T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n,
Co
m
pu
t
ing
,
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
18
,
No
.
4
,
A
u
g
u
s
t
2020
,
p
p
.
18
19
~
1
8
2
7
I
SS
N:
1
6
9
3
-
6
9
3
0
,
ac
cr
ed
ited
First Gr
ad
e
b
y
Ke
m
e
n
r
is
te
k
d
i
k
ti,
Dec
r
ee
No
: 2
1
/E/KPT
/2
0
1
8
DOI
:
1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
KA
.
v
1
8
i4
.
1
4
1
7
9
1819
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
Ana
ly
sis
senti
m
e
nt
a
bo
ut
isla
m
o
p
ho
bia
w
hen
Christchu
rch
a
t
ta
ck on so
cia
l
m
edi
a
Wind
u G
a
t
a
,
Ach
m
a
d B
a
y
ha
qy
M
a
ste
r
o
f
Co
m
p
u
ter S
c
ien
c
e
-
P
o
st
g
ra
d
u
a
te P
r
o
g
ra
m
s,
S
T
M
IK Nu
sa
M
a
n
d
ir
i
Ja
k
a
rta,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
2
2
,
2
0
1
9
R
ev
i
s
ed
Feb
2
8
,
2
0
2
0
A
cc
ep
ted
A
p
r
1
3
,
2
0
2
0
Isla
m
o
p
h
o
b
ia
is
f
o
rm
e
d
b
y
"
Isl
a
m
"
w
it
h
"
-
p
h
o
b
ia"
w
h
ich
m
e
a
n
s
"
f
e
a
r
o
f
Isla
m
"
.
T
h
is
sh
o
w
s
th
e
v
ie
w
o
f
Isla
m
a
s
"
o
th
e
r"
a
n
d
c
a
n
th
re
a
te
n
W
e
ste
rn
c
u
lt
u
re
.
T
h
e
re
c
e
n
t
h
o
rrif
ic
terro
r
a
tt
a
c
k
th
a
t
to
o
k
p
lac
e
a
t
th
e
Ch
ristch
u
rc
h
m
o
sq
u
e
in
Ne
w
Ze
a
lan
d
,
is
th
e
re
su
lt
o
f
a
ll
o
w
in
g
a
n
a
tt
it
u
d
e
o
f
h
a
tred
to
w
a
rd
s
Isla
m
in
th
e
W
e
st.
Tw
i
tt
e
r
is
so
c
ial
m
e
d
ia
th
a
t
a
ll
o
w
s
u
se
rs
se
n
d
re
a
l
-
ti
m
e
m
e
ss
a
g
e
s
a
n
d
c
a
n
b
e
u
se
d
f
o
r
se
n
ti
m
e
n
t
a
n
a
l
y
sis
b
e
c
a
u
se
it
h
a
s
a
larg
e
a
m
o
u
n
t
o
f
d
a
ta.
T
h
e
lex
ica
l
b
a
se
d
m
e
th
o
d
u
si
n
g
V
A
DER
is
u
se
d
f
o
r
a
u
to
m
a
ti
c
lab
e
li
n
g
o
f
c
ra
w
li
n
g
d
a
ta
f
ro
m
Tw
it
ter.
A
n
d
t
h
e
n
c
o
m
p
a
re
s
u
p
e
rv
ise
d
m
a
c
h
in
e
lea
rn
in
g
N
a
ïv
e
B
a
y
e
s
a
n
d
S
V
M
a
lg
o
rit
h
m
.
Ad
d
it
i
o
n
o
f
S
M
OT
E
f
o
r
i
m
b
a
lan
c
e
d
d
a
ta
.
A
s
re
su
lt
,
S
V
M
w
it
h
S
M
OT
E
is
p
ro
v
e
n
th
e
h
ig
h
e
st
p
e
rf
o
rm
a
n
c
e
v
a
lu
e
a
n
d
sh
o
rt
p
ro
c
e
ss
in
g
ti
m
e
.
K
ey
w
o
r
d
s
:
C
h
r
i
s
tch
u
r
ch
at
tack
I
s
la
m
o
p
h
o
b
ia
Naïv
e
B
a
y
es
SMOT
E
SVM
VADE
R
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r
th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
A
c
h
m
ad
B
ay
h
aq
y
,
Ma
s
ter
o
f
C
o
m
p
u
ter
Scie
n
ce
-
P
o
s
tg
r
ad
u
ate
P
r
o
g
r
am
s
,
ST
MI
K
Nu
s
a
Ma
n
d
ir
i
,
Kr
a
m
at
R
a
y
a
No
.
1
8
,
Ko
ta
J
ak
ar
ta
P
u
s
at,
DKI
J
ak
ar
ta
,
I
n
d
o
n
esia.
E
m
ail:
ac
h
m
ad
b
a
y
h
aq
y
9
2
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
No
w
ad
a
y
s
,
w
ith
t
h
e
r
ap
id
d
e
v
elo
p
m
e
n
t
o
f
tech
n
o
lo
g
y
,
an
y
th
i
n
g
ca
n
b
e
d
o
n
e
m
o
r
e
p
r
ac
ticall
y
an
d
ea
s
il
y
.
T
h
e
p
o
s
iti
v
e
i
m
p
ac
t
o
f
th
e
i
n
ter
n
et
i
n
t
h
e
d
ev
e
lo
p
m
e
n
t
o
f
I
T
ac
tu
all
y
b
r
in
g
s
m
a
n
y
b
en
ef
it
s
.
Ho
w
e
v
er
,
th
er
e
is
a
n
eg
a
tiv
e
i
m
p
ac
t
o
n
i
ts
d
ev
elo
p
m
en
t.
Fo
r
ex
a
m
p
le,
w
h
e
n
s
p
r
ea
d
in
g
f
al
s
e
n
e
w
s
o
r
ex
p
r
ess
i
n
g
h
a
tr
ed
.
B
y
u
s
i
n
g
t
h
e
w
eb
,
i
t c
a
n
s
tr
en
g
th
e
n
id
ea
s
a
n
d
o
p
in
io
n
s
i
n
a
g
r
o
u
p
o
r
i
n
d
iv
id
u
al.
I
t
'
s
m
ea
n
th
e
h
ate
s
p
ee
ch
also
ca
n
f
i
n
d
f
er
ti
le
g
r
o
u
n
d
o
n
ce
r
tain
w
eb
s
ite
s
an
d
s
o
cial
m
ed
ia
[
1
]
.
E
u
r
o
p
ea
n
r
ig
h
t
-
w
i
n
g
a
n
d
r
ac
i
s
t
m
o
v
e
m
en
t
s
,
o
f
te
n
u
s
e
d
i
g
it
al
s
p
ac
e
as
a
p
r
ef
er
r
ed
p
lace
to
s
p
r
ea
d
th
eir
m
e
s
s
a
g
e
an
d
r
ec
r
u
it
n
e
w
m
e
m
b
er
s
[2
,
3]
.
T
h
e
y
o
f
te
n
s
p
r
ea
d
r
ac
is
m
o
n
th
e
w
eb
an
d
also
co
n
tr
ib
u
te
i
n
s
p
r
ea
d
in
g
t
h
e
i
m
a
g
e
o
f
I
s
la
m
th
at
’
s
d
i
f
f
er
en
t
w
i
th
th
e
v
al
u
e
s
o
f
w
e
s
ter
n
.
T
h
is
co
u
ld
lead
to
p
h
y
s
ica
l
ac
tio
n
s
ag
ain
s
t
M
u
s
li
m
s
[
4
]
.
I
s
la
m
o
p
h
o
b
ia
co
m
es
f
r
o
m
th
e
w
o
r
d
s
"
I
s
la
m
"
an
d
"
p
h
o
b
ia
"
w
h
ich
m
ea
n
s
"
f
ea
r
o
f
s
o
m
et
h
i
n
g
ab
o
u
t
I
s
la
m
"
an
d
it
s
h
o
w
s
a
v
ie
w
o
f
I
s
la
m
w
h
ic
h
w
ill
th
r
ea
te
n
t
h
e
cu
lt
u
r
e
o
f
w
ester
n
.
I
f
w
e
tr
ac
e
b
ac
k
to
E
u
r
o
p
e
1
4
ce
n
t
u
r
ies
ag
o
,
th
at
w
a
s
o
n
e
a
m
o
n
g
th
e
r
esu
lts
o
f
th
e
"
o
r
ien
talis
m
"
o
f
th
e
A
r
ab
w
o
r
ld
.
I
n
r
ec
en
t
ti
m
es,
t
h
e
ter
m
i
s
la
m
o
p
h
o
b
ia
h
a
s
b
eg
u
n
to
r
ea
p
p
ea
r
in
co
n
n
ec
tio
n
w
it
h
th
e
"
war
o
n
ter
r
o
r
"
d
u
e
to
th
e
ter
r
o
r
is
t
attac
k
s
th
a
t
to
o
k
p
lace
o
n
Sep
te
m
b
er
1
1
,
2
0
0
1
,
w
h
ic
h
h
av
e
n
eg
at
iv
e
s
o
cial
p
er
ce
p
tio
n
s
ab
o
u
t
I
s
la
m
[
5
]
.
T
h
er
e
is
a
s
tu
d
y
o
f
i
s
la
m
o
p
h
o
b
ia
co
n
d
u
cted
b
y
th
e
B
r
itis
h
as
s
o
ciatio
n
[
6
]
w
h
ich
ai
m
s
to
f
ig
h
t
an
ti
-
Mu
s
li
m
cr
i
m
e
an
d
also
f
in
d
t
h
at
v
icti
m
s
u
s
u
all
y
e
x
p
er
ien
ce
h
ar
a
s
s
m
e
n
t,
b
o
th
o
n
lin
e
a
n
d
o
f
f
li
n
e.
R
ec
en
t
l
y
,
w
o
r
ld
lead
er
s
a
n
d
h
u
m
a
n
r
i
g
h
ts
i
n
s
tit
u
tio
n
s
as
s
ess
ed
t
h
e
h
o
r
r
if
ic
ter
r
o
r
attac
k
s
t
h
at
o
cc
u
r
r
ed
at
th
e
t
w
i
n
m
o
s
q
u
e
i
n
C
h
r
i
s
tc
h
u
r
ch
,
Ne
w
Z
ea
la
n
d
,
w
h
er
e
ter
r
o
r
is
ts
h
av
e
k
il
led
4
9
p
eo
p
le
an
d
in
j
u
r
ed
at
least
4
8
o
th
er
s
,
ar
e
th
e
ef
f
ec
t
s
o
f
all
o
w
i
n
g
a
n
attit
u
d
e
o
f
h
a
tr
ed
to
w
ar
d
s
I
s
la
m
(
I
s
la
m
o
p
h
o
b
ia)
in
th
e
w
est
[
7
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
18
1
9
-
1
8
2
7
1820
A
cc
o
r
d
in
g
to
[
8
]
,
in
h
ate
s
p
e
ec
h
o
n
lin
e
t
h
er
e
’
s
a
d
if
f
er
en
c
e
f
r
o
m
o
f
f
li
n
e
ab
u
s
e
du
e
to
t
h
e
i
n
ter
n
et
th
er
e
’
s
an
o
n
y
m
i
t
y
,
r
elati
v
el
y
ch
ea
p
an
d
ea
s
y
ac
ce
s
s
,
lack
o
f
p
h
y
s
ical
p
r
ese
n
ce
,
an
d
esp
ec
iall
y
s
p
o
n
tan
e
it
y
.
On
e
b
r
an
c
h
o
f
r
esear
c
h
th
a
t
later
d
ev
elo
p
ed
f
r
o
m
th
e
in
f
o
r
m
atio
n
ex
p
lo
s
io
n
s
it
u
atio
n
o
n
th
e
i
n
ter
n
et
is
s
en
ti
m
e
n
t
an
a
l
y
s
is
.
