I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
14
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
5
,
p
p
.
447
~
456
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
14
.i
1
.
p
p
4
4
7
-
4
5
6
447
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
User sen
timent
d
y
na
mics
in
so
cia
l media
:
a
com
pa
r
a
tive
a
na
ly
sis
of X
a
nd
Threa
ds
Rez
k
i K
ha
irunn
a
s
,
J
er
i A
pri
a
ns
y
a
h P
a
g
ua
,
G
hin
a
F
it
riy
a
,
Yo
v
a
Ruld
ev
iy
a
ni
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
m
a
t
i
o
n
Te
c
h
n
o
l
o
g
y
,
F
a
c
u
l
t
y
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
U
n
i
v
e
r
si
t
y
o
f
I
n
d
o
n
e
si
a
,
J
a
k
a
r
t
a
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
17
,
2
0
2
4
R
ev
is
ed
Oct
12
,
2
0
2
4
Acc
ep
ted
Oct
18
,
2
0
2
4
Th
is
re
se
a
rc
h
e
x
a
m
in
e
s
th
e
d
y
n
a
m
ics
o
f
u
se
r
se
n
ti
m
e
n
t
a
n
d
it
s
c
o
rre
l
a
ti
o
n
wit
h
th
e
u
sa
g
e
fa
c
to
rs
o
f
a
p
p
l
ica
ti
o
n
s
i
n
th
e
c
o
n
tex
t
o
f
t
h
e
c
o
m
p
e
ti
ti
o
n
b
e
twe
e
n
X
(fo
rm
e
rly
Twit
ter)
a
n
d
T
h
re
a
d
s,
a
so
c
ial
m
e
d
ia
a
p
p
li
c
a
ti
o
n
u
n
d
e
r
th
e
u
m
b
re
ll
a
o
f
M
e
ta.
T
h
ro
u
g
h
se
n
t
ime
n
t
a
n
a
ly
sis
o
f
u
se
r
re
v
iew
s
o
n
t
h
e
G
o
o
g
le
P
lay
S
t
o
re
a
n
d
Ap
p
S
to
re
,
t
h
e
stu
d
y
a
ims
to
id
e
n
t
ify
t
h
e
k
e
y
fa
c
to
rs
c
o
n
tr
ib
u
ti
n
g
to
a
sig
n
ifi
c
a
n
t
d
e
c
li
n
e
i
n
u
se
r
e
n
g
a
g
e
m
e
n
t
with
T
h
re
a
d
s
a
n
d
t
h
e
re
tu
r
n
o
f
u
se
rs
to
X.
Th
e
m
e
th
o
d
e
m
p
l
o
y
e
d
i
n
th
is
re
se
a
rc
h
is
th
e
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
i
n
e
(S
VM)
fo
r
se
n
t
ime
n
t
c
las
sifica
ti
o
n
o
f
re
v
i
e
ws
.
Th
e
st
u
d
y
th
e
n
c
o
rre
late
s
th
e
c
las
sified
se
n
ti
m
e
n
ts
with
a
p
p
li
c
a
ti
o
n
u
sa
g
e
fa
c
to
rs:
u
sa
b
il
it
y
,
fe
a
tu
re
s,
d
e
sig
n
,
a
n
d
su
p
p
o
rt.
Th
e
re
se
a
rc
h
fin
d
i
n
g
s
in
d
ica
te
u
se
r
se
n
ti
m
e
n
t
i
n
fl
u
e
n
c
e
s
u
se
r
e
n
g
a
g
e
m
e
n
t,
e
sp
e
c
iall
y
in
fe
a
tu
re
s
a
n
d
d
e
sig
n
.
Th
e
re
se
a
rc
h
c
o
n
c
lu
d
e
s
with
in
sig
h
ts
re
g
a
rd
in
g
imp
li
c
a
ti
o
n
s
fo
r
a
p
p
li
c
a
ti
o
n
d
e
v
e
lo
p
e
rs
a
n
d
su
g
g
e
sts
d
irec
ti
o
n
s f
o
r
f
u
tu
re
re
se
a
rc
h
.
K
ey
w
o
r
d
s
:
C
o
r
r
elatio
n
Sen
tim
en
t a
n
aly
s
is
So
cial
m
ed
ia
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
T
h
r
ea
d
s
X
(
T
witter
)
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
:
R
ez
k
i K
h
air
u
n
n
as
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atio
n
T
e
ch
n
o
lo
g
y
,
Facu
lty
o
f
C
o
m
p
u
te
r
Scien
ce
,
Un
iv
er
s
ity
o
f
I
n
d
o
n
esia
Ken
ar
i 2
St.
No
.
4
,
R
W
.
5
,
J
ak
ar
ta
Pu
s
at,
DKI
J
ak
ar
ta,
I
n
d
o
n
e
s
ia
E
m
ail: r
ez
k
i.k
h
air
u
n
n
as@
u
i.a
c.
id
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
d
i
g
ital
ag
e
h
as
s
ee
n
n
u
m
e
r
o
u
s
s
o
cial
m
ed
ia
p
latf
o
r
m
s
r
i
s
e
an
d
f
all,
ea
c
h
v
y
in
g
f
o
r
a
s
h
ar
e
o
f
t
h
e
g
lo
b
al
u
s
er
b
ase.
On
J
u
ly
5
,
2
0
2
3
,
th
e
s
o
cial
m
ed
ia
lan
d
s
ca
p
e
witn
ess
ed
th
e
lau
n
c
h
o
f
T
h
r
ea
d
s
,
a
n
ew
p
latf
o
r
m
d
ev
elo
p
e
d
b
y
Me
ta
aim
ed
at
c
h
allen
g
in
g
th
e
d
o
m
in
an
ce
o
f
X
(
f
o
r
m
er
ly
T
witter
)
.
X,
wh
ich
E
lo
n
Mu
s
k
ac
q
u
ir
ed
in
Octo
b
er
2
0
2
2
,
h
a
d
lo
n
g
b
e
en
a
c
r
itical
p
lay
er
in
o
n
lin
e
p
u
b
lic
d
is
co
u
r
s
e
[
1
]
.
T
h
e
in
tr
o
d
u
ctio
n
o
f
T
h
r
ea
d
s
was
s
ee
n
as
a
s
tr
ateg
ic
m
o
v
e
b
y
Me
ta
C
E
O
Ma
r
k
Z
u
ck
e
r
b
e
r
g
to
ca
p
italize
o
n
th
e
p
e
r
ce
iv
ed
v
u
l
n
er
ab
ilit
ies
o
f
X
an
d
to
f
u
lf
il
th
e
am
b
itio
n
o
f
cr
ea
tin
g
a
p
latf
o
r
m
th
at
co
u
ld
h
o
s
t
p
u
b
lic
co
n
v
er
s
atio
n
s
o
n
a
s
ca
le
ex
ce
ed
in
g
a
b
illi
o
n
u
s
er
s
.
T
h
r
ea
d
s
m
ad
e
an
im
p
r
ess
iv
e
d
eb
u
t,
r
ea
ch
in
g
u
n
p
r
ec
ed
e
n
ted
m
iles
to
n
es
in
u
s
er
ac
q
u
is
itio
n
.
W
ith
in
f
o
u
r
h
o
u
r
s
o
f
its
r
elea
s
e,
t
h
e
a
p
p
licatio
n
h
ad
b
ee
n
d
o
wn
l
o
ad
ed
f
iv
e
m
illi
o
n
tim
es,
an
d
b
y
J
u
ly
1
0
,
2
0
2
3
,
it
h
ad
am
ass
ed
1
0
0
m
illi
o
n
u
s
er
s
[
2
]
.
T
h
is
ex
p
lo
s
iv
e
g
r
o
wth
s
u
r
p
ass
ed
r
ec
o
r
d
h
o
ld
e
r
s
lik
e
T
ik
T
o
k
an
d
C
h
atGPT
,
m
ar
k
in
g
T
h
r
ea
d
s
as
h
is
to
r
y
'
s
f
astes
t
-
g
r
o
win
g
s
o
cial
m
ed
ia
p
latf
o
r
m
.
T
h
e
r
ap
i
d
ad
o
p
tio
n
o
f
T
h
r
ea
d
s
was
f
u
r
th
er
f
u
eled
b
y
d
is
co
n
ten
t
am
o
n
g
X
u
s
er
s
,
wh
o
wer
e
d
is
en
ch
a
n
ted
with
E
l
o
n
Mu
s
k
'
s
co
n
tr
o
v
er
s
ial
p
o
licies
[
2
]
,
in
clu
d
in
g
lim
itatio
n
s
o
n
twee
t
v
is
ib
ilit
y
,
th
e
in
tr
o
d
u
ctio
n
o
f
p
aid
v
er
if
icatio
n
,
a
n
d
f
r
e
q
u
en
t
a
p
p
licatio
n
g
litch
es.
