mining”
.
Proce
ed
ings
of
the
2015
European
Symposium
o
n
Arti
ti
fa
l
Neural
Net
works,
Computati
onal
Int
ellige
n
ce
and
Mac
hine
Learnin
g
,
(April)
,
22
–
24.
htt
ps://
do
i
.
org/ISBN
978
-
287587014
-
8.
[13]
Kapur,
B.
,
Ahlu
wali
a
,
N.,
&
Sat
h
y
ar
aj,
R.
(2017).
“
Com
par
at
ive
Stud
y
on
Marks
P
red
ic
ti
on
using
Data
Mining
and
Cla
ss
ifi
c
at
ion
Algorit
hm
s”.
I
nte
rnational
J
ournal
of
A
dvanc
ed
,
8(3)
,
632
–
636.
Ret
ri
eve
d
fro
m
htt
p://ww
w.i
ja
r
c
s.inf
o/i
nd
ex.
php/
Ija
rcs/
art
i
cle/vie
w/3066
[14]
W
il
li
ams
,
D.,
&
W
hit
ing,
A.
(2
016).
“
Expl
orin
g
the
Relati
onsh
ip
Bet
wee
n
S
tu
dent
Enga
g
eme
nt,
Twitter
,
and
a
Le
arn
ing
Mana
g
ement
S
y
stem:
A
Study
of
Und
erg
rad
ua
te
Mark
et
ing
Student
s
”
.
Inte
rnational
Jo
urnal
of
Teachi
ng
&
Lea
rning
in
Higher
Educ
at
io
n
,
28(3),
302.
Ret
ri
eved
from
htt
ps://
ez
prox
y
.
e
afi
t
.
edu
.
co/login
?
ur
l=
h
tt
p:
//
sea
r
c
h.
eb
scohost.
com/logi
n.
aspx
?
dir
e
ct
=true&
db
=e
do
&AN=12061738
1&l
ang=es&sit
e
=e
ds
-
li
v
e&
scope
=sit
e
[15]
Shum
,
S.
B.
,
&
Ferguson,
R.
(20
12).
“
Socia
l
Le
a
rning
Anal
y
t
ic
s.
Educ
a
ti
ona
l
T
echnolog
y
&
Soci
e
t
y
”
,
15(3)
,
3
–
26
.
htt
ps://
do
i.
org/1
0.
1145/2330601.2330616
[16]
Garc
ía,
O.
A.,
&
Seca
des
,
V.
A.
(2013).
“
Big
dat
a
and
le
arn
i
ng
ana
l
y
t
ic
s:
A
pote
ntial
wa
y
to
opti
m
iz
e
e
learn
ing
te
chno
logi
c
al
to
ols”.
Proceedi
n
gs
of
th
e
Int
ernati
onal
Con
fe
re
nce
E
-
Learning
2013,
313
–
317
.
Re
tri
ev
ed
fro
m
htt
p://ww
w.scopus.c
om
/i
nward/
r
ec
ord.
ur
l
?
e
id=
2
-
s2.0
-
84
886911408&pa
rtn
erI
D=t
ZOtx3
y
1
[17]
Remes,
R.
(200
5).
“
Le
arn
ing
Mana
gement
S
ystem”
.
14th
An
nual
Confe
renc
e
of
Doctoral
S
tude
nts,
207
–
21
2.
Ret
ri
eve
d
f
rom
htt
p://ww
w.m
ff.
cuni
.
cz
/v
eda/kon
fer
ence/
wds
/pro
c/
pdf05/WD
S05_037_m
8_Reme
s.pdf
[18]
Jiugen,
Y.,
Ruo
nan,
X.,
&
Lu
yao,
Y.
(2011).
“
The
Applic
atio
n
of
the
Atutor
Le
arn
ing
Cont
ent
Mana
gemen
t
S
y
stem i
n
Teac
h
ing”
,
12,
57
–
60.
[19]
W
ei
,
Y.
(2014).
“
The
Applic
ati
on
of
Sakai
in
Univer
sit
y
of
Scie
nc
e
and
Engi
n
ee
ring
”
.
Edu
cat
i
on
Journal
,
3(4)
,
224
–
228.
ht
tps:/
/
doi.
org/10
.
1164
8/j
.
edu.
2014
030
4.
13
[20]
Fenton,
W
.
(201
0).
“
Schoolog
y
LMS”.
Re
trieve
d
from
htt
ps:/
/www
.
schoolog
y
.
c
om
[21]
Charoe
nwet
,
S.
,
&
Christe
nsen
,
A.
(2016).