Se
n
t
i
m
e
n
t
an
al
y
s
is
o
r
also
ca
lled
o
p
in
io
n
m
i
n
in
g
is
a
f
ield
o
f
s
t
u
d
y
t
h
at
an
al
y
ze
s
s
en
ti
m
e
n
ts
,
o
p
in
io
n
s
,
atti
tu
d
e
s
,
e
m
o
tio
n
s
,
e
v
al
u
atio
n
s
,
a
n
d
j
u
d
g
m
e
n
ts
p
eo
p
le'
s
ab
o
u
t
a
s
er
v
ice,
p
r
o
d
u
ct,
in
d
iv
id
u
al,
o
r
g
an
izatio
n
,
ev
en
t,
to
p
ic,
attr
ib
u
te,
an
d
p
r
o
b
lem
[
9
]
.
On
e
o
f
th
e
So
cial
m
ed
ia
lik
e
T
w
itter
allo
w
s
u
s
er
s
to
b
e
ab
le
to
s
en
d
m
es
s
ag
e
s
in
r
ea
l
-
ti
m
e.
O
n
th
e
o
th
er
h
an
d
,
d
ata
m
i
n
in
g
is
a
m
et
h
o
d
f
o
r
f
in
d
in
g
k
n
o
w
led
g
e
i
n
d
atab
ases
to
f
in
d
u
s
e
f
u
l
k
n
o
w
led
g
e
f
r
o
m
d
ata.
T
h
is
is
th
e
p
r
o
ce
s
s
o
f
g
etti
n
g
attr
ac
ti
v
e,
s
er
v
icea
b
le
d
esi
g
n
s
an
d
r
elati
o
n
s
h
ip
s
i
n
lar
g
e
v
o
lu
m
e
s
o
f
d
ata.
T
h
u
s
d
ata
m
in
i
n
g
ca
n
b
e
u
s
ed
f
o
r
s
e
n
ti
m
e
n
t
an
al
y
s
is
b
ec
a
u
s
e
it
h
as a
lar
g
e
a
m
o
u
n
t o
f
T
w
it
ter
d
ata.
As
in
p
r
ev
io
u
s
r
esear
ch
th
at
d
is
cu
s
s
e
s
s
en
t
i
m
e
n
t
an
a
l
y
s
is
w
i
th
v
ar
io
u
s
th
e
m
es
s
u
c
h
as
I
s
la
m
o
p
h
o
b
ia
o
n
f
ar
-
r
ig
h
t
UK
p
o
liti
ca
l
p
ar
ties
,
I
s
la
m
o
p
h
o
b
ic
b
eh
a
v
io
r
af
ter
#
P
ar
is
Attack
s
,
elec
tio
n
r
esu
lt
p
r
ed
ictio
n
s
,
e
-
co
m
m
er
ce
,
co
n
s
u
m
er
r
e
v
ie
w
s
a
n
d
alg
o
r
it
h
m
e
v
al
u
atio
n
s
.
I
n
t
h
at
r
e
s
ea
r
ch
,
Naï
v
e
B
a
y
es
an
d
th
e
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
alg
o
r
ith
m
h
a
v
e
th
e
b
est
a
v
er
a
g
e
clas
s
i
f
icatio
n
r
es
u
lt
s
i
n
s
en
ti
m
e
n
t
a
n
al
y
s
is
.
I
n
t
h
e
elec
tio
n
r
es
u
lt
p
r
ed
ictio
n
r
esear
ch
,
th
e
y
ap
p
lied
v
alen
ce
a
w
ar
e
d
ict
io
n
ar
y
an
d
s
en
ti
m
e
n
t
r
ea
s
o
n
er
(
VA
DE
R
)
to
lab
elin
g
t
h
e
tr
ain
in
g
d
ataset.
A
n
d
also
,
if
th
er
e
is
a
d
ata
im
b
ala
n
ce
,
in
th
e
ev
alu
a
tio
n
r
esear
c
h
s
en
ti
m
e
n
t a
n
al
y
s
is
al
g
o
r
ith
m
u
s
es t
h
e
s
y
n
t
h
etic
m
i
n
o
r
it
y
o
v
er
s
a
m
p
li
n
g
tech
n
iq
u
e
(
SM
OT
E
)
to
b
alan
ce
it.
In
th
i
s
r
esear
ch
,
w
ill
b
e
d
is
c
u
s
s
ed
ab
o
u
t
h
o
w
to
d
o
s
en
t
i
m
en
t
an
al
y
s
is
d
er
iv
ed
f
r
o
m
T
w
i
t
ter
u
s
er
t
w
ee
t
s
ab
o
u
t
I
s
la
m
o
p
h
o
b
ia.
I
d
ea
s
an
d
p
u
b
lic
o
p
in
io
n
v
ia
T
w
itter
in
lar
g
e
n
u
m
b
er
s
,
at
least
b
e
ab
le
to
an
al
y
ze
g
lo
b
all
y
ab
o
u
t
th
e
s
en
t
i
m
e
n
t
s
o
f
I
s
la
m
o
p
h
o
b
ia
to
w
ar
d
s
M
u
s
li
m
s
ar
o
u
n
d
th
e
w
o
r
ld
o
n
th
e
d
a
y
o
f
th
e
n
e
w
s
h
ap
p
en
in
g
m
o
s
q
u
e
C
h
r
i
s
tch
u
r
ch
atta
ck
i
n
Ne
w
Z
ea
la
n
d
.
B
ased
o
n
th
e
r
es
u
lts
o
f
s
ev
er
al
p
r
ev
io
u
s
r
esear
ch
,
th
e
an
al
y
s
i
s
to
b
e
ca
r
r
ied
o
u
t
is
b
y
u
ti
lizi
n
g
h
y
b
r
id
s
en
ti
m
en
t
an
al
y
s
i
s
u
s
in
g
th
e
le
x
ical
b
ased
m
eth
o
d
an
d
s
u
p
er
v
i
s
ed
m
ac
h
in
e
lear
n
in
g
.
T
h
e
lex
ical
b
ased
m
et
h
o
d
u
s
e
s
VADE
R
w
ill
b
e
ap
p
l
ied
f
o
r
au
to
m
atic
lab
eli
n
g
o
f
cr
a
w
lin
g
d
ata
f
r
o
m
T
w
itte
r
.
T
h
e
s
u
p
er
v
is
ed
m
ac
h
i
n
e
le
ar
n
in
g
m
et
h
o
d
w
a
s
ch
o
s
e
n
to
test
t
h
e
r
esu
lts
o
f
au
to
m
at
ic
lab
elin
g
u
s
i
n
g
V
ADE
R
an
d
th
e
Na
ïv
e
B
a
y
e
s
an
d
SVM
alg
o
r
ith
m
w
ill
b
e
co
m
p
ar
ed
.
T
h
e
ad
d
itio
n
o
f
f
ea
tu
r
e
s
elec
tio
n
tec
h
n
iq
u
es
f
r
o
m
SMOT
E
w
as
also
ad
d
ed
to
b
alan
ce
th
e
lab
elin
g
d
ata
f
r
o
m
V
A
DE
R
s
o
a
s
to
i
m
p
r
o
v
e
th
e
tes
t r
esu
l
ts
o
f
t
h
e
alg
o
r
it
h
m
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
er
e
ar
e
s
ev
er
al
s
tu
d
ie
s
o
n
I
s
la
m
o
p
h
o
b
ic
a
n
d
T
h
e
Use
o
f
T
w
i
tter
’
s
Data
,
as
f
o
llo
w
s
:
“
Dete
ct
in
g
w
ea
k
an
d
s
tr
o
n
g
I
s
la
m
o
p
h
o
b
ic
h
ate
s
p
ee
ch
o
n
s
o
cial
m
e
d
ia"
b
u
ild
m
u
lti
-
clas
s
class
if
i
er
s
th
at
d
is
tin
g
u
is
h
b
et
w
ee
n
n
o
n
-
I
s
la
m
o
p
h
o
b
ic,
w
ea
k
I
s
la
m
o
p
h
o
b
ic
a
n
d
s
tr
o
n
g
I
s
la
m
o
p
h
o
b
ic
co
n
te
n
t
[
1
0
]
,
“
P
r
ed
ictin
g
o
n
lin
e
I
s
la
m
o
p
h
o
b
ic
b
eh
a
v
io
r
af
ter
#
P
ar
is
A
ttack
s
”
i
n
t
h
i
s
r
esear
ch
c
o
llected
t
w
ee
t
s
r
elate
d
t
o
th
e
P
ar
is
attac
k
s
w
it
h
i
n
5
0
h
o
u
r
s
a
f
ter
th
e
ev
e
n
t
[
1
1
]
,
"
E
lectio
n
r
esu
l
t
p
r
ed
ictio
n
u
s
i
n
g
T
w
itter
s
en
t
i
m
e
n
t
an
al
y
s
i
s
”
t
h
e
tr
ai
n
i
n
g
d
ataset,
f
o
r
lab
elin
g
,
u
s
in
g
v
alen
ce
a
w
ar
e
d
ictio
n
ar
y
a
n
d
s
en
ti
m
en
t
r
ea
s
o
n
er
(
V
A
D
E
R
)
Nex
t
u
s
e
t
w
o
alg
o
r
ith
m
s
,
m
u
lti
n
o
m
ial
Naï
v
e
B
ay
e
s
an
d
SVM
[
1
2
]
,
“
Se
n
ti
m
en
t
an
al
y
s
is
ab
o
u
t
e
-
co
m
m
er
ce
f
r
o
m
t
w
ee
t
u
s
i
n
g
d
ec
is
io
n
t
r
ee
,
k
-
n
ea
r
e
s
t
n
eig
h
b
o
r
,
an
d
Naïv
e
B
a
y
e
s
”
u
s
e
r
ap
id
m
i
n
er
to
m
ak
e
s
e
n
ti
m
en
t
an
al
y
s
is
b
y
co
m
p
ar
i
n
g
t
h
e
Dec
i
s
io
n
T
r
ee
,
K
-
N
N,
an
d
Naï
v
e
B
a
y
e
s
C
lass
i
f
ier
a
n
d
u
s
i
n
g
1
0
-
Fo
ld
C
r
o
s
s
v
alid
atio
n
to
ev
alu
a
te
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
m
ac
h
in
e
lear
n
i
n
g
m
o
d
el
a
n
d
g
et
th
e
h
ig
h
est
r
es
u
lts
f
r
o
m
Naï
v
e
B
a
y
es
[
1
3
]
,
“
A
n
a
lis
i
s
S
en
timen
P
a
d
a
R
e
view
K
o
n
s
u
men
Men
g
g
u
n
a
k
a
n
Meto
d
e
N
a
ïve
B
a
ye
s
Den
g
a
n
S
elek
s
i
F
itu
r
C
h
i
S
q
u
a
r
e
Un
tu
k
R
ek
o
men
d
a
s
i
Lo
ka
s
i
Ma
ka
n
a
n
Tr
a
d
is
io
n
a
l
”
u
s
i
n
g
f
ea
t
u
r
e
s
elec
tio
n
th
e
ch
i
-
s
q
u
ar
e
an
d
class
i
f
icatio
n
p
r
o
ce
s
s
u
s
in
g
t
h
e
Naï
v
e
B
a
y
es
m
et
h
o
d
[
1
4
]
,
“An
ev
al
u
atio
n
o
f
SVM
an
d
Naïv
e
B
a
y
es
w
it
h
SMOT
E
o
n
s
en
ti
m
en
t
an
al
y
s
i
s
d
ata
s
et
”
d
eter
m
i
n
e
th
e
f
ac
to
r
s
in
v
o
lv
i
n
g
th
e
cla
s
s
i
f
icatio
n
o
f
SVM
an
d
Naï
v
e
B
ay
e
s
in
s
en
t
i
m
e
n
t
cla
s
s
i
f
icati
o
n
o
f
p
r
o
b
lem
s
u
s
in
g
SM
OT
E
in
th
e
d
atase
t,
also
co
m
p
ar
in
g
th
e
u
s
e
o
f
10
-
f
o
ld
cr
o
s
s
v
alid
ati
o
n
w
i
th
7
0
:3
0
s
p
lit in
t
h
e
test
[
1
5
]
.
