Indonesi
an
Journa
l
of El
ect
ri
cal Engineer
ing
an
d
Comp
ut
er
Scie
nce
Vo
l.
24
,
No.
1
,
Octo
be
r
20
21
,
pp.
47
3
~
483
IS
S
N: 25
02
-
4752, DO
I: 10
.11
591/ijeecs
.v
2
4
.i
1
.
pp
47
3
-
483
473
Journ
al h
om
e
page
:
http:
//
ij
eecs.i
aesc
or
e.c
om
Engaging studen
ts to fill
surve
ys usin
g c
h
atbots:
U
niversi
ty case
study
Nadir B
el
haj
1
,
A
b
demo
un
aime H
amdane
2
, Nou
r
El
H
ouda Ch
aoui
3
, Habib
a Ch
aoui
4
,
Moulhi
me El
Be
kka
li
5
1,2,3,5
Depa
rtment
of
Elec
tr
ical and
Com
pute
r
Eng
i
nee
ring
,
Sidi
Mo
hamed
Ben
Abdellah
Univer
si
t
y
,
Fez, Moroc
co
4
Nati
ona
l
School
of
Appli
ed
Sc
ience
s, Ibn T
of
ail
Univer
sit
y
,
Keni
tra
,
Morocc
o
Art
ic
le
In
f
o
ABSTR
A
CT
Art
ic
le
history:
Re
cei
ved
J
u
n
9
,
20
21
Re
vised
J
ul
26
,
2021
Accepte
d
Aug
4
,
2021
T
h
e
u
s
e
o
f
c
h
a
t
b
o
t
o
r
c
o
n
v
e
r
s
a
t
i
o
n
a
l
a
g
e
n
t
s
i
s
b
e
c
o
m
i
n
g
c
o
m
m
o
n
t
h
e
s
e
d
a
y
s
b
y
t
h
e
c
o
m
p
a
n
i
e
s
i
n
m
a
n
y
f
i
e
l
d
s
t
o
m
a
k
e
s
m
a
r
t
c
o
n
v
e
r
s
a
t
i
o
n
s
w
i
t
h
u
s
e
r
s
.
B
a
c
k
e
d
b
y
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
a
n
d
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
s
s
i
n
g
t
h
e
y
p
r
o
v
i
d
e
a
s
t
r
o
n
g
p
l
a
t
f
o
r
m
t
o
e
n
g
a
g
e
u
s
e
r
s
.
T
h
e
s
e
p
o
s
i
t
i
v
e
a
s
p
e
c
t
s
o
f
c
h
a
t
b
o
t
s
c
a
n
b
e
b
e
n
e
f
i
c
i
a
l
i
n
t
h
e
e
d
u
c
a
t
i
o
n
a
l
s
e
c
t
o
r
,
e
s
p
e
c
i
a
l
l
y
i
n
c
o
n
d
u
c
t
i
n
g
o
n
l
i
n
e
s
u
r
v
e
y
.
T
h
i
s
s
t
u
d
y
a
i
m
s
t
o
e
x
p
l
o
r
e
t
h
e
f
e
a
s
i
b
i
l
i
t
y
o
f
a
n
e
w
c
h
a
t
b
o
t
a
p
p
r
o
a
c
h
s
u
r
v
e
y
a
s
a
n
e
w
s
u
r
v
e
y
m
e
t
h
o
d
i
n
M
o
r
o
c
c
a
n
u
n
i
v
e
r
s
i
t
y
t
o
o
v
e
r
c
o
m
e
t
h
e
w
e
b
s
u
r
v
e
y
’
s
c
o
m
m
o
n
r
e
s
p
o
n
s
e
q
u
a
l
i
t
y
p
r
o
b
l
e
m
s
.
I
n
d
e
e
d
,
h
a
v
i
n
g
s
t
u
d
e
n
t
f
e
e
d
b
a
c
k
b
e
f
o
r
e
a
n
d
a
f
t
e
r
g
r
a
d
u
a
t
i
o
n
i
s
e
s
s
e
n
t
i
a
l
f
o
r
u
n
i
v
e
r
s
i
t
y
a
s
s
e
s
s
m
e
n
t
.
T
h
i
s
n
e
w
a
p
p
r
o
a
c
h
k
e
e
p
s
s
t
u
d
e
n
t
s
e
n
g
a
g
e
d
,
s
u
p
p
o
r
t
i
v
e
,
a
n
d
e
v
e
n
e
x
c
i
t
e
d
t
o
o
f
f
e
r
f
e
e
d
b
a
c
k
w
i
t
h
o
u
t
g
e
t
t
i
n
g
b
o
r
e
d
a
n
d
d
r
o
p
p
i
n
g
t
h
e
c
o
n
v
e
r
s
a
t
i
o
n
,
e
s
p
e
c
i
a
l
l
y
i
n
M
o
r
o
c
c
a
n
u
n
i
v
e
r
s
i
t
i
e
s
k
n
o
w
n
b
y
a
n
o
v
e
r
c
r
o
w
d
i
n
g
o
f
s
t
u
d
e
n
t
s
w
h
e
r
e
i
t
i
s
d
i
f
f
i
c
u
l
t
t
o
g
e
t
t
h
e
i
r
f
e
e
d
b
a
c
k
.
T
h
i
s
f
e
e
d
b
a
c
k
f
e
e
d
s
i
n
t
o
o
u
r
u
n
i
v
e
r
s
i
t
y
'
d
a
t
a
b
a
s
e
s
f
o
r
f
u
r
t
h
e
r
r
e
p
o
r
t
i
n
g
a
n
d
d
e
c
i
s
i
o
n
m
a
k
i
n
g
t
o
i
m
p
r
o
v
e
t
h
e
q
u
a
l
i
t
y
o
f
e
d
u
c
a
t
i
o
n
a
l
c
o
n
t
e
n
t
a
n
d
s
t
u
d
e
n
t
-
o
r
i
e
n
t
e
d
s
e
r
v
i
c
e
s
.
F
i
n
a
l
l
y
,
w
e
h
a
v
e
s
h
o
w
n
t
h
e
e
f
f
e
c
t
i
v
e
n
e
s
s
o
f
o
u
r
a
p
p
r
o
a
c
h
b
y
a
c
o
m
p
a
r
a
t
i
v
e
d
a
t
a
s
t
u
d
y
b
e
t
w
e
e
n
t
h
e
t
r
a
d
i
t
i
o
n
a
l
o
n
l
i
n
e
s
u
r
v
e
y
a
n
d
t
h
e
u
s
e
o
f
t
h
i
s
c
h
a
t
b
o
t
.
Ke
yw
or
ds:
Ar
ti
fici
al
intel
li
gen
ce
Chatb
ot
Conver
sat
ion s
yst
e
m
s
Hu
m
an
-
m
achine inte
racti
on
NLP
Ov
e
rcro
wd
i
ng
un
i
ver
sit
y
Un
i
ver
sit
y
This
is an
open
acc
ess arti
cl
e
un
der
the
CC
B
Y
-
SA
l
ic
ense
.
Corres
pond
in
g
Aut
h
or
:
Nour El
Hou
da
Cha
ou
i
Dep
a
rtm
ent o
f El
ect
rical
an
d
Com
pu
te
r
E
ng
i
neer
i
ng
Sidi Mo
ham
ed
Be
n A
bd
el
la
h
Un
i
ver
sit
y
Ecole
Nati
on
al
e d
es
Sciences
Appliq
uées,
St
reet M
y A
bd
al
l
ah
Km
5
, Route
d'
Im
ou
zzer, B
P
72, fez, M
oroc
co
Em
a
il
:
ho
uda.c
haoui@
us
m
ba.
ac.m
a
1.
INTROD
U
CTION
Currentl
y,
the
uni
ve
rsity
is
con
f
r
on
te
d
m
or
e
tha
n
eve
r
with
sever
al
chall
enges
an
d
co
ns
trai
nts
exp
ect
in
g
it
s
m
ai
n
ro
le
,
w
hich
is
the
trans
m
issi
on
of
knowle
dge.
I
n
a
w
or
l
d
so
-
cal
le
d
vo
la
ti
li
ty
,
un
ce
rtai
nty,
com
plexity
and
am
big
uity
(
VU
C
A
)
[1
]
,
[
2],
T
he
dig
it
al
trans
form
at
io
n
of
t
he
un
i
ve
rsity
is
an
a
bs
ol
ute
pr
i
or
it
y
in
ord
er
to
be
a
ble
to
ada
pt
bette
r
to
this
world
but
al
so
to
ev
ol
ve
an
d
to
re
-
e
valuate
it
s
assessm
en
t
syst
e
m
.
Howe
ver,
this
ev
olu
t
ion
can
not
be
done
with
out
a
co
ntin
uous
ev
al
uation
by
t
he
va
rio
us
act
or
s
of
t
he
un
i
ver
sit
y
and
m
or
e
par
ti
cu
la
rly
by
it
s
st
ud
e
nts
be
fore
and
/o
r
after
ob
ta
ini
ng
thei
r
dip
lom
as
in
order.