Desp
ite
its
in
itial
s
u
cc
ess
,
T
h
r
ea
d
s
ex
p
er
ie
n
ce
d
a
s
teep
d
ec
li
n
e
in
u
s
er
en
g
a
g
em
en
t.
R
ep
o
r
t
s
in
d
icate
d
th
at
th
e
d
aily
ac
tiv
e
u
s
er
co
u
n
t
h
alv
ed
with
in
j
u
s
t
two
wee
k
s
o
f
its
p
ea
k
,
a
n
d
b
y
Au
g
u
s
t
7
,
2
0
2
3
,
th
e
av
er
a
g
e
d
aily
u
s
ag
e
tim
e
h
a
d
p
lu
m
m
eted
to
a
m
er
e
th
r
ee
m
i
n
u
tes
p
er
u
s
er
[
3
]
.
I
n
s
tar
k
c
o
n
tr
a
s
t,
X
d
em
o
n
s
tr
ated
r
esil
ien
ce
,
m
ain
tain
in
g
a
s
tead
y
b
ase
o
f
1
0
0
m
illi
o
n
d
aily
ac
ti
v
e
u
s
er
s
with
an
av
er
ag
e
u
s
ag
e
tim
e
o
f
2
5
m
in
u
tes.
T
h
is
r
esear
ch
s
ee
k
s
to
u
n
r
a
v
el
th
e
co
m
p
lex
d
y
n
a
m
ics o
f
u
s
er
s
en
tim
en
t in
t
h
e
f
a
ce
o
f
t
h
e
c
o
m
p
etitio
n
b
etwe
en
X
an
d
T
h
r
ea
d
s
.
I
t
a
im
s
to
id
en
tify
th
e
f
ac
to
r
s
co
n
tr
ib
u
tin
g
to
th
e
d
r
am
atic
f
lu
ctu
atio
n
s
in
u
s
er
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
5
:
447
-
4
5
6
448
en
g
ag
em
e
n
t
o
b
s
er
v
e
d
with
T
h
r
ea
d
s
an
d
to
u
n
d
e
r
s
tan
d
wh
y
u
s
er
s
r
etu
r
n
to
X.
T
h
is
s
tu
d
y
will
an
aly
ze
u
s
er
r
ev
iews
f
r
o
m
th
e
Go
o
g
le
Play
Sto
r
e
an
d
Ap
p
Sto
r
e
u
s
in
g
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM
)
f
o
r
s
en
tim
e
n
t
class
if
icatio
n
,
co
r
r
elatin
g
th
e
class
if
ied
s
en
tim
en
ts
with
v
ar
io
u
s
ap
p
licatio
n
u
s
ag
e
f
ac
to
r
s
,
in
clu
d
in
g
u
s
ab
ilit
y
,
f
ea
tu
r
es,
d
esig
n
,
a
n
d
s
u
p
p
o
r
t.
T
h
e
m
o
t
iv
ati
o
n
f
o
r
t
h
is
r
es
ea
r
ch
s
t
em
s
f
r
o
m
t
h
e
n
ee
d
t
o
c
o
m
p
r
e
h
en
d
t
h
e
s
h
if
ti
n
g
la
n
d
s
ca
p
e
o
f
s
o
cia
l
m
e
d
ia
u
s
e
r
e
n
g
a
g
e
m
e
n
t
.
P
r
e
v
io
u
s
s
o
cia
l
m
e
d
i
a
s
e
n
ti
m
e
n
t
an
al
y
s
is
r
ese
ar
ch
h
as
p
r
im
ar
il
y
f
o
c
u
s
ed
o
n
u
s
er
s
atis
f
ac
ti
o
n
a
n
d
p
la
tf
o
r
m
g
r
o
wt
h
.
H
o
we
v
e
r
,
t
h
e
r
e
is
a
g
a
p
in
u
n
d
e
r
s
t
an
d
i
n
g
t
h
e
r
a
p
i
d
c
h
an
g
es
i
n
u
s
e
r
en
g
ag
em
en
t
an
d
t
h
e
r
o
le
o
f
s
e
n
t
im
e
n
t
i
n
c
o
m
p
eti
ti
v
e
d
y
n
a
m
ics
b
etw
ee
n
p
l
atf
o
r
m
s
.
B
y
d
e
lv
in
g
in
to
u
s
er
s
en
t
im
en
t,
t
h
is
s
t
u
d
y
aim
s
t
o
s
h
e
d
li
g
h
t
o
n
t
h
e
c
o
m
p
etiti
o
n
d
y
n
a
m
i
cs
b
etw
ee
n
X
a
n
d
T
h
r
ea
d
s
,
o
f
f
e
r
i
n
g
in
s
ig
h
ts
i
n
t
o
t
h
e
e
le
m
e
n
ts
t
h
a
t
d
r
iv
e
u
s
e
r
p
r
e
f
e
r
e
n
ce
s
a
n
d
b
eh
av
i
o
u
r
s
.
T
h
e
f
i
n
d
i
n
g
s
a
r
e
e
x
p
e
cte
d
t
o
p
r
o
v
id
e
v
al
u
a
b
l
e
g
u
i
d
a
n
c
e
f
o
r
s
o
cial
m
e
d
i
a
ap
p
li
ca
ti
o
n
d
e
v
e
lo
p
er
s
,
e
n
a
b
li
n
g
t
h
e
m
to
en
h
a
n
ce
p
r
o
d
u
ct
q
u
al
ity
a
n
d
u
s
e
r
e
x
p
er
ie
n
c
e,
t
h
e
r
eb
y
f
o
s
t
er
in
g
a
d
e
ep
er
u
n
d
er
s
ta
n
d
i
n
g
o
f
t
h
e
f
ac
to
r
s
i
n
f
l
u
e
n
c
in
g
u
s
er
e
n
g
a
g
em
en
t i
n
t
h
e
s
o
ci
al
m
e
d
i
a
d
o
m
ai
n
.
2.
L
I
T
E
R
AT
U
RE
S
T
UD
I
E
S
T
h
is
liter
atu
r
e
r
ev
iew
p
r
o
v
id
es
a
co
m
p
r
eh
en
s
iv
e
o
v
er
v
iew
o
f
s
en
tim
en
t
an
aly
s
is
an
d
te
x
t
m
in
in
g
,
s
p
ec
if
ically
f
o
cu
s
in
g
o
n
t
h
eir
ap
p
licatio
n
in
i
d
en
tify
in
g
f
ac
t
o
r
s
in
f
lu
en
ci
n
g
th
e
d
ec
lin
e
in
u
s
ag
e
o
f
t
h
e
T
h
r
ea
d
s
s
o
cial
m
ed
ia
ap
p
licatio
n
.
T
h
r
o
u
g
h
a
n
u
n
d
er
s
tan
d
in
g
o
f
th
e
s
e
cr
itical
co
n
ce
p
ts
,
th
is
r
esear
ch
aim
s
to
p
r
o
v
id
e
in
-
d
ep
th
in
s
ig
h
ts
in
to
th
e
latest
tr
en
d
s
an
d
ch
allen
g
es
in
s
en
tim
en
t
an
aly
s
is
in
th
e
co
n
tin
u
o
u
s
ly
ev
o
lv
in
g
er
a
o
f
s
o
cial
m
ed
ia.
Fu
r
th
er
m
o
r
e,
p
r
ev
io
u
s
s
tu
d
ies
d
is
cu
s
s
in
g
S
VM
an
d
Naiv
e
B
ay
es
m
et
h
o
d
s
will
b
e
b
r
ief
ly
ex
p
lain
ed
to
estab
lis
h
a
f
o
u
n
d
atio
n
al
u
n
d
e
r
s
tan
d
in
g
f
o
r
t
h
is
r
esear
ch
.
2
.
1
.
Sentim
ent
a
na
ly
s
is
Sen
tim
e
n
t
a
n
al
y
s
is
,
al
te
r
n
ati
v
ely
r
ef
er
r
ed
t
o
as
o
p
i
n
i
o
n
m
i
n
i
n
g
,
co
n
s
t
it
u
tes
a
d
o
m
ai
n
o
f
r
es
ea
r
c
h
f
o
c
u
s
i
n
g
o
n
e
x
a
m
i
n
i
n
g
i
n
d
iv
id
u
als'
v
iew
p
o
i
n
ts
,
e
v
a
lu
ati
o
n
s
,
a
p
p
r
aisa
ls
,
j
u
d
g
m
en
ts
,
p
e
r
s
p
ec
ti
v
es
,
a
n
d
e
m
o
ti
o
n
al
r
es
p
o
n
s
es
c
o
n
ce
r
n
i
n
g
v
ar
io
u
s
e
n
ti
ties
,
i
n
cl
u
d
i
n
g
b
u
t
n
o
t
li
m
i
te
d
t
o
p
r
o
d
u
cts
,
s
e
r
v
ices
,
o
r
g
a
n
i
z
ati
o
n
s
,
i
n
d
i
v
i
d
u
als
,
is
s
u
es
,
e
v
en
ts
,
to
p
i
cs,
a
n
d
th
ei
r
r
es
p
e
cti
v
e
c
h
a
r
a
c
te
r
is
t
ics
.