I
n
t
h
is
r
esear
ch
,
w
e
h
av
e
to
k
n
o
w
ab
o
u
t
I
s
la
m
o
p
h
o
b
ia
co
m
es
f
r
o
m
t
h
e
w
o
r
d
s
"
I
s
la
m
"
an
d
"
p
h
o
b
ia
"
w
h
ic
h
m
ea
n
s
"
f
ea
r
o
f
s
o
m
eth
i
n
g
ab
o
u
t
I
s
la
m
"
an
d
it
s
h
o
w
s
a
v
ie
w
o
f
I
s
la
m
w
h
ich
w
il
l
th
r
ea
ten
th
e
cu
l
tu
r
e
o
f
W
ester
n
.
I
f
w
e
tr
ac
e
b
ac
k
to
E
u
r
o
p
e
1
4
ce
n
tu
r
ies
ag
o
,
t
h
at
w
a
s
o
n
e
a
m
o
n
g
t
h
e
r
esu
lts
o
f
th
e
"
o
r
ien
talis
m
"
o
f
th
e
A
r
ab
w
o
r
ld
.
I
n
r
ec
en
t
ti
m
e
s
,
th
e
ter
m
i
s
la
m
o
p
h
o
b
ia
h
as
b
eg
u
n
to
r
ea
p
p
ea
r
in
co
n
n
ec
ti
o
n
w
ith
t
h
e
"
w
ar
o
n
ter
r
o
r
"
d
u
e
to
th
e
ter
r
o
r
is
t
a
ttack
s
th
a
t
to
o
k
p
lace
o
n
Se
p
te
m
b
er
11
,
2
0
0
1
,
w
h
ic
h
h
a
v
e
n
e
g
ati
v
e
s
o
cial
p
er
ce
p
tio
n
s
ab
o
u
t I
s
la
m
[
5
]
.
T
h
at
w
a
s
co
n
f
ir
m
ed
b
y
n
eg
a
tiv
e
m
e
d
ia
r
ep
r
esen
ta
tiv
e
s
ab
o
u
t
I
s
la
m
.
Alth
o
u
g
h
f
a
r
f
r
o
m
a
n
e
w
f
o
r
m
o
f
f
a
n
aticis
m
,
I
s
la
m
o
p
h
o
b
ia
ca
n
h
av
e
d
i
f
f
er
en
t
n
u
a
n
ce
s
d
ep
en
d
i
n
g
o
n
th
e
s
o
cio
-
p
o
liti
ca
l
co
n
tex
t:
[
1
6
]
f
o
r
ex
a
m
p
le,
ex
p
lain
in
g
th
at
Am
er
ican
I
s
la
m
o
p
h
o
b
ia
is
in
f
l
u
e
n
ce
d
b
y
e
v
e
n
ts
i
n
E
u
r
o
p
e
s
u
c
h
as
B
r
ex
it,
b
u
t
at
th
e
s
a
m
e
ti
m
e
i
s
co
n
n
ec
ted
to
th
e
le
g
al
s
y
s
te
m
,
n
atio
n
al
p
o
liti
cs,
r
ac
ial
d
em
o
g
r
ap
h
ic
s
an
d
U
S
r
elig
io
n
.
Desp
ite
t
h
e
lack
o
f
a
u
n
iv
er
s
a
l
u
n
d
er
s
ta
n
d
i
n
g
o
f
th
e
ter
m
I
s
la
m
o
p
h
o
b
ia,
th
e
d
ef
in
i
tio
n
o
f
I
s
la
m
o
p
h
o
b
ia
g
i
v
e
n
b
y
t
h
e
R
u
n
n
y
m
ed
e
T
r
u
s
t
is
"
b
aseless
h
o
s
tili
t
y
to
w
ar
d
s
I
s
la
m
"
a
n
d
ex
p
lain
s
h
o
s
tili
t
y
i
n
un
f
air
d
is
cr
i
m
i
n
atio
n
ag
ai
n
s
t
th
e
M
u
s
li
m
co
m
m
u
n
it
y
a
n
d
in
d
iv
id
u
als
,
b
y
ex
c
lu
d
i
n
g
M
u
s
li
m
s
f
r
o
m
s
o
cial
af
f
a
ir
s
an
d
p
o
liti
ca
l
.
T
h
at
w
a
s
co
n
f
ir
m
ed
b
y
n
e
g
ati
v
e
m
e
d
ia
r
ep
r
esen
tati
v
es a
b
o
u
t I
s
la
m
[
1
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
n
a
lysi
s
s
en
timen
t a
b
o
u
t
is
la
mo
p
h
o
b
i
a
w
h
en
C
h
r
is
tch
u
r
ch
a
tta
ck
o
n
s
o
cia
l m
e
d
ia
(
W
in
d
u
Ga
ta
)
1821
T
h
er
e
is
a
s
tu
d
y
o
f
i
s
la
m
o
p
h
o
b
ia
co
n
d
u
cted
b
y
t
h
e
B
r
iti
s
h
a
s
s
o
ciatio
n
[
6
]
w
h
ich
a
i
m
s
to
f
i
g
h
t
an
ti
-
Mu
s
li
m
cr
i
m
e
an
d
also
f
in
d
t
h
at
v
icti
m
s
u
s
u
all
y
e
x
p
er
ien
ce
h
ar
a
s
s
m
e
n
t,
b
o
th
o
n
lin
e
a
n
d
o
f
f
li
n
e.
R
ec
en
t
l
y
,
w
o
r
ld
lead
er
s
a
n
d
h
u
m
a
n
r
i
g
h
ts
i
n
s
tit
u
tio
n
s
as
s
ess
ed
t
h
e
h
o
r
r
if
ic
ter
r
o
r
attac
k
s
t
h
at
o
cc
u
r
r
ed
at
th
e
t
w
i
n
m
o
s
q
u
e
i
n
C
h
r
i
s
tc
h
u
r
ch
,
Ne
w
Z
ea
la
n
d
,
w
h
er
e
ter
r
o
r
is
ts
h
av
e
k
il
led
4
9
p
eo
p
le
an
d
in
j
u
r
ed
at
least
4
8
o
th
er
s
,
ar
e
th
e
ef
f
ec
t
s
o
f
all
o
w
i
n
g
a
n
attit
u
d
e
o
f
h
a
tr
ed
to
w
ar
d
s
I
s
la
m
(
I
s
la
m
o
p
h
o
b
ia)
in
th
e
w
est
[
7
]
.
On
e
o
f
t
h
e
So
cial
m
ed
ia
lik
e
T
w
itter
al
lo
w
s
u
s
er
s
to
b
e
ab
le
to
s
e
n
d
m
e
s
s
a
g
es
in
r
ea
l
-
ti
m
e
.
T
h
is
m
es
s
ag
e
i
s
p
o
p
u
lar
l
y
k
n
o
w
n
as
a
t
w
ee
t.
A
T
w
ee
t
i
s
a
s
h
o
r
t
m
es
s
ag
e
w
i
th
a
li
m
ited
ch
ar
ac
ter
len
g
t
h
o
f
o
n
l
y
1
4
0
ch
ar
ac
ter
s
.
Du
e
to
th
e
li
m
itatio
n
s
o
f
c
h
ar
ac
ter
s
th
at
ca
n
b
e
w
r
i
tten
,
a
t
wee
t
o
f
ten
co
n
tain
s
ab
b
r
ev
iatio
n
s
,
s
la
n
g
a
n
d
s
p
el
li
n
g
er
r
o
r
s
[
1
7
]
.
A
ll
d
ata
w
i
ll
b
e
p
r
o
ce
s
s
ed
f
o
r
f
in
d
in
g
m
ea
n
i
n
g
f
u
l
r
elatio
n
s
h
ip
s
,
p
atter
n
s
,
an
d
tr
en
d
s
b
y
ex
a
m
i
n
in
g
t
h
e
lar
g
e
d
ata
s
ets
s
to
r
ed
in
s
to
r
ag
e
b
y
u
s
i
n
g
p
atter
n
r
ec
o
g
n
itio
n
tech
n
iq
u
e
s
s
u
c
h
as st
a
tis
tica
l a
n
d
m
a
th
e
m
atica
l te
ch
n
iq
u
e
s
[
1
8
]
.
T
h
e
u
s
e
o
f
T
w
i
tter
’
s
d
ata
u
s
ag
e
tex
t,
t
h
e
m
et
h
o
d
to
m
in
e
d
ata
is
tex
t
m
i
n
i
n
g
w
h
ic
h
is
d
ef
i
n
ed
d
ef
in
ed
a
s
t
h
e
p
r
o
ce
s
s
o
f
e
x
t
r
ac
tin
g
i
m
p
l
icit
k
n
o
w
led
g
e
f
r
o
m
d
ata.
B
ec
au
s
e
i
m
p
l
icit
k
n
o
w
led
g
e
w
h
ich
i
s
th
e
o
u
tp
u
t
o
f
t
h
e
tex
t
d
o
es
n
o
t
ex
is
t
i
n
t
h
e
g
i
v
e
n
s
to
r
ag
e,
it
m
u
s
t
b
e
d
is
ti
n
g
u
i
s
h
ed
f
r
o
m
in
f
o
r
m
atio
n
o
b
tain
ed
f
r
o
m
s
to
r
ag
e
[
1
9
]
.
Af
ter
th
a
t
w
e
ca
n
u
s
e
to
a
n
al
y
ze
p
e
o
p
le'
s
s
e
n
ti
m
e
n
ts
,
o
p
in
io
n
s
,
attitu
d
es,
e
m
o
tio
n
s
,
ev
alu
a
tio
n
s
,
an
d
j
u
d
g
m
e
n
t
s
p
eo
p
le'
s
ab
o
u
t
a
s
er
v
ice,
p
r
o
d
u
ct,
in
d
iv
id
u
al,
o
r
g
an
izat
io
n
,
ev
e
n
t,
to
p
ic,
attr
ib
u
te,
an
d
p
r
o
b
lem
.
T
h
er
e
ar
e
also
m
an
y
s
li
g
h
tl
y
d
i
f
f
er
en
t
n
a
m
es
a
n
d
task
s
,
f
o
r
ex
a
m
p
le,
s
en
ti
m
e
n
t
an
al
y
s
is
,
o
p
in
io
n
m
in
i
n
g
,
o
p
in
io
n
e
x
tr
a
ctio
n
,
s
en
ti
m
en
t
m
i
n
i
n
g
,
s
u
b
j
ec
tiv
it
y
a
n
al
y
s
is
,
a
f
f
ec
t
an
al
y
s
i
s
,
e
m
o
tio
n
a
n
al
y
s
i
s
,
r
ev
ie
w
m
i
n
i
n
g
,
etc.
Se
n
ti
m
e
n
t
an
al
y
s
is
a
n
d
o
p
in
io
n
m
i
n
i
n
g
m
ai
n
l
y
f
o
cu
s
e
s
o
n
o
p
in
io
n
s
t
h
at
ex
p
r
es
s
o
r
i
m
p
l
y
p
o
s
itiv
e
o
r
n
eg
ati
v
e
s
e
n
ti
m
en
ts
,
w
h
ich
is
ca
lled
b
y
te
x
t
m
i
n
in
g
[
9
]
.
T
h
er
e
ar
e
w
a
y
s
to
c
lass
i
f
y
s
e
n
ti
m
e
n
ts
,
in
cl
u
d
in
g
[
2
0
]
:
m
ac
h
i
n
e
lear
n
i
n
g
,
le
x
ico
n
-
b
ased
,
an
d
h
y
b
r
id
.