Gen
e
rall
y,
the m
os
t
widely
use
d
re
prese
ntati
ve
re
searc
h
m
et
hod
is
base
d
on
s
urveys
by
ga
therin
g
i
nform
at
ion
from
a
la
rg
e
num
ber
of
stu
de
nts
to
ens
ur
e
a
dequate
res
ponse
rates
for
the
evaluati
on
of
serv
ic
es
a
nd
qual
it
y
of
trai
ning.
Ne
ver
t
heless,
in
orde
r
to
obta
in
t
heir
fee
dback
,
it
is
m
os
t
of
te
n
diff
ic
ult
to
en
coura
ge
or
m
ot
ivate
the
stu
de
nt
s
to
fill
in
the
e
valu
at
ion
qu
e
sti
onna
ires
co
ns
i
der
e
d
too
hea
vy
[3
]
,
[
4].
In
e
m
e
r
g
i
n
g
c
ou
n
t
r
i
e
s
,
e
s
p
e
c
i
a
l
l
y
i
n
M
o
r
o
c
c
a
n
u
n
i
v
e
r
s
i
t
i
e
s
,
t
h
e
p
r
o
b
l
e
m
p
e
r
s
i
s
t
s
e
v
e
n
m
o
r
e
b
e
c
a
u
s
e
o
f
s
e
v
e
r
a
l
r
e
a
s
o
n
s
:
l
a
c
k
o
f
i
n
f
o
r
m
a
t
i
o
n
s
y
s
t
e
m
,
o
v
e
r
c
r
o
w
d
i
n
g
o
f
s
t
u
d
e
n
t
s
w
i
t
h
a
l
o
w
a
dm
i
n
i
s
t
r
a
t
i
ve
a
n
d
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.
2
4
, N
o.
1
,
Oct
o
ber
20
21
:
47
3
-
483
474
p
e
d
a
g
o
g
i
c
a
l
s
u
p
e
r
v
i
s
i
o
n
r
a
t
e
,
l
a
c
k
o
f
r
e
s
o
u
r
c
e
s
a
n
d
o
t
h
e
r
s
c
o
n
s
t
r
a
i
n
t
s
,
[
5
]
-
[
7
]
.
I
t
i
s
t
h
e
r
e
f
o
r
e
n
e
c
e
s
s
a
r
y
t
o
u
s
e
o
t
h
e
r
m
o
r
e
i
n
no
v
a
t
i
v
e
a
n
d
i
n
t
e
r
a
c
t
i
v
e
a
p
p
r
o
a
c
h
t
o
e
s
t
a
bl
i
s
h
g
o
o
d
c
o
n
t
a
c
t
w
i
t
h
s
t
u
d
e
n
t
s
i
n
o
r
d
e
r
t
o
h
a
v
e
t
h
e
i
r
f
e
e
d
b
a
c
k
a
n
d
t
o
r
e
c
e
i
v
e
t
h
e
i
nf
o
r
m
a
t
i
o
n
n
e
c
e
s
s
a
r
y
f
o
r
u
n
i
v
e
r
s
i
t
y
a
s
s
e
s
s
m
e
nt
.
T
o
e
s
t
a
b
l
i
s
h
a
f
r
u
i
t
f
u
l
r
e
l
a
t
i
o
n
s
h
i
p
w
i
t
h
t
h
e
s
t
u
d
e
n
t
s
,
a
c
o
n
c
e
pt
i
on
o
f
a
n
i
n
t
e
r
a
c
t
i
v
e
a
n
d
a
t
t
r
a
c
t
i
v
e
s
y
s
t
e
m
i
s
f
u
n
d
a
m
e
n
t
a
l
.
W
i
t
h
t
h
e
e
m
e
r
g
e
n
c
e
o
f
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
,
i
t
i
s
t
i
m
e
t
o
r
e
t
h
i
n
k
t
h
e
w
a
y
w
e
c
om
m
u
n
i
c
a
t
e
w
i
t
h
s
t
u
d
e
n
t
s
.
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
c
o
u
l
d
d
i
s
r
u
p
t
s
o
c
i
e
t
y
i
n
s
e
v
e
r
a
l
w
a
y
s
.
I
t
i
s
g
r
a
d
u
a
l
l
y
a
f
f
e
c
t
i
n
g
o
u
r
h
a
b
i
t
s
a
n
d
t
h
e
r
e
f
o
r
e
o
u
r
w
a
y
o
f
l
i
f
e
.
I
t
a
c
t
u
a
l
ly
i
n
f
l
u
e
n
c
e
s
o
u
r
d
a
i
l
y
b
e
h
a
v
i
o
r
s
a
n
d
t
h
e
w
a
y
w
e
i
n
v
o
l
v
e
b
y
d
e
s
i
g
n
i
n
g
i
n
t
e
l
l
i
g
e
n
t
"
b
o
t
"
a
g
e
n
t
s
a
b
l
e
o
f
p
e
r
f
o
r
m
i
ng
v
a
r
i
o
u
s
f
u
n
c
t
i
o
n
s
p
r
e
v
i
o
u
s
l
y
d
o
n
e
b
y
h
u
m
a
n
s
.
T
h
e
o
p
p
o
r
t
u
n
i
t
i
e
s
f
o
r
u
s
i
n
g
b
o
t
s
a
r
e
e
n
d
l
e
s
s
[
8
]
-
[
1
1
]
.
P
a
r
t
i
c
u
l
a
r
l
y
,
y
o
u
n
g
p
e
o
p
l
e
a
r
e
a
f
f
e
c
t
e
d
b
y
t
h
e
i
m
p
a
c
t
o
f
t
h
i
s
t
e
c
h
n
o
l
o
g
y
a
n
d
u
s
e
i
t
a
l
m
o
s
t
a
l
l
t
h
e
t
i
m
e
.
T
h
e
e
x
p
o
n
e
n
t
i
a
l
p
r
o
l
i
f
e
r
a
t
i
o
n
o
f
s
m
a
r
t
p
h
o
n
e
s
a
n
d
t
h
e
i
r
w
i
d
e
s
p
r
e
a
d
u
s
e
b
y
s
t
ud
e
n
t
s
o
f
f
e
r
s
u
n
i
v
e
r
s
i
t
i
e
s
e
n
o
r
m
o
u
s
o
p
p
o
r
t
u
n
i
t
i
e
s
i
n
t
e
r
m
s
o
f
i
n
n
o
v
a
t
i
v
e
t
e
c
h
n
o
l
o
g
i
c
a
l
a
p
p
r
o
a
c
h
e
s
t
o
i
n
t
e
r
a
c
t
w
i
t
h
s
t
u
d
e
n
t
s
i
n
o
r
d
e
r
t
o
i
m
p
r
ov
e
t
h
e
q
u
a
l
i
t
y
o
f
i
t
s
s
t
r
a
t
e
g
i
e
s
[
1
2
]
.
C
h
a
t
b
o
t
s
o
r
c
o
n
v
e
r
s
a
t
i
o
n
a
l
a
ge
n
t
s
a
r
e
b
e
c
om
i
n
g
a
v
e
r
y
i
m
po
r
t
a
n
t
t
o
o
l
i
n
o
u
r
l
i
v
e
s
.
C
h
a
t
bo
t
s
a
r
e
c
om
p
u
t
e
r
p
r
o
g
r
a
m
s
r
e
p
l
a
c
i
n
g
s
om
e
o
f
t
h
e
jo
b
s
t
h
a
t
a
r
e
t
r
a
d
i
t
i
o
n
a
l
l
y
p
e
r
f
o
r
m
e
d
b
y
h
u
m
a
n
s
,
s
u
c
h
a
s
o
n
l
i
n
e
c
u
s
t
om
e
r
s
e
r
v
i
c
e
a
g
e
n
t
s
,
m
u
s
e
um
g
u
i
d
e
s
,
t
e
c
h
n
i
c
a
l
s
u
p
p
o
r
t
,
l
a
n
g
u
a
g
e
t
e
a
c
h
e
r
s
a
n
d
e
d
u
c
a
t
o
r
s
[
8
]
,
[
1
3
]
.
T
h
r
o
u
g
h
a
p
e
r
s
o
n
-
m
a
c
hi
n
e
i
nt
e
r
f
a
c
e
[
1
4
]
,
t
h
e
c
h
a
t
bo
t
i
s
a
n
a
g
e
n
t
w
h
o
c
o
m
m
u
n
i
c
a
t
e
s
w
i
t
h
a
us
e
r
o
n
a
w
e
l
l
-
d
e
f
i
n
e
d
s
u
b
j
e
c
t
o
r
d
o
m
a
i
n
u
s
i
n
g
t
e
x
t
a
n
d
v
o
i
c
e
i
n
o
r
d
e
r
t
o
p
r
o
v
i
d
e
i
n
t
e
r
a
c
t
i
v
e
s
e
r
v
i
c
e
s
[
9
]
,
[
1
0
]
,
[15
]
-
[17]
.