T
h
e
f
ie
ld
o
f
s
e
n
t
im
en
t
a
n
a
ly
s
is
e
n
c
o
m
p
ass
es
a
d
i
v
er
s
e
ar
r
a
y
o
f
c
o
n
ce
r
n
s
.
M
o
r
e
o
v
e
r
,
n
u
m
er
o
u
s
t
er
m
s
e
x
is
t
al
o
n
g
s
id
e
s
lig
h
t
ly
v
a
r
i
e
d
o
b
j
ec
t
iv
es,
e
n
c
o
m
p
ass
i
n
g
s
e
n
ti
m
e
n
t
an
al
y
s
is
,
o
p
i
n
i
o
n
m
i
n
i
n
g
,
o
p
i
n
io
n
e
x
t
r
ac
t
io
n
,
s
e
n
t
im
en
t
m
i
n
i
n
g
,
s
u
b
j
ec
ti
v
it
y
a
n
a
ly
s
is
,
a
f
f
ec
t
a
n
al
y
s
is
,
em
o
t
io
n
an
al
y
s
is
,
an
d
r
e
v
i
ew
m
in
in
g
[
4
]
.
S
en
tim
e
n
t
a
n
a
ly
s
is
h
as
b
ec
o
m
e
c
r
u
ci
al
i
n
g
ai
n
i
n
g
i
n
s
i
g
h
ts
f
r
o
m
s
o
ci
al
n
et
wo
r
k
s
[
5
]
.
M
ac
h
i
n
e
lea
r
n
i
n
g
-
d
r
i
v
e
n
s
en
t
im
en
t
a
n
a
l
y
s
is
t
ec
h
n
i
q
u
es,
lik
e
SVM
cl
ass
i
f
ic
ati
o
n
,
h
av
e
d
e
m
o
n
s
tr
ate
d
t
h
ei
r
ef
f
ic
ac
y
.
Fe
at
u
r
e
s
el
ec
t
io
n
s
t
r
at
e
g
ies
h
a
v
e
b
ee
n
e
m
p
l
o
y
e
d
t
o
b
o
ls
te
r
m
o
d
el
e
f
f
ec
ti
v
e
n
ess
a
n
d
s
tr
ea
m
li
n
e
o
p
e
r
at
io
n
s
,
am
o
n
g
w
h
i
ch
t
h
e
c
h
i
-
s
q
u
ar
e
m
e
th
o
d
s
ta
n
d
s
o
u
t
as
a
f
r
e
q
u
e
n
t
ly
u
til
iz
ed
a
p
p
r
o
ac
h
[
6
]
.
2
.
2
.
T
ex
t
m
ining
T
e
x
t
m
i
n
i
n
g
in
v
o
l
v
es
u
n
c
o
v
er
i
n
g
p
at
te
r
n
s
o
r
e
x
t
r
ac
t
in
g
in
f
o
r
m
at
io
n
f
r
o
m
l
ar
g
e
-
s
ca
l
e
te
x
t
d
at
a,
en
co
m
p
ass
i
n
g
u
n
s
t
r
u
c
tu
r
e
d
o
r
s
em
i
-
s
t
r
u
ct
u
r
e
d
f
o
r
m
ats
.
I
t
r
ep
r
ese
n
ts
a
p
r
e
v
al
e
n
t
a
p
p
li
ca
t
io
n
o
f
d
ata
m
i
n
i
n
g
,
o
f
te
n
u
ti
liz
ed
f
o
r
tas
k
s
s
u
c
h
as
te
x
t
cl
u
s
t
er
in
g
,
ca
t
eg
o
r
iz
ati
o
n
a
n
a
ly
s
is
,
an
d
s
e
n
ti
m
e
n
t
e
v
al
u
ati
o
n
.
T
h
e
t
ex
t
m
i
n
i
n
g
wo
r
k
f
l
o
w
t
y
p
ic
all
y
e
n
c
o
m
p
as
s
es
m
u
lti
p
l
e
s
t
ag
es,
i
n
c
lu
d
i
n
g
f
e
at
u
r
e
s
el
ec
t
io
n
,
t
e
x
t
r
e
p
r
ese
n
ta
ti
o
n
,
a
n
d
t
h
e
u
ti
liz
ati
o
n
o
f
v
a
r
i
o
u
s
te
x
t
m
i
n
i
n
g
m
et
h
o
d
o
lo
g
i
es
[
4
]
.
Ac
co
r
d
i
n
g
t
o
M
u
s
s
al
im
u
n
et
a
l
.
[
7
]
,
t
h
e
s
te
p
s
i
n
p
e
r
f
o
r
m
i
n
g
class
i
f
i
ca
t
io
n
-
b
ase
d
s
e
n
ti
m
e
n
t
an
al
y
s
is
o
n
te
x
t
d
ata
o
r
t
ex
t m
i
n
i
n
g
d
at
a
ar
e
as
i)
i
n
it
ial
s
ta
g
e:
d
atas
et
c
o
ll
ec
t
io
n
;
ii)
p
r
e
p
r
o
ce
s
s
in
g
:
s
ta
g
es
i
n
cl
u
d
i
n
g
t
o
k
e
n
iz
ati
o
n
,
s
t
o
p
-
w
o
r
d
r
em
o
v
al
,
a
n
d
s
t
em
m
i
n
g
;
iii
)
t
r
an
s
f
o
r
m
a
ti
o
n
:
s
ta
g
e
wh
e
r
e
te
x
t
d
at
a
is
we
ig
h
e
d
;
iv
)
f
ea
t
u
r
e
s
e
lec
ti
o
n
:
s
ta
g
e
o
f
r
e
d
u
ci
n
g
u
n
n
e
ce
s
s
a
r
y
d
at
a
;
v
)
c
l
ass
if
ica
ti
o
n
:
t
h
e
t
ex
t
class
i
f
i
ca
t
io
n
s
ta
g
e
u
s
u
all
y
u
s
es
a
lg
o
r
it
h
m
s
s
u
c
h
as
n
ai
v
e
B
ay
es,
K
-
n
ea
r
est
n
ei
g
h
b
o
r
(
KNN
)
,
a
n
d
S
VM
;
a
n
d
v
i
)
ev
al
u
a
ti
o
n
:
t
h
e
ev
al
u
at
io
n
s
tag
e
is
co
n
d
u
ct
e
d
t
o
c
alc
u
l
ate
ac
c
u
r
a
cy
a
n
d
ar
ea
u
n
d
er
t
h
e
c
u
r
v
e
v
al
u
es
.
2
.
3
.
Su
pp
o
rt
v
ec
t
o
r
ma
chine
T
h
e
s
u
p
er
v
is
ed
m
ac
h
i
n
e
lear
n
i
n
g
m
eth
o
d
,
lik
e
SVM,
ap
p
lies
to
class
if
icatio
n
an
d
r
eg
r
ess
io
n
task
s
[
8
]
.
SVM
i
s
a
cla
s
s
if
icat
io
n
m
eth
o
d
th
at
d
o
es
n
o
t
r
ely
o
n
p
r
o
b
ab
ilit
ies
an
d
r
eq
u
ir
es
s
u
b
s
tan
tial
tr
ain
in
g
d
ata.
T
h
is
alg
o
r
ith
m
u
tili
ze
s
th
e
co
n
ce
p
t
o
f
a
d
ec
is
io
n
b
o
u
n
d
ar
y
to
estab
lis
h
lim
its
b
etwe
en
d
if
f
er
e
n
t
class
es
o
n
ea
c
h
o
b
ject.
T
h
e
d
ec
is
io
n
b
o
u
n
d
ar
y
is
a
s
ep
ar
ato
r
b
etwe
en
o
b
ject
s
'
m
em
b
er
s
h
ip
in
o
th
er
class
es
[
9
]
.
Fo
r
i
n
s
tan
ce
,
co
n
s
id
er
a
d
ataset
co
n
tain
in
g
p
air
s
m
{(
xi,
yi
)}
,
wh
er
e
ea
ch
x
i
r
ep
r
esen
ts
th
e
ch
ar
ac
ter
is
tics
o
f
a
d
ata
p
o
in
t,
an
d
yi
in
d
icate
s
its
class
lab
el
[
1
0
]
.
T
h
e
SVM
class
if
icatio
n
alg
o
r
ith
m
ass
u
m
es
th
at
a
h
y
p
er
p
lan
e
ex
is
ts
,
o
r
m
o
r
e
g
en
er
ally
,
a
d
−1
s
u
r
f
a
ce
,
ca
p
ab
le
o
f
s
ep
ar
atin
g
th
e
two
class
es
with
in
th
e
f
ea
tu
r
e
s
p
ac
e.