Fo
r
lab
ellin
g
f
o
r
te
x
t
lab
eli
n
g
,
w
e
u
s
e
th
e
V
A
DE
R
to
o
l
w
h
i
ch
is
a
v
ailab
le
o
n
li
n
e
an
d
ca
n
b
e
u
s
ed
i
n
th
e
P
y
t
h
o
n
p
r
o
g
r
a
m
m
i
n
g
lan
g
u
a
g
e
.
V
A
DE
R
is
a
r
u
le
a
n
d
a
lex
ico
n
-
b
ased
s
e
n
ti
m
en
t
an
al
y
s
is
to
o
l,
th
at
's
s
p
ec
if
icall
y
alig
n
ed
w
i
th
t
h
e
s
en
ti
m
en
t
e
x
p
r
ess
ed
o
n
t
h
e
s
o
c
ial
m
ed
ia.
T
h
is
i
s
a
n
i
n
te
n
s
i
t
y
s
en
ti
m
e
n
t
p
o
lar
izer
d
ev
elo
p
ed
b
y
Hu
tto
a
n
d
Gilb
er
t.
VA
DE
R
tak
e
s
s
en
ten
ce
s
as
i
n
p
u
t
an
d
g
iv
e
s
p
er
ce
n
t
v
al
u
e
s
f
o
r
th
r
ee
p
o
s
itiv
e,
n
eu
tr
al
a
n
d
n
e
g
ati
v
e
an
d
c
o
m
p
o
u
n
d
ca
te
g
o
r
ies
(
p
o
lar
ity
o
f
w
h
o
le
s
e
n
ten
ce
s
)
[
1
2
]
.
R
eg
ar
d
in
g
s
co
r
es,
th
e
co
m
b
in
ed
s
co
r
es
ar
e
ca
lcu
lated
b
y
ad
d
in
g
u
p
th
e
v
ale
n
ce
s
co
r
es
o
f
ea
ch
w
o
r
d
in
th
e
lex
ico
n
,
ad
j
u
s
ted
ac
co
r
d
in
g
to
th
e
r
u
les,
a
n
d
t
h
en
n
o
r
m
al
ized
to
b
et
w
ee
n
-
1
(
th
e
m
o
s
t
ex
tr
e
m
e
n
eg
a
tiv
e
)
an
d
+1
(
th
e
m
o
s
t
ex
tr
e
m
e
p
o
s
iti
v
e)
.
I
t
’
s
th
e
m
o
s
t
u
s
e
f
u
l
m
atr
i
x
i
f
w
e
w
a
n
t
a
s
in
g
le
s
e
n
ti
m
e
n
t
m
ea
s
u
r
e
an
d
u
n
id
i
m
e
n
s
io
n
al
f
o
r
a
p
ar
ticu
lar
s
e
n
ten
ce
.
C
all
i
n
g
'
n
o
r
m
alize
d
a
n
d
w
ei
g
h
ted
co
m
p
o
s
i
te
s
co
r
es
'
ac
cu
r
ate.
T
h
e
g
en
er
al
th
r
e
s
h
o
ld
v
alu
e
(
u
s
ed
i
n
t
h
e
liter
at
u
r
e
cited
o
n
t
h
is
p
ag
e)
i
s
[
2
1
]
:
p
o
s
itiv
e
s
e
n
ti
m
e
n
t
,
n
eu
tr
al
s
e
n
ti
m
e
n
ts
,
a
n
d
n
eg
at
iv
e
s
en
t
i
m
e
n
t
.
B
ec
au
s
e
t
h
e
d
ata
i
s
n
o
t
b
alan
ce
,
t
h
e
m
eth
o
d
f
o
r
b
alan
c
in
g
is
s
y
n
t
h
etic
m
in
o
r
it
y
o
v
er
s
a
m
p
li
n
g
tech
n
iq
u
e
(
S
MO
T
E
)
.
T
h
e
SM
OT
E
alg
o
r
ith
m
p
er
f
o
r
m
s
t
h
e
Ov
er
Sa
m
p
li
n
g
ap
p
r
o
ac
h
to
b
alan
ce
t
h
e
o
r
i
g
in
a
l
tr
ain
i
n
g
s
et.
I
n
s
tead
o
f
i
m
p
le
m
en
tin
g
s
i
m
p
le
r
ep
licatio
n
o
f
m
i
n
o
r
it
y
cla
s
s
in
s
ta
n
ce
s
,
t
h
e
m
ai
n
id
ea
o
f
SMOT
E
is
to
in
tr
o
d
u
ce
s
y
n
t
h
etic
d
ata
ex
a
m
p
le
s
.
T
h
is
n
e
w
d
ata
is
cr
ea
ted
b
y
in
ter
p
o
latin
g
b
et
w
ee
n
s
e
v
er
al
in
s
tan
ce
s
o
f
m
i
n
o
r
it
y
cla
s
s
e
s
th
at
ar
e
i
n
th
e
s
p
ec
i
f
ied
en
v
ir
o
n
m
en
t
[2
2
]
.
T
h
e
alg
o
r
ith
m
f
o
r
d
eter
m
in
i
n
g
th
e
ac
c
u
r
ac
y
o
f
p
r
ed
ictio
n
s
u
s
es
th
e
cla
s
s
i
f
ica
tio
n
alg
o
r
ith
m
co
m
m
o
n
l
y
u
s
ed
,
n
a
m
el
y
:
Na
ïv
e
B
a
y
es
a
n
d
SVM.
Naïv
e
B
ay
es
i
s
a
class
i
f
icatio
n
w
i
th
p
r
o
b
ab
ilit
y
a
n
d
s
tatis
t
ical
m
et
h
o
d
s
t
h
at
p
r
ed
ic
t
f
u
t
u
r
e
o
p
p
o
r
tu
n
itie
s
b
a
s
ed
o
n
p
ast
ex
p
er
ie
n
ce
s
o
t
h
at
it
is
k
n
o
w
n
a
s
t
h
e
B
a
y
es
t
h
eo
r
e
m
[
14
,
2
3
]
,
an
d
SVM
a
lg
o
r
ith
m
w
ill
id
en
t
if
y
h
y
p
er
p
lan
e
(
o
r
a
s
er
ies
o
f
h
y
p
er
p
lan
e
)
th
at
w
ill
p
r
o
v
id
e
th
e
b
est
s
ep
ar
atio
n
b
et
w
ee
n
tr
ain
i
n
g
d
ata
in
s
tan
ce
s
.
Am
o
n
g
all
p
o
s
s
ib
le
h
y
p
er
p
lan
e
s
o
f
s
ep
ar
atio
n
,
th
e
SVM
alg
o
r
ith
m
tr
ies
to
id
en
ti
f
y
w
h
o
h
as
th
e
g
r
ea
te
s
t
d
is
ta
n
ce
to
th
e
clo
s
est
tr
a
i
n
in
g
i
n
s
ta
n
ce
o
f
an
y
clas
s
,
b
ec
au
s
e
th
at
w
i
ll
b
e
r
ef
lecte
d
i
n
g
en
e
r
aliza
tio
n
er
r
o
r
s
th
at
ar
e
lo
w
er
th
an
th
e
c
la
s
s
i
f
ier
[
2
4
,
2
5
]
.
B
o
th
p
r
o
ce
s
s
in
g
w
il
l
b
e
e
v
alu
a
ted
u
s
in
g
cr
o
s
s
-
v
a
lid
atio
n
,
w
h
ic
h
i
s
a
n
ap
p
r
o
ac
h
f
o
r
e
v
al
u
ati
n
g
th
e
p
er
f
o
r
m
an
ce
o
f
m
ac
h
i
n
e
lear
n
in
g
m
o
d
els.
T
h
er
e
ar
e
tw
o
t
y
p
e
s
o
f
p
h
ase
s
i
n
t
h
e
d
at
aset,
m
ai
n
l
y
tr
ai
n
i
n
g
d
e
v
ices
an
d
test
i
n
g
d
ev
ice
s
.
W
ith
t
h
e
ap
p
licatio
n
o
f
cr
o
s
s
-
v
a
lid
atio
n
,
t
h
e
te
s
ti
n
g
s
et
w
i
ll
b
e
co
m
p
ar
ed
w
it
h
t
h
e
tr
ai
n
in
g
s
et
to
v
a
lid
ate
o
v
er
f
itti
n
g
a
n
d
to
d
ec
id
e
h
o
w
th
e
m
ac
h
i
n
e
lear
n
i
n
g
m
o
d
el
w
ill
p
r
o
d
u
ce
in
d
ep
en
d
e
n
t
d
ata
[
1
5
]
.
T
h
e
b
est
class
i
f
icatio
n
p
er
f
o
r
m
an
ce
ca
n
b
e
d
escr
ib
ed
p
r
ec
is
ely
b
y
a
to
o
l
ca
lled
c
o
n
f
u
s
io
n
m
atr
ix
a
n
d
tr
ad
itio
n
all
y
it
’
s
ar
r
an
g
ed
as
2x
2
[
2
6
]
.
2
.
1
.
M
et
o
do
lo
g
y
T
h
e
m
e
th
o
d
u
s
ed
to
o
b
tain
i
n
f
o
r
m
atio
n
is
to
u
s
e
T
ex
t
m
i
n
i
n
g
in
o
r
d
er
to
b
e
ab
le
to
class
if
y
t
w
ee
t
s
r
elatin
g
to
I
s
la
m
o
p
h
o
b
ia
w
h
e
n
C
h
r
i
s
tch
u
r
ch
attac
k
.
T
h
e
r
esear
ch
m
eth
o
d
o
lo
g
y
u
s
ed
i
n
t
h
i
s
r
esear
ch
is
to
u
s
e
th
e
cr
o
s
s
-
i
n
d
u
s
tr
y
s
ta
n
d
ar
d
p
r
o
ce
s
s
f
o
r
d
ata
m
in
in
g
(
C
R
I
S
P
-
DM
)
m
et
h
o
d
[
2
7
]
w
h
ic
h
c
o
n
s
is
ts
o
f
s
i
x
s
tag
e
s
an
d
w
ill b
e
d
escr
ib
ed
in
Fig
u
r
e
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
18
1
9
-
1
8
2
7
1822
Fig
u
r
e
1
.
C
R
I
SP
-
DM
m
o
d
el
2
.
1
.
1
.
B
us
s
ines
s
un
der
s
t
a
nd
i
ng
R
esear
ch
co
n
d
u
cted
to
f
i
n
d
o
u
t
p
u
b
lic
s
e
n
ti
m
e
n
ts
in
r
esp
o
n
d
in
g
to
"
I
s
la
m
o
p
h
o
b
ia"
o
n
th
e
d
a
y
o
f
th
e
atta
ck
o
n
t
h
e
m
o
s
q
u
e
in
C
h
r
is
tc
h
u
r
c
h
,
Ne
w
Z
ea
la
n
d
w
h
i
ch
e
m
er
g
ed
f
r
o
m
s
o
cial
m
ed
ia
T
w
itter
o
n
Ma
r
c
h
1
5
,
2
0
1
9
,
th
e
i
m
p
le
m
e
n
tati
o
n
w
as
ca
r
r
ied
o
u
t
u
s
i
n
g
t
h
e
p
y
t
h
o
n
p
r
o
g
r
a
m
m
i
n
g
la
n
g
u
a
g
e
alo
n
g
w
i
th
th
e
r
eq
u
ir
ed
lib
r
ar
ies.
2
.
1
.
2
.
Da
t
a
un
dersta
nd
i
ng
Usi
n
g
d
ata
f
r
o
m
T
w
itter
s
o
cial
m
ed
ia
w
it
h
th
e
I
s
la
m
o
p
h
o
b
ia
h
a
s
h
ta
g
an
d
n
o
t
f
ilter
i
n
g
o
n
l
y
i
n
to
o
n
e
lan
g
u
a
g
e
o
r
r
eg
io
n
,
b
u
t
r
etr
ie
v
in
g
d
ata
f
r
o
m
t
w
ee
t
s
ar
o
u
n
d
th
e
w
o
r
ld
.