T
h
e
c
h
a
t
b
o
t
i
s
a
n
i
n
t
e
r
a
c
t
i
v
e
t
o
o
l
,
w
h
i
c
h
a
i
m
s
t
o
r
e
s
p
o
n
d
t
o
r
e
q
u
e
s
t
s
m
a
d
e
b
y
u
s
e
r
s
o
n
a
s
p
e
c
i
f
i
c
a
r
e
a
[
1
8
]
,
[
1
9
]
.
F
r
e
q
u
e
n
t
l
y
,
i
t
i
s
e
q
u
i
p
p
e
d
w
i
t
h
a
r
t
i
f
i
c
i
a
l
i
nt
e
l
l
i
g
e
n
c
e
t
h
a
t
a
l
l
o
w
s
i
t
t
o
u
n
d
e
r
s
t
a
n
d
t
h
e
c
o
nt
e
x
t
a
n
d
r
e
a
c
t
a
c
c
o
r
d
i
n
g
t
o
t
h
e
d
a
t
a
a
v
a
i
l
a
b
l
e
o
n
t
he
s
u
b
j
e
c
t
i
n
t
h
e
d
a
t
a
b
a
s
e
s
e
r
v
e
r
s
.
T
h
e
c
h
a
t
b
o
t
a
r
c
h
i
t
e
c
t
u
r
e
i
n
t
e
g
r
a
t
e
s
c
a
l
c
u
l
a
t
i
o
n
a
l
g
o
r
i
t
hm
s
,
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
s
s
i
n
g
(
N
L
P
)
a
n
d
p
s
y
c
h
o
l
o
g
i
c
a
l
k
n
o
w
l
e
d
g
e
t
o
i
n
t
e
r
a
c
t
w
i
t
h
h
um
a
n
s
o
r
o
t
h
e
r
c
h
a
t
b
o
t
s
in
h
u
m
a
n
l
a
n
g
u
a
g
e
b
y
t
e
x
t
o
r
v
o
i
c
e
[
2
0
]
-
[23]
.
E
v
e
r
y
t
h
i
n
g
s
t
a
r
t
e
d
f
r
om
1964
to
1
9
6
6
,
w
h
e
n
W
e
i
z
e
n
b
a
u
m
d
e
v
e
l
o
p
e
d
t
h
e
f
i
r
s
t
bot
E
L
I
Z
A
,
an
e
a
r
l
y
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
s
s
i
n
g
c
om
p
ut
e
r
p
r
o
g
r
a
m
at
t
he
m
i
n
i
m
um
i
g
n
i
t
i
o
n
t
e
m
p
e
r
a
t
u
r
e
(
M
I
T
)
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
l
a
b
o
r
a
t
o
r
y
[
2
4
]
.
T
h
e
n
A
l
i
c
e
[25]
to
A
l
e
x
a
f
r
om
A
m
a
z
o
n
[26
]
,
[
27
],
A
m
a
z
o
n
E
c
h
o
[
2
8
]
,
G
o
o
g
l
e
a
s
s
i
s
t
a
n
t
,
M
i
c
r
o
s
o
f
t
’
s
C
o
r
t
a
n
a
[
2
9
]
,
S
i
r
i
f
r
om
A
p
p
l
e
a
n
d
o
t
h
e
r
s
.
T
o
d
a
y
c
h
a
t
b
o
t
s
a
r
e
g
e
t
t
i
n
g
s
m
a
r
t
e
r
a
n
d
a
c
c
e
s
s
i
b
l
e
w
i
t
h
t
h
e
p
r
o
g
r
e
s
s
of
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
a
l
g
o
r
i
t
h
m
s
,
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
s
s
i
n
g
[
2
2
]
,
[30]
a
n
d
m
e
s
s
a
g
i
n
g
pl
a
t
f
o
r
m
s
s
u
c
h
as
F
a
c
e
bo
o
k
.
In
the
e
du
cat
io
n
fiel
d,
m
any
t
ype
of
r
esearc
h
ha
ve
bee
n
done
in
t
he
i
m
ple
m
entat
ion
of
a
ped
a
gogi
c
conve
rsati
on
al
agen
t
that
disc
us
s
a
certai
n
to
pic
with
a
stude
nt
assum
ing
the
ro
le
of
the
te
acher
[31
]
,
[
32]
,
or
helping
st
ud
e
nt
in
univer
sit
y
or
ie
ntati
on
[33
]
.
As
well
deliveri
ng
pe
dago
gical
co
ntent
a
nd
c
overi
ng
a
wide
var
ie
ty
of
le
ss
ons
an
d
sub
j
ect
s
by
us
in
g
m
ult
i
m
edia
con
te
nt
and
s
peec
hes
[
34
]
,
[
35]
.
In
re
cent
ye
ars,
ther
e
has
been
a
pa
rtic
ul
ar
interest
in
the
use
of
C
hatbo
ts
i
n
ed
u
cat
i
on.
Di
ff
e
ren
t
a
dv
a
ntage
s
offe
red
by
these
s
yst
e
m
s
com
bin
ed
with
the
be
ne
fits
of
dig
it
al
te
ch
no
l
og
y:
insta
nt
aneous
a
vaila
bili
ty
,
low
co
s
t,
co
ns
ist
ency,
qu
ic
k
respo
ns
e
ti
m
e
s,
scal
e
up
a
nd
interact
ivit
y
[36].
Wh
ic
h
m
akes
it
possible
t
o
e
nsure
in
vo
l
vem
e
nt
an
d
m
ot
ivati
on
as
well
as
the
rev
isi
on
of
ed
ucati
on
al
ob
j
ect
ives
and
strat
egy.
The
ad
van
ta
ge
of
the
chatb
ot
is
al
so
that
it
s
us
e
is
s
i
m
ple
and
i
ntui
ti
ve
and
it
can
be
i
nteg
rated
into
gro
up
co
nversati
ons
or
s
har
e
d
li
ke
any
oth
e
r
con
ta
ct
[37].
Re
centl
y,
to
e
xam
ine
edu
cat
ion
al
c
hatb
ot
s
f
or
Face
book
m
esseng
er,
a
stu
dy
wa
s
c
onduct
ed
wh
ic
h
e
valuate
d
47
out
of
89
chatb
ot
s
f
or
l
earn
i
ng
i
de
ntifie
d
us
i
ng
the
Faceb
ook
m
essen
ger
platf
orm
.
The
resu
lt
s
of
this
stud
y
co
nf
irm
t
hat
chatb
ot
pro
gr
am
m
ing
(espec
ia
ll
y
on
Face
boo
k
m
essen
ger
)
is
sti
ll
in
its
early
sta
ges
[
15]
.
In
a
cha
ng
i
ng
e
du
cat
io
nal
e
nviro
nm
ent,
every
un
i
ver
sit
y
ne
eds
to
colle
ct
feedbac
k
from
its
stud
e
nts,
w
hether
t
hro
ugh
i
nt
erv
ie
ws
or
by
co
nductin
g
onli
ne
s
urveys
and
it
’
s
a
da
unti
ng
ta
sk
bec
ause
no
hu
m
an
bei
ng
li
kes
to
s
pend
a
long
-
ti
m
e
fill
in
g
form
,
and
t
his
is
w
here
c
hatbo
ts
will
com
e
to
act
ion.
Our
resea
rch
pur
pose
is
twofold.
Fi
rst,
this
stud
y
ai
m
s
to
pro
po
se
a
ne
w
appr
oach
base
d
on
chat
bo
ts
to
hook
stu
de
nt
s
to
the
us
e
of
the
conve
rsati
on
syst
em
by
m
aking
it
m
or
e
affordable
,
use
fu
l
a
nd
fun
to
us
e
.
This
c
hatb
ot
w
il
l
colle
ct
sign
i
ficant
a
nd
qu
al
it
at
ive
data
from
stud
e
nt
s
by
m
aking
them
eng
age
d
in
t
he
conve
rsati
on
on
a
daily
or
w
eekly
basis
wi
thout
getti
ng
bore
d
an
d
dro
pp
i
ng
the
c
on
ver
sat
io
n
i
n
order
t
o
process
them
fo
r
quic
k
an
d
a
ccur
at
e
re
ports
on
t
he
un
i
ver
s
it
y.
Seco
nd,
a
com
par
at
ive
da
ta
stud
y
bet
w
een
t
he
tradit
ion
al
on
li
ne
sur
vey
an
d
the
us
e
of
this
chatb
ot
was
ca
rr
ie
d
t
o
sho
w
the
ef
fecti
ven
e
s
s
of
our
a
ppro
a
ch.
I
n
the
first
sect
io
n,
we
giv
e
a
ge
ner
al
intr
odu
c
ti
on
of
the
cha
tbo
t
f
ram
ewo
r
k
an
d
we
desc
ribe
the
c
onve
rsati
on
flo
w
of
t
he
ch
at
bo
t
an
d
it
s
com
po
sin
g
blo
c
ks
.