T
h
is
h
y
p
er
p
lan
e
is
d
elin
ea
ted
b
y
a
lin
ea
r
d
ec
is
io
n
f
u
n
cti
o
n
f
(
x
)
,
ch
ar
ac
ter
ize
d
b
y
p
ar
am
e
ter
s
w
∈
R
d
,
r
e
f
er
r
ed
to
as
th
e
weig
h
t,
an
d
b
∈
R
,
ter
m
ed
th
e
b
ias,
as d
ep
icted
in
(
1
)
a
n
d
(
2
)
.
(
)
=
+
b
,
(
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
User
s
en
timen
t d
yn
a
mics in
s
o
cia
l m
ed
ia
:
a
c
o
mp
a
r
a
tive
a
n
a
lysi
s
o
f X
a
n
d
Th
r
ea
d
s
(
R
ezki
K
h
a
ir
u
n
n
a
s
)
449
s
.
t
.
{
(
)
>
0
if
=
+
1
,
(
)
<
0
if
=
−
1
.
(
2
)
T
h
e
p
r
im
ar
y
o
b
jectiv
e
o
f
th
e
SVM
alg
o
r
ith
m
is
t
o
id
e
n
tify
a
h
y
p
er
p
lan
e
r
e
p
r
esen
ted
b
y
p
ar
am
eter
s
(
w,
b
)
th
at
m
ax
im
ize
th
e
m
ar
g
in
1
/|
|
w|
|
(
wh
er
e
|
|
·
|
|
d
en
o
tes
th
e
E
u
clid
ea
n
n
o
r
m
)
b
etwe
en
th
e
h
y
p
er
p
l
an
e
an
d
th
e
n
ea
r
est
d
ata
p
o
i
n
ts
b
elo
n
g
in
g
to
ea
ch
class
[
1
1
]
.
B
h
alla
a
n
d
J
asy
,
in
th
eir
r
esear
ch
,
ex
p
lain
ed
th
at
SVM
ex
h
ib
its
a
h
i
g
h
lev
el
o
f
ac
cu
r
ac
y
co
m
p
ar
e
d
to
n
aïv
e
B
ay
es a
n
d
KNN
[
1
2
]
,
[
1
3
]
.
2
.
4
.
Co
rr
ela
t
io
n
I
n
s
t
a
ti
s
t
i
c
al
a
n
a
l
y
s
is
,
c
o
r
r
e
la
t
i
o
n
o
r
d
e
p
e
n
d
e
n
c
e
d
e
n
o
t
e
s
a
n
y
s
ta
t
i
s
t
i
c
al
c
o
n
n
e
c
ti
o
n
,
w
h
e
t
h
e
r
c
au
s
a
t
i
v
e
o
r
n
o
t
,
b
e
t
w
e
e
n
t
w
o
r
a
n
d
o
m
v
a
r
i
a
b
l
e
s
.
W
h
i
l
e
"
c
o
r
r
e
l
at
i
o
n
"
c
a
n
e
n
c
o
m
p
a
s
s
v
a
r
i
o
u
s
f
o
r
m
s
o
f
a
s
s
o
c
i
a
t
i
o
n
i
n
a
g
e
n
e
r
a
l
c
o
n
t
e
x
t
,
s
t
a
t
is
ti
c
a
l
d
i
s
c
o
u
r
s
e
c
o
m
m
o
n
l
y
r
e
f
e
r
s
t
o
t
h
e
d
e
g
r
e
e
t
o
w
h
i
c
h
a
p
ai
r
o
f
v
a
r
i
a
b
l
es
e
x
h
i
b
it
a
li
n
e
a
r
r
e
la
t
i
o
n
s
h
i
p
[
1
4
]
.
T
h
e
P
e
a
r
s
o
n
c
o
r
r
e
l
a
t
i
o
n
co
e
f
f
i
c
i
e
n
t
is
t
h
e
m
o
s
t
w
i
d
e
l
y
u
s
e
d
m
e
a
s
u
r
e
o
f
c
o
r
r
e
l
a
t
i
o
n
,
a
n
d
i
t
d
e
t
e
c
ts
e
x
p
l
i
ci
t
ly
t
h
e
l
i
n
e
a
r
r
e
l
a
ti
o
n
s
h
i
p
b
et
w
e
e
n
t
w
o
v
a
r
i
a
b
l
e
s
.
I
t'
s
w
o
r
t
h
n
o
ti
n
g
t
h
a
t
t
h
is
c
o
r
r
e
l
a
t
i
o
n
m
e
a
s
u
r
e
c
a
n
c
a
p
t
u
r
e
l
i
n
e
a
r
a
s
s
o
ci
a
t
i
o
n
s
e
v
e
n
i
n
c
a
s
es
w
h
e
r
e
o
n
e
v
a
r
i
a
b
l
e
is
a
n
o
n
l
i
n
e
a
r
f
u
n
c
t
i
o
n
o
f
t
h
e
o
t
h
e
r
.
C
o
r
r
e
l
a
tio
n
i
s
a
f
u
n
d
a
m
e
n
t
al
a
s
p
e
c
t
o
f
d
e
s
c
r
i
p
t
i
v
e
a
n
d
e
x
p
l
o
r
a
t
o
r
y
r
e
s
e
a
r
c
h
a
n
d
f
u
n
c
t
i
o
n
s
as
a
n
e
f
f
e
ct
m
e
as
u
r
e
,
ai
d
i
n
g
i
n
th
e
i
n
t
e
r
p
r
e
t
at
i
o
n
a
n
d
c
o
m
p
a
r
i
s
o
n
o
f
f
i
n
d
i
n
g
s
a
c
r
o
s
s
v
a
r
i
o
u
s
s
t
u
d
ie
s
[
1
5
]
.
T
h
e
f
o
r
m
u
l
a
f
o
r
P
e
a
r
s
o
n
c
o
r
r
e
l
at
i
o
n
is
as
(
3
)
[
1
6
]
.
=
∑
(
−
̅
)
(
−
̅
)
=
1
√
[
∑
(
−
̅
)
2
=
1
]
[
∑
(
−
̅
)
2
=
1
]
(
3
)
R
e
g
a
r
d
i
n
g
t
h
e
s
t
r
e
n
g
t
h
o
f
t
h
e
r
e
l
a
t
i
o
n
s
h
i
p
,
c
o
r
r
e
l
a
t
i
o
n
c
o
e
f
f
i
c
i
e
n
t
v
a
l
u
e
s
r
a
n
g
e
f
r
o
m
+
1
t
o
-
1
.
A
v
a
l
u
e
o
f
±
1
d
e
n
o
t
e
s
a
p
e
r
f
e
c
t
d
e
g
r
e
e
o
f
r
e
l
a
t
i
o
n
s
h
i
p
b
e
t
w
e
e
n
t
h
e
v
a
r
i
a
b
l
e
s
.
F
o
r
e
x
a
m
p
l
e
,
a
s
t
h
e
c
o
r
r
e
l
a
t
i
o
n
c
o
e
f
f
i
c
i
e
n
t
a
p
p
r
o
a
c
h
e
s
0
,
t
h
e
r
e
l
a
t
i
o
n
s
h
i
p
b
e
t
w
e
e
n
t
h
e
v
a
r
i
a
b
l
e
s
w
e
a
k
e
n
s
.
T
h
e
s
i
g
n
o
f
t
h
e
c
o
e
f
f
i
c
i
e
n
t
i
n
d
i
c
a
t
e
s
t
h
e
d
i
r
e
c
t
i
o
n
o
f
t
h
e
r
e
l
a
t
i
o
n
s
h
i
p
:
a
"
+
"
s
i
g
n
s
i
g
n
i
f
i
e
s
a
p
o
s
i
t
i
v
e
r
e
l
a
t
i
o
n
s
h
i
p
,
w
h
e
r
e
a
s
a
"
-
"
s
i
g
n
s
i
g
n
i
f
i
e
s
a
n
e
g
a
t
i
v
e
r
e
l
a
t
i
o
n
s
h
i
p
[
1
7
]
.
2
.
5
.
P
re
v
io
us
r
esea
rc
hes
A
r
ev
iew
o
f
f
o
u
r
p
r
e
v
io
u
s
s
tu
d
ies
was
co
n
d
u
cte
d
to
d
eter
m
in
e
th
e
m
o
s
t
s
u
itab
le
m
ac
h
i
n
e
lear
n
in
g
m
eth
o
d
f
o
r
s
en
tim
en
t
class
if
icatio
n
in
th
is
s
tu
d
y
.
T
h
e
a
n
a
ly
s
is
f
o
cu
s
ed
o
n
co
m
p
ar
in
g
t
h
e
p
er
f
o
r
m
an
ce
o
f
v
ar
io
u
s
alg
o
r
ith
m
s
,
in
clu
d
in
g
SVM,
n
aiv
e
B
ay
es,
KNN,
a
n
d
d
ec
is
io
n
tr
ee
,
in
d
if
f
er
e
n
t
s
en
tim
en
t
an
aly
s
is
co
n
tex
ts
.
Su
k
m
a
et
a
l.