T
ak
en
o
n
th
e
d
a
y
o
f
th
e
attac
k
o
n
th
e
m
o
s
q
u
e
i
n
C
h
r
i
s
tc
h
u
r
c
h
,
Ne
w
Z
ea
lan
d
o
n
1
5
Ma
r
c
h
2
0
1
9
.
T
h
is
w
as
d
o
n
e
s
o
t
h
at
t
h
e
d
ata
ta
k
e
n
f
r
o
m
th
e
T
w
i
tter
d
is
c
u
s
s
io
n
th
at
o
cc
u
r
r
ed
w
a
s
s
till
r
ele
v
a
n
t
to
t
h
e
in
cid
e
n
t
o
f
t
h
e
attac
k
o
n
I
s
la
m
o
p
h
o
b
ia.
T
h
e
d
ata
is
r
etr
iev
ed
u
s
i
n
g
d
ata
-
m
i
n
er
.
io
.
"
Data
s
cr
ap
er
"
a
p
p
licatio
n
,
w
h
ich
i
s
an
ad
d
itio
n
al
p
lu
g
-
i
n
in
t
h
e
C
h
r
o
m
e
b
r
o
w
s
er
w
h
ic
h
f
u
n
ctio
n
s
f
o
r
s
cr
ap
in
g
d
ata
f
r
o
m
HT
ML
web
p
ag
es
an
d
ex
p
o
r
ts
in
to
XL
S,
C
SV,
X
L
SX
o
r
T
SV f
iles
.
B
y
u
s
in
g
"
Data
s
cr
ap
er
"
m
a
n
ag
ed
to
co
llect
t
w
ee
ts
f
r
o
m
ea
c
h
u
s
er
a
n
d
o
b
tain
ed
a
s
m
a
n
y
as
3
1
1
5
t
w
ee
ts
,
d
ata
tak
e
n
f
r
o
m
T
w
itter
co
n
s
is
t
s
o
f
s
e
v
er
al
co
lu
m
n
s
n
a
m
el
y
u
s
er
n
a
m
e,
f
u
ll
n
a
m
e,
d
ate,
f
ir
s
t
h
as
h
ta
g
s
,
alt
h
a
s
h
tag
s
,
t
w
ee
t
s
(
m
ess
a
g
e
tex
t)
,
r
et
w
ee
t,
r
et
w
e
et
(
r
et
w
ee
t
(
r
et
w
ee
t
(
r
et
w
ee
t)
w
/te
x
t)
,
l
ik
e
s
,
li
k
es
(
w
/te
x
t
)
,
an
d
UR
L
p
at
h
.
T
h
e
o
n
l
y
co
l
u
m
n
u
s
ed
i
n
th
i
s
r
esear
ch
is
"
t
w
ee
t
(
m
es
s
ag
e
te
x
t)
"
.
2
.
1
.
3
.
Da
t
a
prepa
ra
t
io
n
T
h
er
e
ar
e
2
s
tag
es
o
f
d
ata
p
r
ep
ar
atio
n
in
t
h
is
r
ea
s
ea
r
c
h
,
n
a
m
el
y
p
r
ep
r
o
ce
s
s
in
g
p
h
ase
1
a
n
d
p
h
ase
2
.
P
r
ep
r
o
ce
s
s
in
g
p
h
a
s
e
1
i
s
ca
r
r
i
ed
o
u
t a
f
ter
cr
a
w
li
n
g
T
w
i
tter
d
ata,
w
h
ic
h
co
n
s
i
s
ts
o
f
ca
s
e
f
o
ld
in
g
,
clea
n
s
i
n
g
an
d
tr
an
s
late
i
n
t
o
E
n
g
lis
h
.
W
h
er
e
as
f
o
r
P
h
ase
2
P
r
e
p
r
o
ce
s
s
in
g
is
ca
r
r
ied
o
u
t
af
ter
g
ettin
g
d
ata
lab
elin
g
f
r
o
m
VADE
R
,
w
h
ic
h
co
n
s
i
s
ts
o
f
T
o
k
en
ize,
N
-
Gr
a
m
,
Sto
p
w
o
r
d
s
an
d
Ste
m
m
i
n
g
.
Sta
g
e
2
p
r
o
ce
s
s
i
n
g
is
ca
r
r
ied
o
u
t
in
th
e
T
F
-
I
D
F p
r
o
ce
s
s
w
h
ic
h
f
u
n
ct
io
n
s
to
d
o
w
o
r
d
w
e
ig
h
ti
n
g
.
2
.
1
.
4
.
M
o
delin
g
Af
ter
d
o
in
g
t
h
e
d
ata
p
r
ep
ar
atio
n
p
r
o
ce
s
s
i
n
t
h
e
p
r
ev
io
u
s
s
ta
g
e,
at
t
h
i
s
s
ta
g
e,
t
h
e
d
ata
w
ill
b
e
u
s
ed
a
s
th
e
i
n
p
u
t
cla
s
s
i
f
icatio
n
al
g
o
r
it
h
m
.
T
h
e
p
r
o
ce
s
s
i
s
ca
r
r
ied
o
u
t
in
cr
o
s
s
-
v
a
lid
atio
n
w
it
h
1
0
-
F
o
ld
,
w
h
ich
i
s
d
o
in
g
1
0
tim
es
cr
o
s
s
-
v
alid
atio
n
u
s
i
n
g
d
ata
th
at
h
as
b
ee
n
p
r
o
ce
s
s
ed
b
ef
o
r
e.
W
ith
th
e
ap
p
licatio
n
o
f
cr
o
s
s
-
v
alid
atio
n
,
th
e
te
s
ti
n
g
s
et
w
i
ll
b
e
co
m
p
ar
ed
w
it
h
t
h
e
tr
ai
n
i
n
g
s
et
to
v
ali
d
ate
o
v
er
f
itti
n
g
a
n
d
to
d
ec
id
e
h
o
w
t
h
e
m
o
d
el
w
i
ll
p
r
o
d
u
ce
in
d
ep
en
d
en
t d
ata.
I
n
th
i
s
r
esear
c
h
,
t
w
o
t
y
p
es
o
f
alg
o
r
it
h
m
s
w
i
ll
b
e
u
s
ed
f
o
r
co
m
p
ar
is
o
n
,
n
a
m
e
l
y
Naï
v
e
B
a
y
es
an
d
SVM
.
A
s
is
k
n
o
w
n
,
th
er
e
is
a
s
i
g
n
if
ican
t
d
if
f
er
e
n
ce
f
r
o
m
t
h
e
r
e
s
u
l
ts
o
f
lab
eli
n
g
u
s
i
n
g
V
ADE
R
b
et
w
ee
n
th
e
p
o
s
iti
v
e
a
n
d
n
e
g
ati
v
e
cla
s
s
es.
So
t
o
h
a
n
d
le
t
h
e
I
m
b
al
an
ce
d
Data
t
h
at
o
cc
u
r
s
,
th
e
SMOT
E
is
u
s
ed
i
n
th
e
co
m
p
ar
is
o
n
o
f
u
s
e
w
it
h
th
e
t
w
o
alg
o
r
it
h
m
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
n
a
lysi
s
s
en
timen
t a
b
o
u
t
is
la
mo
p
h
o
b
i
a
w
h
en
C
h
r
is
tch
u
r
ch
a
tta
ck
o
n
s
o
cia
l m
e
d
ia
(
W
in
d
u
Ga
ta
)
1823
2
.
1
.
5
.
E
v
a
lua
t
io
n
T
h
e
ev
alu
at
io
n
p
h
a
s
e
i
s
t
h
e
s
tag
e
o
f
ev
al
u
ati
n
g
t
h
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
m
o
d
elin
g
a
n
d
c
alcu
latio
n
s
th
at
h
av
e
b
ee
n
ca
r
r
ied
o
u
t b
y
m
ea
s
u
r
in
g
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
clas
s
i
f
icatio
n
al
g
o
r
it
h
m
u
s
ed
.
I
n
th
is
r
esear
c
h
,
p
er
f
o
r
m
a
n
ce
i
s
m
ea
s
u
r
ed
u
s
i
n
g
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all
,
F1
-
s
co
r
e
,
ar
ea
u
n
d
er
c
u
r
v
e
(
A
U
C
)
w
h
ich
w
il
l
b
e
d
is
p
la
y
ed
i
n
t
h
e
f
o
r
m
o
f
R
OC
cu
r
v
es
an
d
w
o
r
d
clo
u
d
to
v
is
u
alize
t
h
e
s
p
r
ea
d
o
f
p
o
s
iti
v
e
a
n
d
n
e
g
ati
v
e
w
o
r
d
s
th
a
t
u
s
u
al
l
y
ar
i
s
e
f
r
o
m
T
F
-
I
DF.
T
h
ese
r
esu
lt
s
w
ill
s
h
o
w
t
h
e
u
s
e
o
f
t
h
e
m
o
s
t
ap
p
r
o
p
r
iate
alg
o
r
ith
m
f
o
r
th
e
m
o
d
eli
n
g
t
h
at
h
as b
ee
n
p
r
o
p
o
s
ed
p
r
ev
io
u
s
l
y
.
2
.
1
.
6
.
Deplo
y
m
ent
T
h
e
n
ex
t
s
ta
g
e
is
t
h
e
ap
p
licati
o
n
o
f
th
e
m
o
d
el
b
y
d
e
v
elo
p
in
g
in
to
t
h
e
ap
p
licatio
n
.
T
h
e
ap
p
licatio
n
o
f
th
e
m
o
d
el
i
s
b
ased
o
n
t
h
e
b
est
ev
al
u
atio
n
v
al
u
e
o
b
tain
ed
at
t
h
e
ev
a
lu
at
io
n
s
tag
e.
T
h
e
u
s
e
o
f
ap
p
licatio
n
s
th
a
t
w
il
l b
e
d
ev
elo
p
ed
u
s
in
g
t
h
e
p
y
th
o
n
p
r
o
g
r
a
m
m
i
n
g
lan
g
u
ag
e
a
lo
n
g
w
it
h
t
h
e
r
eq
u
ir
ed
lib
r
ar
ies.
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
3
.
1
.
VADER
re
s
ult
T
h
e
d
ata
o
b
tain
ed
u
s
in
g
th
e
VADE
R
lib
r
ar
y
ar
e
p
o
s
itiv
e,
n
eg
ati
v
e
an
d
n
e
u
tr
al.
I
n
th
is
r
esear
ch
,
th
e
d
ata
u
s
ed
ar
e
o
n
ly
p
o
s
iti
v
e
an
d
n
eg
ati
v
e
s
en
ti
m
e
n
t
d
ata
f
r
o
m
V
A
DE
R
to
ca
r
r
y
o
u
t
th
e
n
ex
t
p
r
o
ce
s
s
.
T
o
tal
d
ata
af
ter
p
r
ep
r
o
ce
s
s
in
g
an
d
la
b
elin
g
u
s
i
n
g
V
A
DE
R
ca
n
b
e
s
ee
n
in
t
h
e
i
m
ag
e
a
s
s
h
o
w
n
i
n
Fig
u
r
e
2
.
Fig
u
r
e
2
.
L
ab
el
d
is
tr
ib
u
tio
n
o
f
d
ata
u
s
in
g
V
A
DE
R
3
.
2
.
E
v
a
lua
t
i
o
n
m
o
del r
es
ult
T
h
e
r
esu
lts
o
f
t
h
e
p
r
o
ce
s
s
i
n
g
o
f
alg
o
r
it
h
m
s
t
h
at
h
a
v
e
b
ee
n
c
o
m
p
leted
h
a
v
e
th
e
r
esu
lts
a
n
d
g
r
ap
h
s
o
f
R
OC
a
n
d
A
U
C
f
o
r
ea
ch
a
lg
o
r
ith
m
.