I
n
the
nex
t
sect
ion
,
we
gi
ve
so
m
e
resu
lt
s
from
it
s
daily
us
ag
e
by
natio
nal
sc
hool of
a
pp
li
ed
sciences
st
ud
e
nts
f
r
om
Sidi
Moh
am
ed
Be
n
A
bd
el
la
h
U
ni
v
ersit
y. In
ad
di
ti
on
, w
e
sh
ow the effect
iveness of our ap
pr
oach
by a co
m
par
at
ive d
a
ta
stud
y betwe
en
the traditi
on
al
o
nline surv
e
y and
the use
of
t
his
chatb
ot and
at
the sam
e tim
e, t
he fin
dings a
re
d
isc
us
se
d
a
nd
con
cl
us
io
n
a
re
dr
a
w
n
at
the
end.
2.
RESEA
R
CH ME
THO
D
2.1.
Chatbo
t framew
ork
T
h
e
r
e
a
r
e
s
e
v
e
r
a
l
c
a
t
e
g
o
r
i
e
s
of
c
h
a
t
b
o
t
s
c
l
a
s
s
i
f
i
e
d
u
s
i
n
g
d
i
f
f
e
r
e
n
t
p
a
r
a
m
e
t
e
r
s
l
i
k
e
t
h
e
i
n
p
u
t
p
r
o
c
e
s
s
i
n
g
,
t
h
e
k
n
o
w
l
e
d
g
e
d
o
m
a
i
n
,
r
e
s
p
o
n
s
e
g
e
n
e
r
a
t
i
o
n
m
e
t
h
o
d
or
o
t
h
e
r
c
a
t
e
g
o
r
i
e
s
[8
]
,
[
1
3
]
.
A
c
h
a
t
b
o
t
can
b
e
l
o
n
g
c
e
r
t
a
i
n
l
y
to
m
o
r
e
t
h
a
n
on
e
c
l
a
s
s
i
f
i
c
a
t
i
on
at
a
t
i
m
e
[38
]
,
[
3
9
]
.
D
e
p
e
n
d
i
n
g
on
t
h
e
a
l
g
o
r
i
t
hm
s
a
n
d
t
e
c
h
n
i
q
u
e
s
a
d
o
p
t
e
d
,
t
w
o
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
En
gaging st
udents to
fi
ll
su
rv
eys us
i
ng chat
bo
ts
:
U
niversi
t
y case
stu
dy
(
Nad
ir
Belh
aj
)
475
a
p
p
r
o
a
c
h
e
s
e
x
i
s
t
to
d
e
v
e
l
o
p
c
h
a
t
b
o
t
.
T
h
e
f
i
r
s
t
one
u
s
e
s
p
a
t
t
e
r
n
m
a
t
c
h
i
n
g
[
8
]
,
[
4
0
]
,
[
4
1
]
,
and
the
s
eco
nd
appr
oach
base
d
on
m
achine
le
arn
in
g
e
xtr
act
s
con
te
nt
f
ro
m
us
er
in
put
and
has
the
capaci
ty
to
acqu
i
re
conve
rsati
ons
us
in
g
NLP,
[8
]
,
[
42
]
,
[
43]
.
In
this
pap
e
r,
we
us
e
knowle
dg
e
dom
ai
n
-
based
cat
eg
or
iz
at
ion
that
ta
kes
i
nto
acc
ount
the
know
le
dge
a
chatbo
t
can
acce
ss
and
the
qu
a
ntit
y
of
data
it
is
trai
ned
upon.
Th
e
desi
gn
of
chat
bo
t
is
based
on
m
a
chin
e
le
arn
in
g
us
i
ng
NLP
.
We
sta
rted
with
the
m
a
in
chatb
ot
f
ra
m
ewo
r
k
as
sho
wn
in
Fi
gure
1
wh
ic
h
e
xp
la
in
s
how
an
e
nd
us
e
r
will
interact
with
t
he
un
i
ver
sit
y
bot.
Let
us
descri
be
our
dif
fer
e
nt
f
ram
ewo
rk
c
om
po
ne
nt
an
d
their
functi
onal
it
ie
s:
Figure
1. Chat
bo
t
f
ram
ewo
r
k
User (
m
ob
il
e use
r
):
th
e stu
de
nt
en
ga
ging i
n
t
he
c
onve
rsati
on.
Phon
e:
is
the
de
vice
the
stu
de
nt
usi
ng
to
c
onver
se
.
T
he
pro
cess
sta
rts
with
a
us
er
’
s
reque
st,
f
or
exam
ple,
“
How
easy
is
it
to
ob
ta
in
t
he
resou
rces
yo
u
need
f
r
om
the
un
i
ver
sit
y
li
br
a
ry
syst
e
m
?
”
t
o
the
chatb
ot
usi
ng
a m
essaging
platfor
m
[
44]
.
Me
ssaging
p
la
tfor
m
:
th
e
pla
tfor
m
that
the
conver
sat
io
n
will
be
based
on
.
Ma
ny
op
ti
on
s
exist
here
(F
ace
book
m
e
ssen
ger,
Slac
k,
Tw
it
te
r
and
Allo
)
.
W
e
us
e
d
the
Faceb
oo
k
m
esseng
er
pl
at
fo
rm
becau
s
e
a
la
rg
e
m
ajorit
y
of
Mo
ro
cca
n
unive
rsity
stud
e
nts
us
es
Faceb
ook
e
sp
eci
al
ly
with
this
per
i
od
of
pa
nd
em
i
c
that t
he worl
d i
s experie
ncin
g i
n
the
face
of
Cov
i
d
-
19.
Natu
ral
la
ngua
ge
proces
sin
g
:
a
fter
the
cha
tbo
t
receive
s
the
us
e
r
re
qu
e
st,
ever
y
recei
ved
m
essage
is
processe
d
t
hro
ugh NLP
,
[18],
[
22
]
,
[
23
]
,
[
45]
.
Bot
lo
gic:
the
bo
t l
og
ic
al
flo
w of
i
nteracti
ons
Ma
chine
le
a
r
ni
ng
:
e
ve
r
y t
i
m
e the bot
receive
s a m
essage,
it
can im
pr
ove it
s an
s
wers.
Kno
wled
ge
ba
se:
it
i
s
the
wisd
om
of
the
bot
an
d
it
can
be
a
data
la
ke
,
a
d
at
a
m
ana
gem
ent
platform
,
database
,
data
war
e
hous
e
a
nd
so
m
e
hu
m
an
i
nteracti
on
beca
us
e
not
al
l
ans
wer
s
a
re
sto
red,
we
m
igh
t
need
to as
k
real
hum
ans.
Be
fore starti
ng
o
ur
bo
t
desig
n, we nee
d
to
find
t
he bes
t ap
proac
h
to
en
ga
ge
o
ur
us
er
s in
a
d
ai
ly
b
asi
s
or
at
le
ast
a
we
ekly
basis
an
d
pu
s
h
t
hem
to
us
e
the
bot
an
d
conve
rse.
We
wire
f
ram
ed
a
si
m
ple
app
r
oac
h
that
is
stud
ent
ce
ntr
ic
wh
ere
th
e
stud
e
nt
is
the
co
re
of
t
he
co
nv
e
rsati
on,
we
will
eng
a
ge
him
b
y
of
fe
rin
g
m
ult
iple
interest
ing
se
r
vices,
an
d
only
then,
we
will
ask
hi
m
on
e
su
r
vey
quest
io
n
per
day
and
store
it
s
answ
e
r.
W
e
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.
2
4
, N
o.
1
,
Oct
o
ber
20
21
:
47
3
-
483
476
al
read
y
know
that
m
any
stude
nts
will
no
t
a
ns
we
r
t
he
qu
e
sti
on
s
so
we
m
ade
it
m
or
e
interest
ing
by
giv
in
g
them
so
m
e fr
e
e facts a
bout t
he
un
ive
r
sit
y an
d
the
stu
de
nt m
ajor
as
s
how
n
i
n
F
i
gure
2
.
Figure
2. Exa
m
ple o
f
a
way
to enga
ge
st
udents to
the c
on
ver
sat
io
n
2.2.
Desig
n
of the c
onvers
ati
on flow
The
first
ste
p
is
to
design
th
e
conver
sat
io
n
flow
or
dialo
g
flo
w
by
sp
li
tt
ing
the
proce
ss
into
tw
o
separ
at
e
bl
ocks
(engag
i
ng
blo
ck
s
an
d
su
r
ve
y
blo
cks
).
A
n
eng
a
ging
bl
oc
k
will
help
us
keep
our
stu
de
nts
in
a
daily
con
ta
ct
with
the
bot
s
yst
e
m
and
a
su
r
vey
blo
c
k
w
il
l
colle
ct
data
from
stud
ents
and
fill
in
the
su
r
vey
database
.