[
9
]
ex
p
lo
r
ed
s
en
tim
en
t
a
n
aly
s
is
o
f
th
e
I
n
d
o
n
esian
g
o
v
er
n
m
en
t'
s
p
o
licy
(
Om
n
ib
u
s
L
aw)
o
n
T
witter
.
T
h
ey
co
m
p
ar
ed
n
aiv
e
B
ay
es,
SVM,
an
d
d
ec
is
io
n
tr
ee
alg
o
r
ith
m
s
,
f
in
d
in
g
th
at
SVM
ac
h
iev
ed
th
e
h
ig
h
est
ac
cu
r
ac
y
r
ate
at
9
1
.
8
0
%,
f
o
llo
wed
b
y
n
ai
v
e
B
ay
es
a
t
8
9
.
7
5
%
a
n
d
d
ec
is
io
n
t
r
ee
at
7
3
.
6
0
%.
Similar
ly
,
J
asy
et
a
l.
[
1
3
]
e
v
alu
ated
s
en
t
im
en
t
class
if
icatio
n
u
s
in
g
SVM,
KNN,
an
d
n
aiv
e
B
ay
es
o
n
th
e
Sen
tim
en
t1
4
0
d
ataset,
with
SVM
ag
ain
d
e
m
o
n
s
tr
atin
g
s
u
p
e
r
io
r
ac
c
u
r
ac
y
a
t 9
2
%,
co
m
p
ar
e
d
to
KNN
at
8
8
% a
n
d
n
aiv
e
B
ay
es
at
8
5
%.
I
n
an
o
th
e
r
s
tu
d
y
,
B
h
alla
[
1
2
]
p
er
f
o
r
m
e
d
a
co
m
p
a
r
ativ
e
an
aly
s
is
o
f
tex
t
class
if
icatio
n
u
s
in
g
SVM,
n
aiv
e
B
ay
es,
an
d
KNN,
th
o
u
g
h
th
e
s
p
ec
if
ic
r
esear
ch
o
b
ject
o
r
d
ata
s
o
u
r
ce
was
n
o
t
m
en
tio
n
e
d
.
R
ah
at
et
a
l
.
[
1
8
]
f
o
cu
s
ed
o
n
co
m
p
ar
in
g
n
aiv
e
B
ay
es
an
d
SVM
u
s
in
g
a
d
ataset
o
f
air
lin
e
r
e
v
iews
o
n
T
witter
,
with
SVM
ac
h
iev
in
g
an
ac
cu
r
ac
y
o
f
8
2
.
4
8
% a
n
d
n
a
iv
e
B
ay
es tr
ailin
g
at
7
6
.
5
6
%.
T
h
e
co
n
s
is
ten
t
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
o
f
SVM
in
th
ese
s
tu
d
ie
s
h
ig
h
lig
h
ts
its
p
r
ac
ticali
ty
as
a
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
e
f
o
r
s
en
tim
en
t
class
if
icatio
n
.
Desp
ite
v
a
r
iatio
n
s
in
r
esear
ch
s
u
b
jects,
s
u
ch
as
s
en
tim
en
t
to
war
d
s
g
o
v
e
r
n
m
en
t
p
o
licies
o
r
p
r
o
d
u
ct
r
ev
iews,
SVM
h
as
co
n
s
is
ten
tly
d
em
o
n
s
tr
ated
h
i
g
h
er
ac
cu
r
ac
y
th
a
n
n
aiv
e
B
ay
es
a
n
d
o
th
er
tech
n
i
q
u
es.
T
h
er
e
f
o
r
e,
SVM
h
as
b
ee
n
ch
o
s
en
as
t
h
e
s
en
tim
en
t
an
a
ly
s
is
m
o
d
el
f
o
r
th
is
r
esear
ch
b
ased
o
n
its
d
em
o
n
s
tr
ated
s
u
p
er
io
r
ity
i
n
ter
m
s
o
f
ac
cu
r
ac
y
.
3.
M
E
T
H
O
DO
L
O
G
Y
T
h
is
s
tu
d
y
s
y
s
tem
atica
lly
co
llects,
p
r
o
ce
s
s
es,
an
d
an
aly
s
es
u
s
er
r
ev
iews
o
f
th
e
T
h
r
e
ad
s
an
d
X
ap
p
licatio
n
s
f
r
o
m
th
e
G
o
o
g
le
Play
an
d
A
p
p
Sto
r
e.
T
h
e
m
e
th
o
d
o
lo
g
y
is
d
esig
n
e
d
to
ex
a
m
in
e
th
e
im
p
ac
t
o
f
ap
p
licatio
n
u
s
ag
e
f
ac
to
r
s
o
n
u
s
er
s
en
tim
en
t
an
d
en
g
ag
em
en
t
.
T
h
e
r
esear
ch
p
r
o
ce
d
u
r
e
is
in
s
p
ir
ed
b
y
th
e
wo
r
k
o
f
Am
r
ie
et
a
l.
[
1
9
]
,
with
m
o
d
if
icatio
n
s
to
s
u
it
th
e
s
p
ec
if
ic
co
n
tex
t
o
f
th
is
s
tu
d
y
.
T
h
e
s
tag
es
o
f
th
e
r
esear
ch
m
eth
o
d
o
l
o
g
y
a
r
e
illu
s
tr
ated
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
R
esear
ch
m
eth
o
d
o
l
o
g
y
D
a
t
a
C
o
ll
e
c
t
ing
D
a
t
a
L
a
b
e
ll
ing
P
r
e
p
r
o
c
e
s
s
ing
C
las
s
if
ic
a
t
ion
E
v
a
lua
t
ion
C
o
r
r
e
lat
ion
A
n
a
ly
s
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
5
:
447
-
4
5
6
450
3
.
1
.
Da
t
a
c
o
llect
ing
T
h
e
f
ir
s
t
s
tep
in
th
e
m
eth
o
d
o
l
o
g
y
is
th
e
c
o
llectio
n
o
f
u
s
er
r
ev
iews.
Usi
n
g
web
s
cr
ap
in
g
tech
n
iq
u
es,
we
ex
tr
ac
ted
r
ev
iews
f
o
r
th
e
T
h
r
ea
d
s
an
d
X
ap
p
licatio
n
s
f
r
o
m
th
e
Go
o
g
le
Play
Sto
r
e
an
d
Ap
p
Sto
r
e.
T
h
e
to
o
ls
g
o
o
g
le
-
p
lay
-
s
cr
ap
e
r
a
n
d
ap
p
-
s
to
r
e
-
s
cr
ap
er
a
r
e
u
tili
ze
d
f
o
r
th
is
p
u
r
p
o
s
e.
T
h
e
co
llected
r
ev
iews
ar
e
th
e
n
ca
teg
o
r
ized
b
ased
o
n
th
e
r
esp
e
ctiv
e
ap
p
licatio
n
an
d
p
latf
o
r
m
.
T
h
is
ca
teg
o
r
izatio
n
h
elp
s
in
v
e
s
tig
ate
wh
eth
er
th
e
p
latf
o
r
m
u
s
ed
co
n
tr
ib
u
tes
to
th
e
o
b
s
er
v
e
d
ch
a
n
g
es
in
d
aily
ac
tiv
e
u
s
er
s
f
o
r
T
h
r
ea
d
s
an
d
X.
T
h
e
r
ev
iews,
wh
ich
ar
e
in
E
n
g
lis
h
,
ar
e
m
er
g
ed
in
t
o
a
s
in
g
le
d
ataset
u
s
in
g
th
e
p
a
n
d
as lib
r
ar
y
i
n
Py
th
o
n
.
3
.
2
.
Da
t
a
l
a
bellin
g
On
ce
th
e
d
ata
is
co
llected
,
th
e
n
ex
t
s
tep
is
lab
ellin
g
th
e
r
ev
ie
ws
b
ased
o
n
s
en
tim
en
t.
T
h
e
s
e
n
tim
en
t
o
f
ea
ch
r
ev
iew
is
d
eter
m
in
e
d
u
s
i
n
g
th
e
r
atin
g
p
r
o
v
id
e
d
b
y
th
e
u
s
er
:
−
Po
s
itiv
e:
r
ev
iews
with
a
r
atin
g
ab
o
v
e
t
h
r
ee
(
>
3
)
.
−
Neu
tr
al:
r
ev
iews
with
a
r
atin
g
o
f
th
r
ee
.
−
Neg
ativ
e:
r
ev
iews
with
a
r
atin
g
b
elo
w
th
r
ee
(
<3
)
.
T
h
is
lab
ellin
g
p
r
o
ce
s
s
is
au
to
m
ated
u
s
in
g
a
Py
th
o
n
s
cr
ip
t th
at
u
tili
ze
s
th
e
p
an
d
as lib
r
ar
y
.
3
.
3
.