T
h
e
Naïv
e
B
a
y
e
s
al
g
o
r
ith
m
,
a
s
s
h
o
w
n
in
F
ig
u
r
e
3
,
h
as
an
A
U
C
v
al
u
e
o
f
0
.
5
8
8
,
w
h
ic
h
m
ea
n
s
p
o
o
r
class
if
ica
tio
n
.
W
h
er
ea
s
th
e
SVM
alg
o
r
ith
m
,
i
n
F
i
g
u
r
e
4
,
h
as a
n
A
U
C
v
alu
e
o
f
0
.
7
0
8
w
h
ic
h
m
ea
n
s
g
o
o
d
class
if
ica
ti
o
n
.
I
n
Fig
u
r
e
5
,
th
e
Naïv
e
B
ay
es
p
lu
s
SMOT
E
alg
o
r
ith
m
h
as
an
A
UC
v
al
u
e
o
f
0
.
9
0
8
an
d
in
Fi
g
u
r
e
6
,
f
o
r
th
e
SVM
p
l
u
s
S
MO
T
E
alg
o
r
ith
m
w
h
ic
h
h
as
a
n
AUC
v
al
u
e
o
f
0
.
9
1
4
w
h
ic
h
m
ea
n
s
ex
ce
len
t c
lass
if
icatio
n
.
Fig
u
r
e
3
.
C
o
n
f
u
s
io
n
m
atr
ix
a
n
d
k
ur
v
e
ROC
Naïv
e
B
a
y
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
18
1
9
-
1
8
2
7
1824
Fig
u
r
e
4
.
C
o
n
f
u
s
io
n
m
atr
ix
a
n
d
k
u
r
v
e
R
OC
SVM
Fig
u
r
e
5
.
C
o
n
f
u
s
io
n
m
atr
ix
an
d
k
u
r
v
e
R
OC
Na
ïv
e
B
a
y
e
s
w
it
h
SMOT
E
Fig
u
r
e
6
.
C
o
n
f
u
s
io
n
m
atr
ix
a
n
d
k
u
r
v
e
R
OC
SVM
w
it
h
SMO
T
E
B
ased
o
n
th
e
r
esu
lts
o
f
t
h
e
m
o
d
el
tes
ts
in
F
ig
u
r
e
6
,
h
er
e
is
a
s
u
m
m
ar
y
o
f
th
e
test
r
es
u
lts
f
o
r
all
th
e
m
o
d
els
.
B
ased
o
n
t
h
e
Fi
g
u
r
e
7
r
esu
lts
,
it
ca
n
b
e
s
ee
n
t
h
at
t
h
e
S
VM
+
SMOT
E
m
o
d
el
h
as
t
h
e
h
ig
h
est
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
F1
-
Sco
r
e
an
d
A
U
C
an
d
t
h
e
f
a
s
tes
t
m
o
d
el
p
r
o
ce
s
s
in
g
ti
m
e
is
i
n
t
h
e
SVM.
Fro
m
t
h
ese
r
esu
lt
s
,
it
ca
n
b
e
co
n
clu
d
ed
th
at
th
e
SMOT
E
f
ea
tu
r
e
is
v
er
y
in
f
lu
e
n
tia
l
in
i
m
p
r
o
v
i
n
g
th
e
p
er
f
o
r
m
an
ce
o
f
b
o
t
h
alg
o
r
ith
m
s
.
I
n
th
is
r
esear
c
h
,
it
ca
n
also
b
e
co
n
cl
u
d
ed
th
at
t
h
e
r
esu
lt
s
o
f
t
h
e
SVM
+
SMOT
E
m
o
d
el
h
av
e
b
etter
p
er
f
o
r
m
a
n
ce
co
m
p
ar
ed
to
o
th
er
test
in
g
m
o
d
e
ls
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
n
a
lysi
s
s
en
timen
t a
b
o
u
t
is
la
mo
p
h
o
b
i
a
w
h
en
C
h
r
is
tch
u
r
ch
a
tta
ck
o
n
s
o
cia
l m
e
d
ia
(
W
in
d
u
Ga
ta
)
1825
Fig
u
r
e
7
.
C
o
m
p
ar
is
o
n
r
es
u
lt
s
o
f
p
er
f
o
r
m
an
ce
m
o
d
el
3
.
3
.
Wo
rdclo
ud
W
o
r
d
clo
u
d
is
a
to
o
l
f
o
r
v
is
u
alizi
n
g
th
e
s
p
r
ea
d
o
f
k
e
y
wo
r
d
s
th
at
o
f
te
n
ap
p
ea
r
in
a
s
en
te
n
ce
.
I
n
th
i
s
ca
s
e,
t
h
e
s
p
r
ea
d
o
f
p
o
s
itiv
e
a
n
d
n
e
g
ati
v
e
w
o
r
d
s
t
h
at
u
s
u
all
y
ar
i
s
es
f
r
o
m
T
F
-
I
DF.
T
h
e
Fig
u
r
e
8
w
o
r
d
clo
u
d
is
o
b
tain
ed
b
ased
o
n
th
e
to
tal
w
ei
g
h
t
o
f
t
h
e
T
F
-
I
DF
r
esu
l
ts
t
h
at
h
a
v
e
b
ee
n
r
u
n
w
h
e
n
p
r
ep
r
o
ce
s
s
in
g
f
o
r
p
o
s
itiv
e
an
d
n
eg
at
iv
e
s
e
n
te
n
ce
s
.
Fig
u
r
e
8
.
W
o
r
d
cl
o
u
d
f
r
o
m
p
o
s
itiv
e
a
n
d
n
eg
a
tiv
e
s
en
te
n
ce
s
3
.
4
.
Appl
ica
t
io
n
B
ased
o
n
t
h
e
e
v
alu
a
tio
n
o
f
t
est
r
es
u
lt
s
a
n
d
m
o
d
el
v
alid
at
io
n
u
s
i
n
g
t
h
e
Naï
v
e
B
a
y
es
a
n
d
SV
M
w
it
h
o
u
t
SMOT
E
,
also
Naïv
e
B
ay
e
s
an
d
SV
M
w
it
h
SM
OT
E
.
I
t
w
as
f
o
u
n
d
t
h
at
th
e
r
esu
lt
s
o
f
te
s
ti
n
g
th
e
h
ig
h
es
t
m
o
d
el
o
f
all
is
SVM
w
it
h
SM
OT
E
.
T
h
er
ef
o
r
e,
th
e
m
o
d
el
w
il
l
b
e
u
s
ed
f
o
r
d
ep
lo
y
m
e
n
t
i
n
to
th
e
ap
p
licatio
n
b
ased
o
n
t
h
e
r
esu
lt
s
te
s
t
f
r
o
m
SVM
w
it
h
S
MO
T
E
.
T
h
e
f
o
llo
w
i
n
g
is
a
f
l
o
w
c
h
ar
t
m
o
d
el
f
o
r
d
ep
lo
y
m
en
t
ap
p
licatio
n
,
o
n
th
e
Fi
g
u
r
e
9
.
E
x
p
lan
at
io
n
o
f
p
ictu
r
e
at
th
e
Fi
g
u
r
e
9
is
s
tar
ts
f
r
o
m
o
p
en
i
n
g
th
e
ap
p
licatio
n
an
d
in
p
u
tti
n
g
t
h
e
t
ex
t
y
o
u
w
a
n
t
to
a
n
al
y
ze
th
e
s
e
n
ti
m
en
t.
A
f
ter
t
h
at
,
it
w
i
ll
e
n
t
er
to
p
r
ep
r
o
ce
s
s
in
g
p
h
ase
1
w
h
ic
h
in
cl
u
d
e
ca
s
e
f
o
ld
i
n
g
,
r
e
m
o
v
e
U
R
L
,
r
e
m
o
v
e
m
en
t
io
n
,
r
e
m
o
v
e
h
a
s
h
ta
g
,
co
n
v
er
t
e
m
o
tio
n
,
co
n
v
er
t e
m
o
tio
n
,
r
e
m
o
v
e
n
u
m
b
er
an
d
p
u
n
ct
u
atio
n
an
d
t
h
e
la
s
t o
n
e
i
s
tr
a
n
s
late
to
E
n
g
lis
h
.
Af
te
r
g
o
in
g
t
h
r
o
u
g
h
p
r
ep
r
o
ce
s
s
in
g
s
ta
g
e
1
,
p
r
o
ce
s
s
in
g
s
ta
g
e
2
w
i
ll
co
n
s
i
s
ts
o
f
T
o
k
en
ize,
Fil
ter
b
y
L
e
n
g
th
,
N
-
Gr
a
m
(
T
r
i
-
g
r
a
m
)
,
Sto
p
w
o
r
d
s
an
d
s
te
m
m
i
n
g
.
T
h
e
n
ex
t
p
r
o
ce
s
s
is
a
lo
ad
d
ata
m
o
d
el
s
tag
e
t
h
at
h
a
s
b
ee
n
p
r
ev
io
u
s
l
y
s
av
ed
af
ter
th
at
i
s
m
ak
e
a
p
r
ed
ictio
n
to
d
eter
m
i
n
e
t
h
e
te
x
t
i
n
p
u
t
i
s
p
o
s
iti
v
e
o
r
n
e
g
ati
v
e.
Fo
r
co
m
p
ar
is
o
n
,
V
A
DE
R
is
u
s
ed
to
lab
el
s
en
ti
m
en
t a
n
al
y
s
i
s
b
as
ed
o
n
th
e
s
co
r
es.
Fig
u
r
e
9
.
Flo
w
c
h
ar
t
d
ep
lo
y
m
e
n
t
m
o
d
el
A
c
c
u
r
a
c
y
P
r
ec
i
sio
n
Rec
a
ll
F1
-
S
c
o
r
e
A
UC
Time
NB
73
.1
2
8%
42
.3
7
3%
31
.1
5
3%
35
.9
0
7%
0.58
8
0.32
m
in
S
V
M
81
.3
7
0%
64
.7
2
9%
50
.3
1
2%
56
.6
1
7%
0.70
8
0.12
m
in
N
B + S
MOT
E
90
.8
4
4%
85
.6
5
9%
98
.1
1
4%
91
.4
6
4%
0.90
8
0.68
m
in
S
V
M
+
S
MO
TE
91
.3
9
0%
86
.1
0
4%
98
.7
1
0%
91
.9
7
7%
0.91
4
0.49
m
in
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
18
1
9
-
1
8
2
7
1826
T
h
e
ap
p
licatio
n
is
b
u
il
t
u
s
i
n
g
th
e
p
y
th
o
n
p
r
o
g
r
a
m
m
i
n
g
lan
g
u
a
g
e
alo
n
g
w
i
t
h
t
h
e
r
eq
u
ir
e
d
lib
r
ar
ies.
Fu
r
t
h
er
m
o
r
e,
th
e
ap
p
licatio
n
th
at
h
as
b
ee
n
u
s
ed
b
ased
o
n
th
e
Fi
g
u
r
e
9
f
lo
w
c
h
ar
t
m
o
d
el
h
as
b
ee
n
b
u
il
t
on
:
h
ttp
s
:/
/an
ali
s
a
-
s
e
n
ti
m
e
n
.
h
er
o
k
u
ap
p
.
co
m
/
.
F
o
r
e
x
a
m
p
le,
w
h
e
n
a
n
al
y
zi
n
g
s
e
n
ti
m
e
n
ts
,
th
e
i
n
p
u
tted
tex
t
s
h
o
w
s
th
e
r
es
u
lt
s
w
h
en
tr
a
n
s
l
ated
,
th
e
r
esu
l
ts
a
f
ter
clea
n
s
i
n
g
,
th
e
r
es
u
lt
s
a
f
ter
b
ein
g
p
r
ep
r
o
ce
s
s
ed
,
th
e
w
ei
g
h
t
d
is
tr
ib
u
tio
n
o
f
w
o
r
d
s
f
r
o
m
t
h
e
in
p
u
tted
te
x
t
a
n
d
f
in
a
ll
y
t
h
e
r
esu
l
ts
o
f
s
en
t
i
m
e
n
t
an
al
y
s
is
f
r
o
m
V
A
DE
R
an
d
SVM
w
i
th
SMOT
E
.