E
xa
m
ple
of
en
ga
ging
blo
c
ks
:
log
i
n
blo
c
k;
m
enu
of
op
ti
on
s;
un
i
ver
sit
y
ne
ws;
stu
dy
sc
hedule;
exam
ple
of
s
urvey
bl
ock
;
gr
a
du
at
e
s
urv
ey
or
quest
io
ns
a
nd
a
ns
we
rs
(
Q
&A
)
.
W
e
will
dig
dee
per
i
nto
ea
c
h
blo
c
k
a
nd g
i
ve a
f
lo
w of dial
og to
explai
n h
ow they ca
n
m
ake th
e
bot
ver
y
interesti
ng
for our
gr
a
duat
es.
Welcom
e
m
es
sage
The first t
hing
is t
o
greet
our
stud
e
nts
with a
si
m
ple w
el
co
m
e
m
essage.
It
s goal is al
so
t
o
e
xp
la
in t
he
r
ole
and
us
ef
uln
e
ss
of
the
bot.
Th
is
ty
pe
of
m
es
sage
m
akes
it
po
s
sible
to
est
ablish
a
bond
of
tr
us
t
betwee
n
th
e
su
pp
or
t
te
am
un
i
ver
sit
y
an
d
the
stu
de
nts
thr
ough
an
ex
change
of
ric
h
a
nd
c
onte
xt
ual
m
essages.
This
even
t
ually
m
a
kes
tra
ns
act
io
ns
easi
er
bet
we
en
stu
de
nts
an
d
unive
rsity
.
F
igure
3
s
hows
an
exam
ple
of
this
m
essage.
Lo
gin
blo
ck
The
bot
is
co
nn
ect
e
d
thr
ou
gh
a
pp
li
cat
io
n
program
m
ing
interface
(
A
PI
)
to
t
he
university
data
colle
ct
ion
platf
or
m
back
en
d
a
nd
ca
n
get
stu
den
ts
data
only
by
asking
for
it
.
In
or
der
to
connect,
we
ne
ed
t
o
p
r
ovide
tw
o
cr
eden
ti
al
s
the
na
ti
on
al
stud
e
nt
card
ide
ntific
at
ion
(
ID
)
an
d
the
s
tu
den
t
I
D.
At
first,
the
bo
t
asks
for
t
he
st
ud
e
nt
I
D
a
nd
if
no
r
esp
on
se
is
give
n,
stu
den
t
in
di
cat
es
wh
et
her
to
ca
ncel
lo
gin
an
d
go
t
o
the
m
ai
n
m
enu
or
retry
again.
I
f
the
st
ud
e
nt
ID
is
en
te
red
,
the
bot
will
request
for
the
natio
nal
I
D
a
nd
pe
rfor
m
log
i
n
ope
rati
on
by
c
al
li
ng
the
A
PI
functi
on
C
hec
kS
tu
de
nt().
If
al
l
go
es
well
,
a
ve
rificat
ion
m
essage
is
disp
l
ay
ed
to
the
stu
den
t
s
howing
his
fu
ll
nam
e,
degree,
unive
rsity
,
gr
a
duat
ion_ye
ar
a
nd
as
ks
the
st
udent
f
or
c
onfir
m
at
ion
if it
’
s tr
ue.
Fig
ur
e
3 sho
ws
t
he
log
i
n
flo
w.
Su
ccess
f
ully
co
nnect
ed
b
l
oc
k
Af
te
r
the
lo
gin
,
t
he
bot
sta
r
ts
by
ta
king
t
he
st
ud
e
nt
on
a
gu
i
ded
to
ur
of
t
he
diff
e
re
nt
a
vaila
ble
functi
onal
it
ie
s
su
c
h
as
c
hec
ki
ng
the
stu
dy
s
chedule,
exam
sche
dule
,
next
exam
date,
un
ive
rsity
and
week
ly
act
ivit
ie
s
.
As
sh
own
in
Fig
ur
e
4,
e
ach
opti
on
is
bac
ked
by
a
cal
l
to
an
A
PI
to
get
the
la
te
st
data.
T
he
s
tud
e
nt
can
c
hoos
e
to
op
e
n
t
he
m
ai
n
m
enu
if
no
ne
of
the
s
how
n
opti
ons
is
need
e
d.
We
will
ta
ke
the
st
ud
y
sc
he
du
l
e
functi
on
as
an
e
xam
ple,
if
the
stu
de
nt
wr
it
es
to
t
he
bot
one
of
t
he
fo
ll
owin
g
s
entences:
‘
My
stud
y
sche
du
le
’
,
’
study
sche
dule
’
,
’
my
sche
dule
’
the
bot
will
cal
l
the
API
functi
on
getStu
de
ntStud
ySc
he
du
le
()
wit
h
the
par
am
et
er
stud
e
ntI
D
(a
rgum
ents
are
omi
t
te
d
in
the
diag
ram
s
for
si
m
plific
at
ion
)
and
t
he
f
un
ct
i
on
will
r
et
urn
t
he
resu
l
t
in
Ja
vaScr
i
pt
obj
ect
no
ta
ti
on
(
JS
O
N
)
f
or
m
a
t
.
Figure
5
s
how
s
an
exam
ple
of
the
c
onvers
at
ion
flo
w
afte
r
respo
ns
e
f
rom
AP
I.
We
ca
n
see
that
the
chatb
ot
in
form
s
the
st
ud
e
nt
of
the
ne
xt
day'
s
sche
dule
.
He
al
so
as
ks
him
if
he
is
intere
ste
d
in
acce
ssing
the
le
arn
in
g
m
anag
em
ent
syst
e
m
for
t
he
c
ourse
m
at
erial
.
This
ultim
at
ely
facilit
at
es
transacti
on
s
bet
wee
n
st
ud
e
nts
and
t
he
uni
versi
ty
.
This
chat
bo
t
ca
n
pote
ntial
ly
extend
the
reach
a
nd
visi
bili
ty
of
the
un
iversity
.
It
will
al
so
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
En
gaging st
udents to
fi
ll
su
rv
eys us
i
ng chat
bo
ts
:
U
niversi
t
y case
stu
dy
(
Nad
ir
Belh
aj
)
477
i
m
pr
ove
the
qu
al
it
y
of
serv
ic
e
and
stre
ng
t
he
n
the
bond
of
m
e
m
ber
sh
ip
in
the
un
ive
rs
ity.
At
the
sa
m
e
tim
e,
it
will
increase
c
onve
rsions
a
nd
ha
ve
an
im
pact
on
stu
de
nt
sat
isfact
ion
.
-
Un
i
ver
sit
y ne
w
s b
l
ock
This
is
a
par
ti
c
ular
blo
c
k
of
s
ub
s
cripti
on
type
an
d
is
use
d
to
gi
ve
the
stu
de
nts
the
a
bili
ty
to
subsc
rib
e
to
updates
f
rom
their
un
ive
rs
it
y,
wh
ene
ver
s
om
et
hin
g
ne
w
happe
ns
the
B
ot
will
pop
up
with
so
m
e
news.
Th
e
bot
m
akes
it
ea
sy
to
un
s
ubscri
be
from
this
blo
ck
as
a
go
od
us
a
ge
patte
rn.
The
Fig
ur
e
6
be
low
sho
ws
how
the
su
bsc
ri
ption
is
i
m
ple
m
ented.
-
Gr
a
duat
e sur
ve
y bloc
k
This
is
the
m
os
t
i
m
po
rtant
blo
ck
,
beca
us
e
it
colle
ct
s
the
answ
ers
to
our
quest
io
ns
from
stud
e
nts
an
d
to
m
ake
it
an
easy
process,
we
de
velo
pe
d
a
new
bot
sur
veyi
ng
a
ppr
oa
ch
bas
ed
on
f
ree
facts,
whe
re
the
stud
e
nt
will
be
gi
ven
interest
i
ng
in
form
at
ion
ab
out
his
univ
ersit
y,
c
la
ss,
de
gr
ee
.
In
ret
urn,
the
stu
den
t
will
be
aske
d
to
gi
ve
his
opinio
n
to
e
nr
ic
h
the
ans
w
ers
database
.
F
igure
7
descr
i
be
s
the
key
ste
ps
in
t
his
pr
oces
s.
Figure
3. Co
nversati
o
n fl
ow of the
lo
gin
a
nd
welcom
e
m
ess
age
e
xam
ple
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.
2
4
, N
o.
1
,
Oct
o
ber
20
21
:
47
3
-
483
478
Figure
4. Co
nversati
on
fl
ow a
fter s
uccess
fu
l
connecti
on
Figure
5. Exa
m
ple o
f
the c
onve
rsati
on
flo
w
a
fter
respo
nse
f
r
om
A
PI
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
En
gaging st
udents to
fi
ll
su
rv
eys us
i
ng chat
bo
ts
:
U
niversi
t
y case
stu
dy
(
Nad
ir
Belh
aj
)
479
Figure
6. S
ub
s
cripti
on
blo
c
k
t
o
the
unive
rsit
y new
s
Figure
7.