P
re
pro
ce
s
s
ing
B
ef
o
r
e
e
n
t
er
in
g
th
e
c
lass
i
f
i
ca
t
io
n
o
r
s
e
n
ti
m
e
n
t
a
n
al
y
s
is
s
ta
g
e
f
o
r
u
s
e
r
r
e
v
ie
ws
o
f
ap
p
l
ic
ati
o
n
s
X
a
n
d
T
h
r
e
a
d
s
,
ess
e
n
t
ial
s
t
ep
s
i
n
th
e
t
ex
t
m
i
n
i
n
g
p
r
o
c
ess
m
u
s
t
b
e
ap
p
li
ed
t
o
p
r
e
p
ar
e
t
h
e
d
a
ta
c
o
r
r
e
c
tly
.
T
h
ese
s
t
ep
s
h
el
p
en
s
u
r
e
t
h
e
ac
cu
r
a
c
y
a
n
d
ef
f
i
ci
en
cy
o
f
s
e
n
ti
m
e
n
t
an
al
y
s
is
a
n
d
al
lo
w
t
h
e
s
m
o
o
t
h
e
x
e
c
u
ti
o
n
o
f
n
at
u
r
al
la
n
g
u
a
g
e
p
r
o
ce
s
s
i
n
g
(
N
L
P
)
al
g
o
r
i
th
m
s
a
n
d
t
o
o
ls
.
T
h
e
t
o
o
ls
u
s
e
d
f
o
r
t
h
i
s
p
r
ep
r
o
c
ess
i
n
g
a
r
e
n
a
tu
r
al
la
n
g
u
a
g
e
t
o
o
l
k
it
N
L
T
K
an
d
d
e
m
o
ji
.
T
h
e
te
x
t
m
i
n
i
n
g
p
r
o
ce
s
s
c
o
n
s
is
ts
o
f
s
ev
er
al
s
t
ep
s
t
h
a
t
n
ee
d
t
o
b
e
p
er
f
o
r
m
e
d
t
o
p
r
e
p
a
r
e
r
e
v
i
ew
d
a
ta
,
b
o
t
h
f
r
o
m
a
p
p
lic
ati
o
n
X
a
n
d
T
h
r
ea
d
s
,
b
e
f
o
r
e
s
e
n
ti
m
e
n
t
a
n
a
ly
s
is
is
c
o
n
d
u
c
te
d
.
T
h
ese
s
te
p
s
i
n
cl
u
d
e
as
f
o
ll
o
ws.
3
.
3
.
1
.
T
o
k
eniza
t
io
n
Acc
o
r
d
in
g
to
Ku
m
ar
et
a
l
.
[
2
0
]
,
af
ter
th
e
d
ata
is
clea
n
ed
,
th
e
f
ir
s
t
s
tep
is
to
k
en
izatio
n
to
en
h
an
ce
th
e
ef
f
icien
cy
o
f
NL
P
alg
o
r
ith
m
e
x
ec
u
tio
n
.
T
o
k
en
izatio
n
in
v
o
lv
es
b
r
ea
k
in
g
d
o
wn
r
e
v
iews
in
to
to
k
en
s
,
wh
er
e
ea
ch
wo
r
d
in
a
s
en
ten
ce
is
co
n
s
id
e
r
ed
a
to
k
en
.
Du
r
in
g
th
is
p
r
o
ce
s
s
,
th
e
f
r
eq
u
en
cy
o
f
ea
ch
wo
r
d
is
m
ea
s
u
r
ed
an
d
s
to
r
ed
f
o
r
f
u
r
th
e
r
r
ef
e
r
en
ce
.
I
n
th
e
to
k
e
n
izatio
n
s
tag
e,
p
e
r
i
o
d
s
an
d
p
u
n
ctu
atio
n
m
ar
k
s
ar
e
r
em
o
v
e
d
,
an
d
all
wo
r
d
s
in
itially
in
u
p
p
er
ca
s
e
ar
e
co
n
v
er
ted
to
lo
wer
ca
s
e
t
o
ac
h
iev
e
u
n
if
o
r
m
ity
in
th
e
s
y
s
tem
.
T
h
is
s
tep
is
co
n
s
id
er
ed
v
er
y
u
s
ef
u
l in
p
r
ep
ar
in
g
d
ata
f
o
r
s
en
tim
en
t a
n
aly
s
is
.
3
.
3
.
2
.
Rem
o
v
a
l o
f
s
t
o
p wo
rds
Ku
m
ar
et
a
l
.
[
2
0
]
ex
p
lain
th
at
s
to
p
wo
r
d
s
,
s
u
ch
as is
,
an
,
an
d
th
e,
wh
ich
d
o
n
o
t p
lay
a
s
ig
n
i
f
ican
t r
o
le
in
d
eter
m
in
in
g
th
e
s
en
tim
en
t o
f
a
wo
r
d
,
ar
e
elim
in
ated
f
r
o
m
t
h
e
d
ataset.
T
h
ese
wo
r
d
s
o
f
te
n
o
n
ly
f
ill s
p
ac
e
an
d
d
o
n
o
t
co
n
t
r
ib
u
te
m
ea
n
in
g
f
u
ll
y
to
s
en
tim
en
t
a
n
aly
s
is
.
T
h
e
p
r
o
ce
s
s
o
f
r
em
o
v
in
g
s
to
p
wo
r
d
s
aim
s
to
im
p
r
o
v
e
th
e
ef
f
icien
cy
o
f
alg
o
r
ith
m
s
,
as
th
ese
wo
r
d
s
ca
n
ca
u
s
e
p
er
f
o
r
m
a
n
ce
d
e
g
r
ad
atio
n
b
y
c
o
n
s
u
m
in
g
r
eso
u
r
ce
s
with
o
u
t
p
r
o
v
id
i
n
g
v
alu
ab
le
i
n
f
o
r
m
atio
n
.
Dep
en
d
in
g
o
n
th
e
la
n
g
u
a
g
e
an
d
s
cr
ip
t
u
s
ed
,
ea
c
h
co
u
n
tr
y
m
ay
h
a
v
e
a
d
if
f
er
e
n
t
lis
t
o
f
s
to
p
wo
r
d
s
,
an
d
th
is
r
e
m
o
v
al
h
el
p
s
en
s
u
r
e
a
f
o
c
u
s
o
n
wo
r
d
s
t
h
at
h
av
e
a
m
o
r
e
s
ig
n
if
ican
t
im
p
ac
t
o
n
s
en
tim
en
t a
n
aly
s
is
.
3
.
3
.
3
.
Ste
mm
ing
Stem
m
in
g
is
a
tech
n
iq
u
e
u
s
ed
to
s
tr
ip
awa
y
af
f
i
x
es
(
s
u
ch
as
s
u
f
f
ix
es,
p
r
e
f
ix
es,
in
f
ix
es,
an
d
cir
cu
m
f
ix
es)
f
r
o
m
a
wo
r
d
o
r
p
h
r
ase
to
d
er
iv
e
a
r
o
o
t
f
o
r
m
.
F
o
r
in
s
tan
ce
,
tr
an
s
f
o
r
m
in
g
th
e
wo
r
d
s
"a
m
az
in
g
"
o
r
"a
m
az
ed
"
in
to
"a
m
az
e"
aim
s
to
ex
tr
ac
t
a
m
o
r
e
f
u
n
d
am
e
n
ta
l
r
ep
r
esen
tatio
n
o
f
th
e
ter
m
.
Stem
m
in
g
aim
s
to
elim
in
ate
in
f
lecte
d
f
o
r
m
s
a
n
d
v
ar
io
u
s
ty
p
es
r
elate
d
t
o
a
ter
m
in
to
a
s
p
ec
if
ic
b
ase
f
o
r
m
.
T
h
is
p
r
o
ce
s
s
r
ed
u
ce
s
th
e
o
v
er
all
n
u
m
b
e
r
o
f
w
o
r
d
s
a
n
d
im
p
r
o
v
es p
r
o
ce
s
s
in
g
ef
f
ici
en
cy
[
9
]
.
Featu
r
e
ex
tr
ac
tio
n
i
n
v
o
lv
es
ex
tr
ac
tin
g
r
elev
an
t
ch
ar
ac
ter
is
tics
f
r
o
m
a
d
ataset,
in
clu
d
in
g
f
o
r
m
ats
lik
e
tex
t
an
d
im
ag
es,
an
d
co
n
v
er
ti
n
g
th
em
in
to
a
f
o
r
m
at
co
m
p
ati
b
le
with
m
ac
h
in
e
lear
n
in
g
(
M
L
)
alg
o
r
ith
m
s
.
T
h
is
s
tu
d
y
em
p
lo
y
s
th
e
ter
m
f
r
eq
u
en
cy
-
in
v
er
s
e
d
o
c
u
m
en
t
f
r
e
q
u
en
cy
(
TF
-
I
DF
)
tech
n
iq
u
e
u
s
in
g
th
e
s
cik
it
-
lear
n
lib
r
ar
y
.
T
F
-
I
DF
is
u
tili
ze
d
f
o
r
weig
h
tin
g
to
ass
ess
th
e
s
ig
n
if
ican
ce
o
f
a
wo
r
d
o
r
ter
m
wit
h
in
a
d
o
c
u
m
en
t
o
r
co
r
p
u
s
[
2
1
]
.