T
h
e
p
ictu
r
e
in
th
e
Fi
g
u
r
e
1
0
is
a
co
m
p
ar
i
s
o
n
o
f
th
e
r
es
u
lt
s
o
f
th
e
s
en
ti
m
en
t
an
al
y
s
i
s
ev
alu
a
tio
n
co
n
d
u
cted
w
h
e
n
m
o
d
elin
g
.
Fig
u
r
e
10
.
C
o
m
p
ar
is
o
n
o
f
s
e
n
t
i
m
e
n
t a
n
al
y
s
is
r
es
u
lt
s
4.
CO
NCLU
SI
O
N
P
r
o
v
id
e
a
s
tate
m
en
t
t
h
at
w
h
a
t
is
ex
p
ec
ted
,
as
s
ta
ted
i
n
t
h
e
"
in
tr
o
d
u
ctio
n
"
ch
ap
ter
ca
n
u
lti
m
atel
y
r
esu
lt
in
"
r
esu
l
ts
a
n
d
d
is
c
u
s
s
io
n
"
ch
ap
ter
,
s
o
t
h
er
e
is
c
o
m
p
atib
il
it
y
.
Mo
r
eo
v
er
,
it
c
an
also
b
e
ad
d
ed
th
e
p
r
o
s
p
ec
t
o
f
t
h
e
d
e
v
elo
p
m
e
n
t
o
f
r
esear
ch
r
e
s
u
l
ts
a
n
d
ap
p
licati
o
n
p
r
o
s
p
ec
ts
o
f
f
u
r
t
h
er
s
t
u
d
ies
i
n
to
t
h
e
n
ex
t
(
b
ased
o
n
r
esu
lt
an
d
d
is
c
u
s
s
io
n
)
.
Af
ter
co
n
d
u
ctin
g
r
esear
c
h
th
r
o
u
g
h
s
ev
er
al
s
tag
e
s
,
co
n
cl
u
s
io
n
s
ca
n
b
e
d
r
a
w
n
to
an
s
w
er
ac
co
r
d
in
g
to
th
e
f
o
r
m
u
la
tio
n
o
f
th
e
p
r
o
b
le
m
in
co
n
d
u
cti
n
g
s
e
n
ti
m
e
n
t
an
al
y
s
i
s
o
f
2
9
3
6
tw
ee
t
d
ata
f
r
o
m
t
h
e
r
es
u
lts
o
f
a
u
to
m
at
ic
lab
elin
g
u
s
in
g
V
ADE
R
t
h
at
SVM
w
it
h
o
v
er
s
a
m
p
li
n
g
i
m
b
alan
ce
d
d
ata
u
s
i
n
g
SMOT
E
is
p
r
o
v
en
to
h
a
v
e
t
h
e
h
i
g
h
e
s
t
p
er
f
o
r
m
an
ce
v
al
u
e
an
d
tak
e
s
s
h
o
r
t
o
f
p
r
o
ce
s
s
i
n
g
ti
m
e
co
m
p
ar
ed
to
Naïv
e
B
a
y
es
alg
o
r
it
h
m
,
Naï
v
e
B
a
y
e
s
w
i
th
SMOT
E
an
d
SVM
i
n
th
e
clas
s
i
f
icatio
n
o
f
t
w
ee
t
s
ab
o
u
t
I
s
la
m
o
p
h
o
b
ia
w
h
e
n
C
h
r
is
tch
u
r
ch
attac
k
.
I
t
is
h
o
p
ed
th
at
f
u
t
u
r
e
r
esear
ch
ca
n
ad
d
class
if
ica
tio
n
m
eth
o
d
s
f
o
r
co
m
p
ar
is
o
n
w
it
h
o
th
er
s
u
p
er
v
i
s
ed
lear
n
in
g
m
et
h
o
d
s
i
n
o
r
d
er
to
o
b
tain
e
v
en
b
etter
p
er
f
o
r
m
a
n
ce
.
T
h
e
ap
p
licat
io
n
o
f
o
t
h
e
r
f
ea
t
u
r
es
ca
n
b
e
co
m
p
ar
ed
lik
e
th
e
d
o
w
n
s
a
m
p
lin
g
m
eth
o
d
,
P
SO,
C
h
i
Sq
u
ar
e,
o
r
an
y
t
h
i
n
g
else
.
T
h
e
ap
p
licatio
n
u
s
e
s
o
th
er
co
r
p
u
s
-
b
ased
f
o
r
au
to
m
at
ic
d
ata
lab
elin
g
s
u
ch
a
s
T
ex
tB
lo
b
,
s
p
aC
y
,
o
r
an
y
t
h
i
n
g
else
.
A
s
w
e
ll
as
th
e
ap
p
licatio
n
u
s
e
o
f
o
th
er
lib
r
ar
ies
f
o
r
tr
an
s
lati
n
g
s
u
c
h
as
g
o
o
g
le
clo
u
n
d
tr
a
n
s
late
to
b
e
ab
le
to
r
ea
d
th
e
U
n
ico
d
e
d
ata
ty
p
e
f
o
r
m
at.
RE
F
E
R
E
NC
E
S
[1
]
G
.
E
v
o
lv
i,
“
Ha
te
in
a
Tw
e
e
t:
Ex
p
lo
rin
g
In
tern
e
t
-
Ba
se
d
Isla
m
o
p
h
o
b
ic
Disc
o
u
rse
s,”
Relig
io
n
s
,
2
0
1
8
.
d
o
i:
1
0
.
3
3
9
0
/rel9
1
0
0
3
0
7
.
[2
]
C.
W
o
o
d
a
n
d
W
.
M
.
L
.
F
in
lay
,
“
Brit
ish
n
a
ti
o
n
a
l
p
a
rty
re
p
re
s
e
n
tatio
n
s
o
f
m
u
slim
s
in
th
e
m
o
n
th
a
f
t
e
r
th
e
L
o
n
d
o
n
b
o
m
b
in
g
s:
Ho
m
o
g
e
n
e
it
y
,
th
re
a
t,
a
n
d
th
e
c
o
n
sp
irac
y
trad
it
io
n
,
”
Br.
J
.
S
o
c
.
Psy
c
h
o
l.
,
v
o
l.
4
7
,
p
p
.
4
0
7
-
26
,
d
o
i:
1
0
.
1
3
4
8
/0
1
4
4
6
6
6
0
7
X2
6
4
1
0
3
.
[3
]
C.
A
ll
e
n
,
“
Brit
a
in
F
irst:
T
h
e
‘F
ro
n
tl
i
n
e
Re
sista
n
c
e
’
to
th
e
Isla
m
i
f
ic
a
ti
o
n
o
f
Brit
a
in
,
”
T
h
e
P
o
li
ti
c
a
l
Qu
a
rte
rly
,
v
o
l.
8
5
,
n
o
.
3
,
2
0
1
4
,
d
o
i:
1
0
.
1
1
1
1
/
1
4
6
7
-
9
2
3
X.1
2
1
1
8
.
[4
]
M
.
Ek
m
a
n
,
“
On
li
n
e
Isla
m
o
p
h
o
b
ia
a
n
d
th
e
p
o
li
ti
c
s
o
f
f
e
a
r:
m
a
n
u
f
a
c
tu
ri
n
g
th
e
g
re
e
n
sc
a
re
,
”
J
o
u
rn
a
lE
t
h
n
ic
a
n
d
Ra
c
i
a
l
S
tu
d
ies
,
v
o
l.
3
8
,
n
o
.
1
1
,
p
p
.
1
9
8
6
-
2
0
0
2
,
2
0
1
4.
[5
]
N.
Ba
k
a
li
,
“
Isla
m
o
p
h
o
b
ia
in
Q
u
e
b
e
c
se
c
o
n
d
a
ry
sc
h
o
o
ls:
In
q
u
iri
e
s
in
to
th
e
e
x
p
e
rien
c
e
s
o
f
m
u
slim
m
a
le
y
o
u
th
p
o
st
-
9
/1
1
,
”
i
n
M
u
slim S
tu
d
e
n
ts,
E
d
u
c
a
t
io
n
a
n
d
Ne
o
li
b
e
ra
li
sm
:
S
c
h
o
o
li
n
g
a
“
S
u
sp
e
c
t
Co
mm
u
n
it
y
,
”
2
0
1
7
.
[6
]
I.
Aw
a
n
a
n
d
I.
Ze
m
p
i,
“
T
h
e
a
ff
i
n
it
y
b
e
t
w
e
e
n
o
n
li
n
e
a
n
d
o
f
f
li
n
e
a
n
ti
-
M
u
slim
h
a
te
c
ri
m
e
:
D
y
n
a
m
ic
s
a
n
d
im
p
a
c
ts,”
Ag
g
re
ss
io
n
a
n
d
Vi
o
le
n
t
Beh
a
v
io
r
,
v
o
l.
2
7
,
n
o
.
1
-
8
,
2
0
1
6
.
[7
]
Nu
rc
h
o
li
s,
“
Du
n
ia S
e
b
u
t
T
e
ro
r
M
a
sjid
Ke
m
b
a
r
S
e
lan
d
ia Baru
D
a
m
p
a
k
Isla
m
o
p
h
o
b
ia,
in
Ba
h
a
sa
:
T
h
e
W
o
rld
Ca
ll
e
d
th
e
T
e
rro
r
o
f
th
e
T
w
in
T
o
w
e
rs o
f
Ne
w
Zea
lan
d
th
e
Im
p
a
c
t
o
f
Isla
m
o
p
h
o
b
ia,
”
In
d
o
n
e
sia
in
si
d
e
.
id
,
2
0
1
9
.
[8
]
A
.
Bro
w
n
,
“
W
h
a
t
is
so
sp
e
c
ial
a
b
o
u
t
o
n
li
n
e
(a
s
c
o
m
p
a
re
d
to
o
f
f
li
n
e
)
h
a
te
sp
e
e
c
h
?
,
”
Et
h
n
iciti
e
s
,
2
0
1
8
.
d
o
i:
1
0
.
1
1
7
7
/1
4
6
8
7
9
6
8
1
7
7
0
9
8
4
6
.
[9
]
B.
L
iu
,
"
S
e
n
ti
me
n
t
An
a
lys
is:
A
F
a
sc
in
a
ti
n
g
Pr
o
b
lem
,"
S
y
n
th
e
sis L
e
c
tu
re
s o
n
H
u
ma
n
L
a
n
g
u
a
g
e
T
e
c
h
n
il
o
g
ies
,
2
0
1
2
.
[1
0
]
B.
V
i
d
g
e
n
a
n
d
T
.
Ya
ss
e
ri,
“
De
tec
ti
n
g
we
a
k
a
n
d
stro
n
g
Isla
m
o
p
h
o
b
ic
h
a
te
sp
e
e
c
h
o
n
so
c
ial
m
e
d
ia,”
J
o
u
rn
a
l
o
f
In
fo
rm
a
t
io
n
T
e
c
h
n
o
l
o
g
y
&
Po
li
ti
c
s,
v
o
l.
1
7
,
n
o
.
1
,
p
p
.
6
6
-
7
8
,
2
0
1
9
.
[1
1
]
K.
Da
rw
ish
,
W
.
M
a
g
d
y
,
A
.
Ra
h
im
i,
T
.
Ba
ld
w
in
,
a
n
d
N.
A
b
o
k
h
o
d
a
ir,
“
P
re
d
icti
n
g
On
l
in
e
Isla
m
o
p
h
o
b
ic
Be
h
a
v
io
r
a
f
ter #
P
a
risA
tt
a
c
k
s,”
J
.