Fr
ee
Fact
and s
urve
y conve
rsati
on
flo
w
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.
2
4
, N
o.
1
,
Oct
o
ber
20
21
:
47
3
-
483
480
-
Ma
in
m
enu
b
l
oc
k
The
m
ai
n
m
en
u
is
nee
ded
to
si
m
plify
the
acce
ss
for
in
for
m
at
ion
about
the
unive
rsity
and
dif
fer
e
nt
bot
f
un
ct
io
nali
ti
es.
It
giv
es
ac
cess
to
se
ver
al
ser
vices.
He
re
'
s
a
qu
ic
k
over
view
of
what
the
m
ai
n
m
enu
l
ooks
li
ke,
f
ro
m
a
stud
e
nt'
s
perspe
ct
ive.
T
he
below
Fi
gu
re
8
s
hows
how
the
co
nv
e
rsati
on
flo
w
of
t
he
m
enu
is
i
m
ple
m
ented.
Figure
8. Ma
in
m
enu
conv
e
rs
at
ion
flo
w
2.3.
Im
plem
e
nt
ing
the ch
at
bo
t
T
h
e
f
i
r
s
t
s
t
e
p
is
to
c
h
o
o
s
e
t
he
r
i
g
h
t
c
h
a
t
b
o
t
p
l
a
t
f
o
r
m
;
m
o
s
t
of
our
s
t
u
d
e
n
t
s
u
s
e
t
h
e
s
o
c
i
a
l
n
e
t
w
o
r
k
F
a
c
e
b
o
o
k
a
n
d
i
t
s
f
a
m
o
u
s
m
e
s
s
a
g
i
n
g
a
p
p
m
e
s
s
e
n
g
e
r
so
d
e
c
i
d
i
n
g
on
t
h
e
p
l
a
t
f
o
r
m
w
a
s
an
e
a
s
y
s
t
e
p
.
T
h
e
s
e
c
o
n
d
s
t
e
p
is
to
d
e
c
i
d
e
on
w
h
e
t
h
e
r
to
i
m
p
l
e
m
e
n
t
t
he
c
h
a
t
b
o
t
f
r
om
t
h
e
ground
up
or
u
s
e
an
o
n
l
i
n
e
s
e
r
v
i
c
e
.
In
our
c
a
s
e
,
we
u
s
e
d
t
h
e
C
h
a
t
f
u
e
l
s
e
r
v
i
c
e
w
h
i
c
h
m
a
k
e
s
it
e
a
s
y
to
c
r
e
a
t
e
a
r
u
l
e
s
-
b
a
s
e
d
c
h
a
t
b
o
t
.
In
a
d
d
i
t
i
o
n
,
t
h
e
c
h
a
t
b
o
t
o
f
f
e
r
s
a
f
u
l
l
y
i
m
p
l
e
m
e
n
t
e
d
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
s
y
s
t
e
m
t
h
a
t
m
a
k
e
s
it
e
a
s
y
to
c
o
n
f
i
g
u
r
e
k
e
y
-
p
h
r
a
s
e
s
a
n
d
c
o
r
r
e
s
p
o
n
d
i
n
g
bot
r
e
s
p
o
n
s
e
s
.
T
h
e
t
h
i
r
d
s
t
e
p
is
c
o
n
f
i
g
u
r
i
n
g
t
h
e
c
h
a
t
b
o
t
a
n
d
a
d
d
i
n
g
a
rtific
ia
l
intel
li
gen
ce
(
AI
)
r
u
l
e
s
.
A
p
p
l
y
i
n
g
AI
r
u
l
e
s
is
l
i
k
e
u
p
l
o
a
d
i
n
g
i
n
t
e
l
l
i
g
e
n
c
e
to
t
h
e
c
h
a
t
b
o
t
by
i
n
p
u
t
i
n
g
k
e
y
w
o
r
d
s
,
p
h
r
a
s
e
s
a
n
d
s
e
n
t
e
n
c
e
s
t
h
a
t
we
e
x
p
e
c
t
our
s
t
u
d
e
n
t
w
i
l
l
t
y
p
e
w
h
i
l
e
e
n
ga
g
i
n
g
in
t
h
e
c
on
v
e
r
s
a
t
i
o
n
.
F
i
gu
r
e
9
s
h
o
w
s
an
e
x
a
m
pl
e
of
t
h
i
s
AI
m
a
t
c
h
i
n
g
r
u
l
e
s
.
Figure
9. Exa
m
ple o
f
A
I ru
l
es
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
En
gaging st
udents to
fi
ll
su
rv
eys us
i
ng chat
bo
ts
:
U
niversi
t
y case
stu
dy
(
Nad
ir
Belh
aj
)
481
A
s
seen
in
this
exam
ple
we
i
nput
the
two
words
‘m
ark
s’
and
‘m
y
m
ark
s’
ex
pecti
ng
the
stud
e
nt
to
ty
pe
‘
wh
at
are
my
m
ark
s
?’
And
set
ti
ng
the
chat
bo
t
to
a
ns
we
r
bac
k
by
ty
ping
‘Let
me
chec
k
y
our
m
ark
s
’
wh
ic
h
tri
gg
e
rs
a
m
ark
sCheck
(
)
f
unct
io
n
that
looks
for
t
he
st
ud
e
nt
m
ark
s
on
the
database
and
ty
pe
t
hem
back.
This
AI
m
echan
ism
has
the
abili
ty
to
unde
rstan
d
la
ng
ua
ge
a
nd
al
so
le
anin
g
ca
pacit
y
by
disco
ver
i
ng
ne
w
patte
rn
s
a
nd
ge
tt
ing
sm
arter
wh
e
n
enc
ount
erin
g
m
or
e
situ
at
ions.
Ma
chi
ne
le
arn
i
ng
is
a
cor
e
com
pone
nt
of
chatb
ot
AI
by
le
arn
in
g
by
be
ing
ex
pose
d
to
a
lot
of
exam
ples,
w
he
n
a
chatb
ot
receives
an
input
pro
m
pt
it
analy
ses
the
prom
pt
and
unde
rstan
ds
co
ntext
t
o
form
the
cor
res
po
nd
i
ng
ou
t
pu
t.
Af
te
r
the
suc
cessf
ul
i
m
ple
m
entat
io
n
of
the
a
bove
co
nv
e
rsati
on
flo
ws
with
t
he
ap
pro
pr
ia
te
AI
r
ules.
We
gav
e
our
bot
a
nam
e
‘
Un
ive
rsity
Si
di
Mo
ham
ed
Be
n
Abdell
ah
’
and
an
a
vatar
im
age
‘
Un
ive
rsity
Lo
go
’
,
publis
hed
its
Fa
ceboo
k
pag
e
in
our
stu
den
ts
em
ailing
li
st,
and
aske
d
them
to
try
it
ou
t.
3.
RESU
LT
S
AND DI
SCUS
S
ION
In
this
sect
ion,
we
ou
tl
ine
the
resu
lt
s
of
so
m
e
pr
el
im
inary
exp
e
rim
ents
carried
on
in
orde
r
to
exp
l
or
e
the
feasi
bili
ty
of
our
c
hatb
ot
as
a
new
su
r
vey
m
et
ho
d
to
overc
ome
on
li
ne
s
urve
y
’
s
co
ns
trai
nt
caus
e
d
par
ti
cula
rly
by
stu
den
ts
’
inatt
ention
an
d
la
c
k
of
com
m
i
t
m
ent.
To
t
his
e
nd,
we
c
om
par
e
the
us
er
ex
pe
r
ie
nce
of
a
chatbo
t
quest
ionnaire,
with
a
sta
nd
ar
d
we
b
su
r
vey.
More
detai
ls
for
this
stud
y
will
be
the
subj
ect
of
a
fut
ure
publica
ti
on.
Br
ie
fly
,
the
pr
el
i
m
inary
stud
y
exp
e
rim
ent
was
cond
ucted
for
stu
den
ts
fro
m
national
sch
oo
l
of
app
li
ed
sci
e
nc
es
stud
e
nts
at
Sidi
Moh
am
ed
Be
n
Abdell
ah
Un
ive
rsity
in
Mor
occo
for
a
per
io
d
of
3
m
on
t
hs
.
Be
cause
of
the
absen
ce
of
previo
us
resea
rc
h
on
this
to
pic
,
init
ia
ll
y,
it
was
app
li
ed
to
a
pilot
sam
ple
of
only
70
st
ud
e
nts
an
d
grad
uates
co
m
bin
ed
with
the
ai
m
of
m
o
ving
to
a
la
rg
e
r
sam
ple
of
stud
e
nts
sprea
d
acros
s
sever
al
M
oroc
can
un
i
ver
sit
ie
s
in
t
he
c
om
in
g
m
on
ths
.