3
.
4
.
Cla
s
s
if
ica
t
io
n
I
n
p
er
f
o
r
m
i
n
g
th
e
class
if
icatio
n
,
th
e
a
p
p
r
o
ac
h
u
s
ed
in
th
is
r
e
s
ea
r
ch
is
th
e
SVM
ap
p
r
o
ac
h
.
SVM
is
a
b
in
ar
y
lin
ea
r
class
if
icatio
n
th
a
t
is
n
o
t
p
r
o
b
ab
ilis
tic.
T
h
e
p
r
i
m
ar
y
o
b
jectiv
e
o
f
SVM
is
to
p
ar
titi
o
n
th
e
d
ataset
in
to
d
is
tin
ct
g
r
o
u
p
s
to
attain
th
e
m
ax
im
u
m
m
ar
g
in
al
h
y
p
er
p
lan
e
(
MM
H)
.
SVM
em
p
lo
y
s
th
e
k
er
n
el
tr
ick
s
tr
ateg
y
,
wh
er
ein
th
e
k
er
n
el
tr
a
n
s
f
o
r
m
s
a
lo
w
-
d
im
en
s
io
n
al
in
p
u
t
s
p
ac
e
in
to
a
h
ig
h
er
-
d
im
en
s
i
o
n
al
s
p
ac
e.
I
n
o
th
er
wo
r
d
s
,
b
y
ad
d
i
n
g
m
o
r
e
d
im
en
s
io
n
s
,
th
e
k
er
n
el
r
eso
lv
es
p
r
o
b
l
em
s
th
at
ca
n
n
o
t
b
e
s
ep
ar
ated
in
to
s
ep
ar
ab
le
is
s
u
es.
SVM
class
if
icatio
n
h
as e
x
ce
llen
t p
r
ec
is
io
n
an
d
f
u
n
ctio
n
s
ef
f
icien
tly
in
h
ig
h
-
d
im
en
s
io
n
al
s
p
ac
es
[
2
1
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
User
s
en
timen
t d
yn
a
mics in
s
o
cia
l m
ed
ia
:
a
c
o
mp
a
r
a
tive
a
n
a
lysi
s
o
f X
a
n
d
Th
r
ea
d
s
(
R
ezki
K
h
a
ir
u
n
n
a
s
)
451
3
.
5
.
E
v
a
lua
t
io
n
E
v
alu
atio
n
is
co
n
d
u
cte
d
to
m
ea
s
u
r
e
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
im
p
lem
en
ted
class
if
icatio
n
m
o
d
el.
T
h
is
ev
alu
atio
n
p
r
o
ce
s
s
in
clu
d
es
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
m
etr
ics.
Acc
u
r
ac
y
r
e
f
lects
h
o
w
well
th
e
m
o
d
el
ca
n
class
if
y
co
r
r
ec
tly
,
wh
ile
p
r
ec
is
io
n
m
ea
s
u
r
es
th
e
m
o
d
el'
s
ac
cu
r
ac
y
in
id
e
n
tify
in
g
a
p
ar
ticu
lar
class
.
R
ec
all
in
d
icate
s
h
o
w
well
th
e
m
o
d
el
ca
n
r
ed
is
co
v
er
in
s
tan
ce
s
o
f
a
class
,
an
d
th
e
F1
s
co
r
e
p
r
o
v
id
es
a
b
alan
ce
b
etwe
en
p
r
ec
is
io
n
an
d
r
ec
all.
T
h
e
im
p
lem
en
tatio
n
o
f
th
e
S
VM
m
o
d
el
in
th
is
r
esear
ch
is
ev
alu
ated
u
s
in
g
th
e
s
cik
it
-
lear
n
lib
r
ar
y
.
3
.
6
.
Co
rr
ela
t
io
n
a
na
ly
s
is
Af
ter
co
m
p
letin
g
t
h
e
s
en
tim
e
n
t
an
aly
s
is
p
r
o
ce
s
s
o
n
th
e
tes
tin
g
d
ata
o
f
X
an
d
T
h
r
ea
d
s
a
p
p
licatio
n
r
ev
iews,
th
e
n
e
x
t
s
tep
is
to
co
r
r
elate
th
e
s
en
tim
en
t
an
al
y
s
is
r
esu
lts
with
ap
p
licatio
n
u
s
ag
e
f
ac
to
r
s
.
T
h
e
ap
p
licatio
n
u
s
ag
e
f
ac
t
o
r
s
in
th
i
s
r
esear
ch
ar
e
d
iv
id
e
d
in
to
f
o
u
r
m
ain
ca
teg
o
r
ies:
u
s
ab
ilit
y
,
f
ea
tu
r
es,
d
esig
n
,
an
d
s
u
p
p
o
r
t,
with
ea
ch
ca
teg
o
r
y
h
a
v
in
g
a
lis
t
o
f
k
ey
wo
r
d
s
r
ep
r
ese
n
tin
g
th
o
s
e
asp
ec
ts
.
Usab
ilit
y
,
en
co
m
p
ass
in
g
ea
s
e
o
f
u
s
e
an
d
ap
p
licatio
n
ef
f
icien
cy
,
is
cr
u
cial
i
n
ea
r
ly
u
s
er
e
x
p
er
ien
ce
s
[
2
2
]
.
Ap
p
licatio
n
f
ea
tu
r
es
ca
n
en
h
an
ce
u
s
er
en
g
ag
e
m
en
t
an
d
en
co
u
r
a
g
e
r
ep
ea
ted
u
s
ag
e
[
2
3
]
.
T
h
e
a
p
p
licatio
n
d
esig
n
also
p
lay
s
a
v
ital
r
o
le,
wh
er
e
a
n
attr
ac
tiv
e
an
d
in
tu
itiv
e
d
esig
n
ca
n
im
p
r
o
v
e
u
s
er
s
atis
f
ac
tio
n
[
2
4
]
.
Fu
r
th
e
r
m
o
r
e
,
cu
s
to
m
er
s
u
p
p
o
r
t sig
n
if
ican
tly
im
p
ac
ts
b
u
ild
in
g
tr
u
s
t
an
d
u
s
er
lo
y
alty
.
E
f
f
ec
tiv
e
s
u
p
p
o
r
t
f
ac
to
r
s
ca
n
h
elp
r
eso
lv
e
u
s
er
is
s
u
es
q
u
ick
ly
an
d
ef
f
icien
tly
[
2
5
]
.
T
h
ese
f
o
u
r
f
ac
to
r
s
in
ter
ac
t
to
f
o
r
m
th
e
o
v
er
all
u
s
er
ex
p
er
ien
ce
s
.
T
a
b
le
1
co
n
tain
s
k
ey
wo
r
d
lis
ts
f
o
r
ea
ch
ca
teg
o
r
y
u
tili
zin
g
th
e
NL
T
K
co
r
p
u
s
lem
m
as a
n
d
s
y
n
s
ets lib
r
ar
y
.
E
ac
h
r
ev
iew
will
b
e
ex
am
in
ed
to
d
eter
m
in
e
wh
eth
er
it
co
n
ta
in
s
k
ey
wo
r
d
s
f
r
o
m
o
n
e
o
f
th
e
ca
teg
o
r
ies
o
f
u
s
ag
e
f
ac
to
r
s
(
u
s
ab
ilit
y
,
f
ea
tu
r
es,
d
esig
n
,
s
u
p
p
o
r
t)
b
y
u
tili
zin
g
th
e
NL
T
K
co
r
p
u
s
lem
m
as
an
d
s
y
n
s
ets
lib
r
ar
y
to
o
b
tain
h
y
p
e
r
n
y
m
s
,
h
y
p
o
n
y
m
s
,
m
er
o
n
y
m
s
,
an
d
h
o
lo
n
y
m
s
f
o
r
th
ese
f
o
u
r
f
ac
to
r
s
.
I
f
a
co
r
r
esp
o
n
d
en
ce
is
f
o
u
n
d
,
th
e
r
ev
iew
will
b
e
ca
te
g
o
r
ized
as
p
o
s
itiv
e,
n
e
g
ativ
e,
o
r
n
eu
tr
a
l
b
ased
o
n
t
h
e
s
en
tim
en
t
d
etec
t
ed
.
T
h
e
co
r
r
elatio
n
r
esu
lts
will
th
en
b
e
in
ter
p
r
ete
d
to
c
o
n
clu
d
e
th
e
in
f
lu
en
ce
o
f
u
s
er
s
en
tim
en
t
o
n
ea
ch
ap
p
li
ca
tio
n
u
s
ag
e
f
ac
to
r
.
T
h
e
im
p
licatio
n
s
o
f
t
h
ese
f
in
d
in
g
s
ar
e
ex
p
ec
ted
to
g
u
id
e
ap
p
licatio
n
d
ev
elo
p
e
r
s
in
en
h
a
n
cin
g
s
p
ec
if
ic
asp
ec
ts
th
at
im
p
ac
t u
s
er
p
r
e
f
er
en
ce
s
.