W
e
b
S
c
i.
,
v
o
l.
4
,
n
o
.
2
,
p
p
.
3
4
-
5
2
,
2
0
1
8
.
[1
2
]
J.
Ra
m
te
k
e
,
S
.
S
h
a
h
,
D.
G
o
d
h
ia,
a
n
d
A
.
S
h
a
ik
h
,
“
El
e
c
ti
o
n
re
su
lt
p
re
d
ictio
n
u
sin
g
T
w
it
ter
se
n
ti
m
e
n
t
a
n
a
l
y
sis,”
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
n
a
lysi
s
s
en
timen
t a
b
o
u
t
is
la
mo
p
h
o
b
i
a
w
h
en
C
h
r
is
tch
u
r
ch
a
tta
ck
o
n
s
o
cia
l m
e
d
ia
(
W
in
d
u
Ga
ta
)
1827
2
0
1
6
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
In
v
e
n
ti
v
e
Co
mp
u
t
a
ti
o
n
T
e
c
h
n
o
lo
g
ies
(
ICICT
)
,
p
p
.
1
-
5,
2
0
1
6
.
[1
3
]
A
.
B
a
y
h
a
q
y
,
S
f
e
n
rian
to
,
K.
Na
in
g
g
o
lan
,
a
n
d
E.
Ka
b
u
ru
a
n
,
“
S
e
n
ti
m
e
n
t
A
n
a
l
y
sis
a
b
o
u
t
E
-
Co
m
m
e
r
c
e
f
ro
m
Twe
e
ts
Us
in
g
De
c
isio
n
T
re
e
,
K
-
Ne
a
re
st
Ne
ig
h
b
o
r
,
a
n
d
Na
ïv
e
B
a
y
e
s,”
2
0
1
8
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Or
a
n
g
e
T
e
c
h
n
o
l
o
g
ies
(
ICOT)
,
2
0
1
8
.
[1
4
]
N.
D.
P
ra
tam
a
,
Y.
A
.
S
a
ri,
a
n
d
P
.
P
.
A
d
ik
a
ra
,
“
A
n
a
li
sis
S
e
n
ti
m
e
n
P
a
d
a
Re
v
iew
Ko
n
su
m
e
n
M
e
n
g
g
u
n
a
k
a
n
M
e
to
d
e
Na
ïv
e
Ba
y
e
s
D
e
n
g
a
n
S
e
lek
si
F
it
u
r
Ch
i
S
q
u
a
re
Un
tu
k
Re
k
o
m
e
n
d
a
si
L
o
k
a
si
M
a
k
a
n
a
n
T
r
a
d
isio
n
a
l,
in
Ba
h
a
sa
:
S
e
n
ti
m
e
n
t
A
n
a
l
y
sis
o
n
Co
n
s
u
m
e
r
Re
v
ie
w
s
U
sin
g
th
e
Na
ïv
e
Ba
y
e
s
M
e
th
o
d
w
it
h
Ch
i
S
q
u
a
re
F
e
a
tu
re
S
e
lec
ti
o
n
f
o
r
Re
c
o
m
m
e
n
d
e
d
L
o
c
a
ti
o
n
s
o
f
T
ra
d
it
io
n
a
l
F
o
o
d
s,
”
J
.
Pen
g
e
mb
.
T
e
k
n
o
l.
I
n
f.
d
a
n
Ilmu
K
o
mp
u
t.
U
n
iv.
Bra
wij
a
y
a
,
v
o
l.
2
,
n
o
.
9
,
p
p
.
2
9
8
2
-
2
9
8
8
,
2
0
1
8
.
[1
5
]
A
.
C.
F
lo
re
s,
R.
I.
Ic
o
y
,
C.
F
.
P
e
n
a
,
a
n
d
K.
D.
G
o
rro
,
“
A
n
Ev
a
lu
a
ti
o
n
o
f
S
V
M
a
n
d
Na
ïv
e
Ba
y
e
s
w
it
h
S
M
OT
E
on
S
e
n
ti
m
e
n
t
A
n
a
l
y
sis
D
a
ta
S
e
t,
”
2
0
1
8
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
En
g
i
n
e
e
rin
g
,
A
p
p
li
e
d
S
c
ien
c
e
s,
a
n
d
T
e
c
h
n
o
lo
g
y
(
ICEA
S
T
)
,
p
p
.
1
-
4,
2
0
1
8
.
[1
6
]
K.
A
.
Be
y
d
o
u
n
,
"
Am
e
ric
a
n
Isla
m
o
p
h
o
b
ia:
Un
d
e
rsta
n
d
in
g
th
e
Ro
o
t
s
a
n
d
Rise
o
f
F
e
a
r,
1
st
e
d
,"
Oa
k
l
a
n
d
:
Un
ive
rs
it
y
o
f
Ca
li
fo
r
n
ia
Pre
ss
,
2
0
1
8
.
[1
7
]
N.
M
.
S
.
Ha
d
n
a
,
P
.
I.
S
a
n
t
o
sa
,
a
n
d
W
.
W
.
W
in
a
rn
o
,
“
S
tu
d
i
L
it
e
ra
tu
r
T
e
n
tan
g
P
e
rb
a
n
d
in
g
a
n
M
e
t
o
d
e
u
n
t
u
k
P
r
o
se
s
A
n
a
li
sis
S
e
n
ti
m
e
n
d
i
Tw
it
ter,
in
Ba
h
a
sa
:
L
it
e
ra
tu
re
S
tu
d
y
o
f
Co
m
p
a
ra
ti
v
e
M
e
th
o
d
s
f
o
r
S
e
n
ti
m
e
n
t
A
n
a
l
y
si
s
P
ro
c
e
ss
o
n
T
w
it
ter
”
S
e
min
.
Na
s.
T
e
k
n
o
l
.
I
n
f.
d
a
n
Ko
m
u
n
.
, v
o
l.
2
0
1
6
,
n
o
.
S
e
n
ti
k
a
,
p
p
.
5
7
-
6
4
,
2
0
1
6
.
[1
8
]
E.
T
.
L
.
Ku
srin
i,
"
A
l
g
o
rit
m
a
D
a
ta
M
in
i
n
g
,"
Y
o
g
y
a
k
a
rta
:
An
d
i
,
2
0
0
9
.
[1
9
]
T
.
Jo
,
"
T
e
x
t
M
in
in
g
C
o
n
c
e
p
ts,
Im
p
lem
e
n
tatio
n
,
a
n
d
Big
Da
ta Ch
a
ll
e
n
g
e
,"
S
tu
d
ies
i
n
Bi
g
Da
t
a
,
2
0
1
9
.
[2
0
]
S
.
S
y
m
e
o
n
id
is,
“
5
T
h
in
g
s Yo
u
Ne
e
d
to
K
n
o
w
a
b
o
u
t
S
e
n
ti
m
e
n
t
A
n
a
l
y
sis a
n
d
Clas
sif
ica
ti
o
n
,
”
KDn
u
g
g
e
ts,
2
0
1
8
.
[2
1
]
C.
J.
Hu
tt
o
,
“
V
A
DER
-
S
e
n
ti
m
e
n
t
-
A
n
a
l
y
sis,”
E
ig
h
th
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
W
e
b
lo
g
s
a
n
d
S
o
c
ia
l
M
e
d
i
a
(
ICW
S
M
-
14)
,
2
0
1
4
.
[2
2
]
A
lb
e
rto
F
e
rn
a
n
d
e
z
,
S
a
lv
a
d
o
r
Ga
r
c
ia,
F
ra
n
c
isc
o
He
rre
ra
,
a
n
d
N
it
e
sh
V
.
C
h
a
w
la,
“
S
M
OT
E
f
o
r
L
e
a
rn
in
g
f
ro
m
Im
b
a
lan
c
e
d
Da
t
a
:
P
ro
g
re
ss
a
n
d
C
h
a
ll
e
n
g
e
s,
M
a
rk
in
g
th
e
1
5
-
y
e
a
r
A
n
n
iv
e
rsa
r
y
,
”
J
.
Arti
f.
In
tell.
Res
.
,
v
o
l.
6
1
,
n
o
.
1
,
p
p
.
8
6
3
-
9
0
5
,
2
0
1
8
.
[2
3
]
S
.
R.
W
ica
k
so
n
o
,
"
S
tu
d
i
Ka
su
s
S
iste
m
Be
rb
a
sis
P
e
n
g
e
tah
u
a
n
:
M
e
m
b
a
h
a
s
M
e
to
d
e
ID3
,
Na
ïv
e
Ba
y
e
s
d
a
n
Ce
rtain
ty
F
a
c
to
r
,
in
Ba
h
a
sa
:
Ca
se
S
tu
d
y
o
f
Kn
o
w
led
g
e
Ba
s
e
d
S
y
ste
m
s:
Disc
u
ss
e
s
th
e
ID3
M
e
th
o
d
,
Na
ïv
e
Ba
y
e
s
a
n
d
Ce
rtain
ty
F
a
c
to
r,
"
S
e
rib
u
Bin
tan
g
,
2
0
1
8
.
[2
4
]
R.
M
.
G
a
b
a
Ig
n
a
to
w
,
"
A
n
In
tro
d
u
c
t
io
n
to
T
e
x
t
M
in
in
g
:
Re
se
a
rc
h
De
sig
n
,
Da
ta
Co
ll
e
c
ti
o
n
a
n
d
A
n
a
ly
sis
,
"
Un
it
e
d
S
ta
tes
o
f
A:
S
AGE
Pu
b
li
c
a
ti
o
n
s,
In
c
,
2
0
1
7
.
[2
5
]
N.
K.
W
a
rd
h
a
n
i
e
t
a
l.
,
“
S
e
n
ti
m
e
n
t
a
n
a
ly
sis
a
rti
c
le
n
e
w
s
c
o
o
rd
in
a
to
r
m
in
ister
o
f
m
a
rit
i
m
e
a
ff
a
irs
u
sin
g
a
lg
o
rit
h
m
Na
ïv
e
b
a
y
e
s
a
n
d
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
w
it
h
p
a
rti
c
le
sw
a
r
m
o
p
ti
m
iz
a
ti
o
n
,
”
J
.
T
h
e
o
r.
Ap
p
l.
In
f
.
T
e
c
h
n
o
l
.
,
v
o
l
.
9
6
,
n
o
.
2
4
,
p
p
.
8
3
6
5
-
8
3
7
8
,
2
0
1
8
.
[2
6
]
V
.
Ko
t
u
a
n
d
B
.
De
sh
p
a
n
d
e
,
"
P
r
e
d
ictiv
e
A
n
a
l
y
ti
c
s
a
n
d
Da
ta
M
i
n
in
g
:
Co
n
c
e
p
ts
a
n
d
P
ra
c
ti
c
e
w
it
h
Ra
p
id
M
in
e
r
,"
M
o
rg
a
n
Ka
u
fma
n
n
,
2
0
1
5
.
[2
7
]
K.
S
ig
it
,
A
.
P
.
De
w
i,
G
.
W
in
d
u
,
Nu
rm
a
las
a
ri,
T
.
M
u
h
a
m
a
d
,
a
n
d
N.
Ka
d
in
a
r,
“
Co
m
p
a
riso
n
Of
Clas
si
f
ic
a
ti
o
n
M
e
th
o
d
s
On
S
e
n
ti
m
e
n
t
A
n
a
l
y
sis
O
f
P
o
li
ti
c
a
l
F
ig
u
re
El
e
c
tab
il
it
y
Ba
se
d
On
P
u
b
li
c
Co
m
m
e
n
ts
On
On
li
n
e
Ne
w
s
M
e
d
ia S
it
e
s,”
IOP
C
o
n
fer
e
n
c
e
S
e
rie
s: M
a
ter
ia
ls S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
,
v
o
l.
6
6
2
,
n
o
.
4
,
2
0
1
9
.
[
28]
Evaluation Warning : The document was created with Spire.PDF for Python.