F
or
et
hical
co
ns
ide
rati
on
s
,
al
l
in
f
or
m
at
ion
co
nc
ern
i
ng
par
ti
ci
pa
nts
is
anonym
ou
sly
and
c
onfide
nt
ia
lly.
The
co
m
pu
te
r
proces
sing
of
data
is
not
pe
rs
on
al
.
The
transm
issi
on
of
in
form
at
ion
for
e
xp
e
rtise
or
f
or
sci
e
ntif
ic
publica
ti
on
is
al
so
a
nony
m
ou
s.
Data
a
naly
sis
pr
im
aril
y
con
s
ist
ed
of
de
sc
ri
ptive
sta
ti
sti
cs.
All
of
par
ti
ci
pated
in
our
stud
y
ha
ve
ex
pe
rience
d
a
web
su
r
vey
and
are
us
i
ng
Faceb
ook
m
essen
ger.
We
e
sta
blished
a
c
hatb
ot
quest
io
nn
ai
re
wit
h
sa
m
e
qu
est
io
ns
to
the
tradit
ion
al
c
om
pu
te
r
versi
on.
T
he
onli
ne
survey
data
was
c
ollec
te
d
from
s
tud
ent
s
by
em
ai
l
us
ing
t
heir
academ
ic
add
r
esses
an
d
f
ollo
wed
by
te
le
phon
e
rem
ind
ers
in
orde
r
to
rea
ch
a
la
rg
e
r
ta
r
get
of
grad
uate
s.
The
stud
e
nts
wer
e
aske
d
to
fill
both
the
c
hatb
ot
and
sta
ndar
d
w
eb
s
urveys
a
nd
then
,
they
pro
vid
e
d
thei
r
fee
db
a
c
k
after
ab
out
the
us
er
e
xp
e
rien
ce.
Seve
ral
fac
tors
we
re
ta
ke
n
into
acc
ount
to
evaluate
thi
s
stud
y
inclu
di
ng
the
diff
e
re
nce
in
s
cor
e
betwee
n
the
two
m
et
ho
ds
and
t
he
tim
e
to
com
plete
a
qu
e
sti
onnaire
.
The
sc
or
e
is
ba
sed
on
sever
al
it
em
s
(20
it
em
s
in
total
ly
),
for
e
xam
ple,
rap
i
d,
at
tract
ive,
an
d
interest
ing.
In
total
,
1440
(
20
70
)
te
rm
s
wer
e
sco
red.
This
prel
im
inary
ex
per
im
ent
est
ablish
that
t
he
m
ajo
rity
of
stud
e
nts
s
urve
ye
d
prefe
r
to
be
con
ta
ct
e
d
thr
ough
chatb
ot
interact
ive
discuss
i
on
cha
nn
el
s
w
he
n
th
ey
are
avail
able,
com
p
ared
to
oth
e
r
tradit
ion
a
l
channels,
s
uch
as
te
le
ph
on
e
or
e
-
m
ai
l.
Af
te
r
la
un
c
hing
a
first
sp
ri
nt
of
te
sts
in
a
gr
oup
of
70
stu
de
nt
s
and
gr
a
duat
es
com
bin
e
d,
we
obta
ined
this
first
r
esult
.
T
able
1
s
hows
the
res
ult
of
our
fi
rst
te
st
in
a
per
i
od
of
thre
e
consecuti
ve
w
eeks,
a
nd
we
c
an
cl
early
see
that
m
or
e
stude
nts
prefe
rr
e
d
us
in
g
the
bot
a
nd
are
e
ngage
d
in
it
s
us
e.
Stu
de
nts
pr
e
ferred
the
s
ta
nd
a
rd
c
om
pu
te
r
for
9%
(
129.6/1
440)
of
t
he
te
rm
s;
76%
(1
09
4.4/1
440)
of
al
l
te
rm
s
wer
e
sco
red
posit
ive
for
the
chat
bo
t
a
nd
f
or
15%
(
216/
1440)
of
the
te
rm
s
there
wer
e
no
dif
fere
nces.
In
add
it
io
n,
fill
ing
in
t
he
quest
i
onnaire
t
hro
ugh
the
c
hatb
ot
is
faster
th
an
t
he
sta
nd
a
r
d
we
b
su
r
vey.
Re
gard
ing
t
he
com
pleti
on
(average
ti
m
e)
of
the
qu
est
i
onnai
re,
the
ave
rag
e
tim
e
to
co
m
pl
et
e
the
web
survey
took
8
m
i
nu
te
s
against
7.5
m
inu
te
s
for
the
cha
tbo
t
qu
e
sti
onna
ire
as
s
how
n
in
Table
2.
Table
1.
A
ver
a
ge
sc
or
e
p
e
r
te
r
m
in the two m
et
hods
Su
rvey
Metho
d
Pref
erences
Stan
d
ard web su
rvey
Ch
atb
o
t qu
estionnair
e
No
dif
f
erences
Pref
erence: it
e
m
s
s
co
red p
o
sitiv
e of
all
ter
m
s
(12
9
.6/1
4
4
0
)
9
%
(10
9
4
.4/144
0
)
7
6
%
(21
6
/1
4
4
0
)
1
5
%
Table
2.
A
ver
a
ge
ti
m
e to co
m
pleti
on
i
n
t
he
t
wo m
et
ho
ds
Su
rvey
Metho
d
Co
m
p
letio
n
Stan
d
ard web su
rvey
Ch
atb
o
t qu
estionnair
e
Co
m
p
letio
n
(
m
ean
ti
m
e
)
(
m
in
u
tes b
y
stu
d
en
t)
8
7
.5
Finall
y,
we
ha
ve
s
how
n
t
he
e
ff
ect
ive
ness
of
our
ap
proac
h
by
a
c
om
par
at
ive
data
st
ud
y
betwee
n
t
he
tradit
ion
al
onli
ne
s
urvey
a
nd
the
us
e
of
this
chatb
ot.
T
he
r
esults
co
nf
i
rm
that
stu
den
ts
prefe
rr
e
d
the
ch
at
bot
qu
e
sti
onnaire
to
the
sta
nda
rd
web
s
urvey
ac
cordin
g
to
this
stud
y.
This
res
ult
seem
s
ver
y
interest
ing
bec
ause
it
al
lows
us
to
predict
a
hi
gh
qual
it
at
ive
response
rate
in
f
utur
e
chatb
ot
s
urve
ys.
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.
2
4
, N
o.
1
,
Oct
o
ber
20
21
:
47
3
-
483
482
4.
CONCL
US
I
O
N
We
ha
ve
pr
e
s
ented
a
c
om
pr
ehensi
ve
c
hatb
ot
fr
am
ework
to
en
gage
stu
de
nts
to
a
ns
w
er
un
i
ver
sit
y
s
urvey
qu
est
io
ns
.
We
s
epa
r
at
ed
the
c
onve
rsati
on
fl
ow
s
into
t
wo
dif
f
eren
t
blo
c
ks
c
al
le
d
en
gag
i
ng
a
nd
su
r
veyi
ng
bl
oc
ks
a
nd
t
hen
we
m
ade
the
an
swer
i
ng
proce
ss
fact
dri
ve
n
wh
e
re
the
st
udent
gets
inter
est
ing
inf
or
m
at
ion
ab
ou
t
his
unive
rs
it
y,
his
own
c
ourse
stu
dy
an
d
career
c
hoic
es.
In
retu
rn,
we
a
sk
e
d
him
to
prov
i
de
his
opini
on
an
d
fee
dback
ab
out
two
m
et
ho
ds
of
s
urveys
an
d
by
ap
plyi
ng
arti
fici
al
intel
lig
ence
r
ules
we
m
ade
it
s
m
arter
by
unde
rstan
ding
di
ff
ere
nt
w
ords
,
phrases
a
nd
se
ntences
.
In
f
ut
ur
e
,
this
arti
cl
e
cou
l
d
f
orm
basis
for
bu
il
di
ng
a
sm
arter
c
hatb
ot
with
se
nti
m
ent
analy
sis
capa
bili
ty
to
bette
r
unde
rstan
d
hum
ans
i
nteracti
on
s
an
d
trigg
e
r
quest
io
ns
base
d
on
st
ud
e
nts
en
ga
ge
m
ent
and
be
ha
vior,
an
d
al
so
m
ake
us
e
of
e
m
oj
is
to
un
de
r
sta
nd
them
and
an
sw
er
ba
ck
us
i
n
g
the
ri
ght
em
oj
i
dep
e
ndin
g
on
the
sit
uatio
n.
To
m
ake
us
e
of
t
he
c
ollec
te
d
da
ta
this
chatb
ot
can
al
so
se
nd
data
t
hro
ugh
e
ven
ts
us
in
g
a
pach
e
Kafka
to
ha
ve
bette
r
an
al
yt
i
cs
an
d
integ
rat
e
with
oth
e
r
stream
s
of
data
f
or
bette
r
decisi
on
m
aking
.