“
Th
e
eff
e
ct
of
Edmodo
le
a
rning
n
etw
ork
on
students
’
per
ce
p
ti
on,
se
lf
-
reg
ulated
learni
ng
beha
viors
an
d
le
arn
ing
per
fo
rm
anc
e”.
IMS
C
I
2016
-
10th
In
te
rnational
Mul
t
i
-
Confe
ren
ce
on
Soci
e
ty
,
Cyb
erne
tics
and
Informatic
s,
Proceedi
ngs
,
(
Ims
ci
)
,
297
–
300.
Ret
r
ie
ved
from
htt
ps://
ww
w.sco
pus.c
om
/i
nward/
rec
ord.
u
ri
?
e
id=
2
-
s2.0
-
85013629379&pa
rtne
rID=40
&md5=f1766af
4775
eb0d96a
2fa
a8c
5
ee
c
c673
[22]
Sim
on,
K.
(20
16).
“
Edmodo:
The
Facebook
of
L
ea
rni
ng
Plat
form
s”.
T
esl
-
Ej,
20(1)
,
1
–
7.
Re
tri
ev
ed
fr
om
htt
ps://
lope
s.idm
.
oclc.
org
/l
ogin
?
u
rl=
htt
p
:/
/se
arc
h
.
e
bscohost.
com/lo
gin.
aspx
?
d
irect=true
&db
=e
hh&
AN
=116408995
&sit
e=eds
-
li
v
e&s
cope
=site
[23]
Sood,
A.,
Sinh
a,
N.,
Dewj
ee,
S.,
&
Zha
o
,
W
.
(20
13).
“
Ta
bl
ea
u
T
utori
al”.
Ret
r
ie
v
ed
from
htt
p:
//
c
a
sci.
um
d.
edu/
wp
-
cont
en
t/
uplo
ads/
2013/12/
Ta
b
leau
-
Tut
ori
al
.
pdf
[24]
Cox,
N.
J.
(2005
).
“
A bri
e
f
histor
y
of
Sta
ta on
i
ts
20th
ann
ive
rsar
y”.
S
tat
a
Journal
,
5(1), 2
–
18.
[25]
Squill
ante,
J.,
&
Hart
e
y
,
T.
(2
014)
.
“
Anal
y
zi
n
g
Bla
ckbo
ard
:
Us
ing
a
Learni
n
g
Mana
gement
S
y
stem
From
th
e
Student
Perspe
ctive”.
[26]
Alves,
P.
,
Mira
nda,
L.,
&
Mor
ai
s,
C
.
(2017)
.
“
The
Influ
enc
e
of
Virtual
L
ea
r
ning
Environm
ent
s
in
Studen
ts’
Perform
anc
e”.
Unive
rs
al
Journal
of
E
ducat
ional
Re
search
,
5
(3),
517
–
527.
htt
ps://
do
i.
org/1
0.
13189/ujer.
20
17.
050325
[27]
Ngu
y
en
,
V.
A.
(
2017).
“
Towa
rd
s
the
implement
at
ion
of
an
asses
sm
ent
-
ce
ntre
d
bl
ende
d
l
ea
rn
ing
f
ramework
at
th
e
cour
se
le
ve
l”.
Inte
rnational
Journal
of
Information
and
Learning
Technol
og
y
,
34(1),
20
–
30.
htt
ps://
do
i.
org/1
0.
1108/IJILT
-
08
-
2016
-
0031
[28]
Park,
Y.,
&
Jo,
I.
-
H.
(2016).
“
Us
ing
log
var
ia
bl
es
in
a
le
arn
ing
m
ana
gement
s
y
s
te
m
to
eva
luate
le
arn
ing
ac
t
ivi
t
y
using
the
le
ns
of
a
ctivity
th
eor
y
”.
Assess
ment
&
Ev
aluat
ion
in
Higher
Educ
a
ti
on,
29
38(April)
,
1
–
17
.
htt
ps://
do
i.
org/1
0.
1080/0260293
8.
2016.
1158236
[29]
W
il
li
ams
,
C.
(
2007).
“
Resea
r
ch
Methods”.
Journal
of
Bu
siness
&
Ec
onomic
Re
search
,
5(3),
65
–
72.
htt
ps://
do
i.
org/1
0.
1093/fa
m
pra
ct/cmi221
[30]
Marti
n,
F.
,
&
Ndo
y
e
,
A.
(201
6).
“
Us
ing
Le
ar
ning
Anal
y
t
ic
s
t
o
As
sess
Student
Learni
ng
in
Online
Courses
”.
Journal
of
Univ
e
rs
it
y
Teach
ing
&
Learning
Prac
tice
,
13(133). ht
tp
s://
doi.
org
/10.
11
77/0047239516656369.
Evaluation Warning : The document was created with Spire.PDF for Python.