ACKN
OWLE
DGE
MEN
TS
This
w
ork
on
t
his
pa
per
was
su
pp
or
te
d
by
the
Sidi
Mo
ha
m
ed
Be
n
A
bd
e
ll
ah
Un
i
ver
sit
y
of
Mo
r
occ
o
and m
or
e p
a
rtic
ularly
b
y i
ts P
reside
nt and t
he
d
irect
or
of th
e n
at
io
nal sc
hool of a
ppli
ed
sc
ie
nces.
REFERE
NCE
S
[1]
H.
F.
Barbe
r,
“
Deve
lop
ing
Strat
e
gic
Leade
rship
:
The
US
Arm
y
W
ar
Coll
ege
Ex
per
ie
n
ce
,”
Journ
al
of
Manage
me
nt
Dev
el
opmen
t
,
v
o
l.
11
,
n
o.
6,
pp
.
4
-
12
,
1992
,
doi
:
1
0.
1108/0262171
9210018208,
19
92.
[2]
W.
G.
Benn
is
an
d
B.
N
anus
,
Lea
ders:
Strate
gi
es
for
Taking
Char
ge
,
N
ew
York,
USA:
Harpe
r
&
Row,
1986.
[3]
E.
San
tha
nam
,
B.
L
y
n
ch,
and
J.
Jones,
“
Maki
ng
sense
of
stu
de
nt
f
ee
dba
ck
using
te
xt
anal
y
sis
-
ada
p
ti
ng
an
d
expa
nding
a
co
m
m
on
le
xic
on,
”
Qualit
y
Assur
ance
in
Edu
cat
ion
,
v
ol.
26
,
n
o.
1,
pp.
60
-
69
,
2018,
d
oi:
10.
1108/QA
E
-
11
-
2016
-
0062
.
[4]
D.
U.
Boll
ige
r
and
F.
Mart
in
,
“
F
ac
tors
unde
rl
y
ing
th
e
per
c
ei
ved
importance
of
onli
n
e
stu
dent
eng
age
m
en
t
strat
eg
ie
s
,”
Jou
rnal
of
Appl
i
e
d
Re
search
in
Higher
Edu
c
ati
on
,
v
ol.
13
,
n
o.
2,
pp
.
404
-
419
,
2021
,
doi:
10
.
1108/JARH
E
-
02
-
2020
-
0045
.
[5]
Z.
Mansouri,
“A
look
at
unive
rsi
t
y
dropou
t
in
Morocc
an
high
er
e
duca
t
ion,
”
The
J
ournal
of
Quality
in
Educ
a
ti
on
,
vol.
7
,
no
.
9,
p.
2
7,
2017
,
doi
:
10
.
37870/j
oqie.v7i
9
.
11
.
[6]
M.
Soum
a
y
a
,
B.
Julie
,
C.
Ma
rgu
eri
t
e,
F.
Eliz
abe
t
h,
K.
Hann
ah,
a
nd
M.
Isobel
,
“
OECD
Revi
ews
of
the
Educat
ion
As
sessment
Fram
ework:
Morocc
o
in
Fr
en
ch
Ex
amens
de
l
'
OCD
E
du
c
adr
e
d
'év
al
ua
ti
on
de
l
'
éd
u
ca
t
ion
:
Maro
c
,”
Paris,
Franc
e:
OCD
E
Publ
ishin
g
,
2018
,
doi
:
10
.
1787/9789264301832
-
fr.
[7]
R
.
Bourqia
,
“
Ret
hinki
ng
and
r
e
buil
ding
schools
in
Morocc
o:
the
Strat
egic
Vision
2015
-
2030
in
Frenc
h:
Repe
nse
r
et
ref
ond
er
l’
école
au
Maro
c
:
la
Vision
stratégique
2015
-
20
30,
”
R
ev
u
e
Inter
nati
onale
d’
éd
ucat
ion
de
Sèv
r
es
,
p
p
.
18
-
24
,
2016
,
doi:
10.
4000
/ri
e
s.4551
.
[8]
E
.
Adam
opoulo
u
and
L
.
Mous
siade
s,
“
Chat
bots
:
Histor
y
,
t
ec
hn
olog
y
,
and
appl
i
ca
t
ions,”
Mac
hi
ne
Learning
w
ith
Appl
ic
a
ti
ons
,
vo
l.
2,
2020
,
do
i:
1
0.
1016/j.m
lwa.
2
020.
100006
.
[9]
R.
De
Cic
co
,
S.
C.
Silva
,
and
F.
R.
Alpar
one
,
“
Mill
ennials
'
attitude
towar
d
chat
bots:
an
expe
ri
m
ent
al
stud
y
in
a
socia
l
re
la
t
ionship
per
spec
t
ive
,
”
Inte
rnational
J
ournal
of
Re
tai
l
&
D
istribut
ion
Manage
ment
,
v
ol.
48
,
n
o.
11,
pp.
1213
-
1233
,
2020,
doi
:
10
.
11
08/IJRDM
-
12
-
2
019
-
0406
.
[10]
J.
Vincz
e
,
“
Virtua
l
ref
ere
n
ce
l
ibra
ri
ans
(Chat
b
ots),
”
Libr
ary
Hi
Tech
News
,
v
ol.
34
,
n
o.
4,
pp.
5
-
8.
2017
,
doi:
10
.
1108/L
H
TN
-
03
-
2017
-
0016
.
[11]
R
.
Suto
y
o,
A
.
C
howanda
,
A
.
Ku
rnia
ti,
and
R
.
W
ongso,
“
Designing
an
Emotion
all
y
Realistic
Ch
atbot
Fram
ework
to
Enha
nc
e
Its
Bel
i
eva
bi
li
t
y
with
A
IML
and
Inform
at
ion
States,”
Pr
oce
dia
Compute
r
Sci
enc
e
,
vol.
1
57,
pp.
621
-
628,
2019
,
doi
:
10
.
10
16/j
.
pro
cs.
2019.
08.
226
.
[12]
J.
Gikas
and
M.
M.
Grant
,
“
Mobile
computing
devi
c
es
in
h
igher
educat
ion
:
Stu
dent
p
erspe
ctive
s
on
learni
ng
wi
th
ce
l
lphone
s,
sm
art
phones
&
soc
ia
l
m
edi
a
,
”
Th
e
Inte
rnet
and
Higher
Educ
a
ti
on
,
vol
.
19
,
pp.
18
-
26,
201
3,
doi:
10
.
1016/j.ih
educ
.
2013
.
06.
00
2
.
[13]
E.
Adam
opoulo
u
and
L.
Mous
siade
s
,
“
An
Over
vie
w
of
Chat
bo
t
Te
chno
log
y
,
”
I
FIP
Ad
vances
in
Information
an
d
Comm
unic
ati
on
Technol
ogy
,
vo
l
.
584
,
pp.
373
-
38
3,
2020
,
doi
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
030
-
4
9
1
8
6
-
4
_
3
1
.
[14]
H.
Bansal
and
R.
Khan,
“
Review
pape
r
on
hum
an
computer
int
eract
ion
,
”
Int
.
Journal
of
Adv
a
nce
d
Re
search
in
Computer
Scien
ce
and
Sof
tware
Engi
ne
ering
,
vol
.
8
,
no
.
4
,
pp
.
53
-
58,
2018
,
doi
:
1
0.
23956/i
j
arc
ss
e
.
v8i4.
630
.
[15]
P.
Sm
utny
and
P
.
Schre
ibe
rov
a,
“
Chat
bots
for
le
arn
ing
:
A
rev
ie
w
of
educat
iona
l
Chat
bo
ts
for
the
Face
boo
k
Mess
enge
r,
”
Co
mputers
and
Ed
ucat
ion
,
vol
.
151
,
2020
,
doi
:
10
.
1
016/j
.
compedu.
2
020.
103862
.
[16]
S
.
Chakra
bort
y
,
“
Chat
bots
and
its
impact
on
user
expe
rie
n
ce,”
Ps
yc
holog
y
and
E
ducat
ion
Journa
l
,
vol.
57
,
no.
9,
2020
,
doi
:
10
.
17
762/pa
e
.
v57i9
.
1
610
.
[17]
A.
B.
Shawar
and
E
.
Atwell.
“
Chat
bots:
Ar
e
they
R
eall
y
Us
efu
l
?
,
”
Journ
al
for
Languag
e
Technol
ogy
a
nd
Computati
onal
L
ingui
stic
s
,
vol
.
2
2,
no
.
1,
pp
.
29
-
49
,
2007
.
[18]
J
.
K
.
Gupta1
an
d
S
.
Agarwal
,
“
An
Epi
tome
of
Chat
bot:
A
Rev
ie
w
Paper
,”
Int
e
rnational
Journ
al
of
Computer
Sci
en
ce
s
and
En
gine
ering
,
vol
.
7,
no
.
1
,
pp
.
633
-
636,
2019
,
doi
:
1
0.
26438/i
j
cse
/v7
i1.
633636
.
Evaluation Warning : The document was created with Spire.PDF for Python.