T
h
e
Pear
s
o
n
m
eth
o
d
f
r
o
m
th
e
p
an
d
as
lib
r
ar
y
will
b
e
u
s
ed
in
th
e
co
r
r
elatio
n
an
al
y
s
is
s
tag
e.
C
o
r
r
elatio
n
v
is
u
aliza
tio
n
will
b
e
g
e
n
er
ate
d
u
s
in
g
t
h
e
m
atp
l
o
tlib
lib
r
ar
y
.
T
h
e
e
n
tire
co
r
r
elatio
n
a
n
aly
s
is
p
r
o
ce
s
s
will
b
e
im
p
lem
en
ted
u
s
in
g
a
Py
t
h
o
n
s
cr
ip
t.
All
th
es
e
s
tep
s
will
b
e
ex
ec
u
ted
th
r
o
u
g
h
Py
th
o
n
s
cr
ip
ts
,
u
tili
zin
g
th
e
m
en
tio
n
ed
f
u
n
ctio
n
s
an
d
e
n
s
u
r
in
g
ac
cu
r
ac
y
,
clar
ity
,
an
d
e
ase
o
f
in
ter
p
r
etatio
n
o
f
th
e
c
o
r
r
elat
io
n
an
aly
s
is
r
esu
lts
.
T
ab
le
1
.
L
is
t o
f
k
ey
wo
r
d
s
f
o
r
ap
p
licatio
n
u
s
ag
e
f
ac
to
r
s
F
a
c
t
o
r
s
K
e
y
w
o
r
d
s
S
u
b
c
a
t
e
g
o
r
i
e
s
U
sab
i
l
i
t
y
f
u
n
c
t
i
o
n
,
a
p
p
l
i
c
a
t
i
o
n
,
u
t
i
l
i
t
y
,
e
n
j
o
y
,
u
s
e
f
u
l
,
u
sa
b
i
l
i
t
y
,
a
n
d
u
sa
b
l
e
p
o
s
i
t
i
v
e
,
n
e
u
t
r
a
l
,
n
e
g
a
t
i
v
e
F
e
a
t
u
r
e
s
f
e
a
t
u
r
e
s,
f
e
e
d
,
p
r
o
d
u
c
t
,
p
r
o
f
i
l
e
,
a
n
d
t
r
e
n
d
i
n
g
p
o
s
i
t
i
v
e
,
n
e
u
t
r
a
l
,
n
e
g
a
t
i
v
e
D
e
si
g
n
d
e
s
i
g
n
,
i
n
t
e
r
f
a
c
e
,
i
n
t
e
r
a
c
t
i
o
n
,
n
a
v
i
g
a
t
i
o
n
,
a
n
d
e
x
p
e
r
i
e
n
c
e
p
o
s
i
t
i
v
e
,
n
e
u
t
r
a
l
,
n
e
g
a
t
i
v
e
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
th
is
s
ec
tio
n
,
an
an
al
y
s
is
will
b
e
co
n
d
u
cted
o
n
th
e
r
esear
ch
r
esu
lts
b
ased
o
n
th
e
p
r
e
v
io
u
s
ly
ex
p
lain
ed
m
eth
o
d
o
l
o
g
y
.
T
h
e
m
ain
f
o
cu
s
o
f
th
is
a
n
aly
s
is
is
to
id
e
n
tify
th
e
f
ac
to
r
s
t
h
at
h
a
v
e
le
d
to
a
s
ig
n
if
ican
t
d
ec
r
ea
s
e
in
th
e
u
s
ag
e
o
f
th
e
s
o
cial
m
ed
ia
a
p
p
licatio
n
T
h
r
ea
d
s
in
a
r
elativ
e
ly
s
h
o
r
t
p
er
i
o
d
.
Ad
d
itio
n
ally
,
it
aim
s
to
u
n
d
e
r
s
tan
d
wh
y
u
s
er
s
r
etu
r
n
to
u
s
in
g
T
witter
o
r
X
af
ter
leav
in
g
T
h
r
ea
d
s
.
4
.
1
.
Da
t
a
c
o
llect
ing
R
ev
iews
f
o
r
th
e
s
o
cial
m
e
d
ia
ap
p
licatio
n
s
X
an
d
T
h
r
ea
d
s
w
er
e
co
llected
t
h
r
o
u
g
h
s
cr
a
p
in
g
f
r
o
m
th
e
Go
o
g
le
Play
Sto
r
e
an
d
Ap
p
Sto
r
e.
Fo
llo
win
g
th
e
co
llectio
n
,
r
ev
iews
wer
e
g
r
o
u
p
ed
b
y
ap
p
l
icatio
n
an
d
m
er
g
ed
to
f
o
r
m
a
co
m
p
r
e
h
en
s
iv
e
d
ata
s
et
f
o
r
ea
ch
p
latf
o
r
m
.
Su
b
s
eq
u
en
t
d
ata
en
g
in
ee
r
in
g
s
tep
s
in
clu
d
ed
clea
n
in
g
th
e
d
ata
to
r
em
o
v
e
n
o
is
e
an
d
ir
r
elev
an
t
in
f
o
r
m
atio
n
a
n
d
p
e
r
f
o
r
m
in
g
te
x
t
m
in
in
g
p
r
o
ce
s
s
es
lik
e
to
k
en
izatio
n
,
s
to
p
-
wo
r
d
r
em
o
v
al,
em
o
tico
n
/
em
o
ji
r
em
o
v
al,
s
tem
m
in
g
,
an
d
weig
h
tin
g
.
T
h
ese
p
r
o
ce
s
s
es
u
tili
ze
d
th
e
NL
T
K
an
d
d
em
o
ji lib
r
ar
ies to
p
r
ep
ar
e
th
e
d
ata
f
o
r
an
aly
s
is
.
T
h
e
r
esu
lts
o
f
th
e
co
llected
d
ata
ca
n
b
e
s
ee
n
in
T
ab
le
2
.
T
ab
le
2
.
Data
co
llectin
g
r
esu
lt
A
p
p
l
i
c
a
t
i
o
n
D
a
t
a
s
e
t
N
u
mb
e
r
o
f
r
o
w
s
X
/
Tw
i
t
t
e
r
R
a
w
d
a
t
a
1
7
9
.
6
2
2
R
a
w
d
a
t
a
s
t
a
r
t
i
n
g
f
r
o
m
Ju
l
y
5
,
2
0
2
3
(
Th
r
e
a
d
s
r
e
l
e
a
s
e
d
a
t
e
)
3
5
.
6
4
2
Tr
a
i
n
i
n
g
d
a
t
a
se
t
(
8
0
%
o
f
t
h
e
d
a
t
a
set
)
2
8
.
5
1
3
Te
st
i
n
g
d
a
t
a
s
e
t
(
2
0
%
o
f
t
h
e
d
a
t
a
s
e
t
)
7
.
1
2
9
Th
r
e
a
d
s
R
a
w
d
a
t
a
3
9
.
3
1
6
Tr
a
i
n
i
n
g
d
a
t
a
se
t
(
8
0
%
o
f
t
h
e
d
a
t
a
set
)
3
1
.
4
5
2
Te
st
i
n
g
d
a
t
a
s
e
t
(
2
0
%
o
f
t
h
e
d
a
t
a
s
e
t
)
7
.
8
6
4
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
5
:
447
-
4
5
6
452
4
.
2
.
Da
t
a
l
a
bellin
g
T
h
e
tr
ain
in
g
d
ata
co
llected
f
r
o
m
th
e
u
s
er
r
ev
iews
o
f
b
o
th
X
an
d
T
h
r
ea
d
s
ap
p
licatio
n
s
was
lab
elled
ac
co
r
d
in
g
t
o
th
e
r
atin
g
s
p
r
o
v
id
ed
b
y
u
s
er
s
o
n
th
e
Go
o
g
le
Play
Sto
r
e
an
d
Ap
p
Sto
r
e
.
R
ev
iews
wer
e
ca
teg
o
r
ized
in
to
p
o
s
itiv
e
(
>3
)
,
n
eu
tr
al
(
3
)
,
an
d
n
eg
ativ
e
(
<
3
)
s
en
tim
en
ts
.
T
h
e
d
is
tr
ib
u
tio
n
o
f
th
ese
lab
els
is
s
u
m
m
ar
ized
in
T
ab
le
3
,
wh
ich
h
ig
h
lig
h
ts
th
e
s
en
tim
en
t tr
en
d
s
ac
r
o
s
s
b
o
th
p
latf
o
r
m
s
.
T
h
e
d
ata
s
h
o
ws
th
at
X
h
as
m
o
r
e
n
eg
ativ
e
r
ev
iews
th
an
p
o
s
itiv
e
an
d
n
eu
tr
al
o
n
es,
in
d
icatin
g
g
en
er
al
u
s
er
d
is
s
atis
f
ac
tio
n
.
I
n
c
o
n
tr
as
t,
T
h
r
ea
d
s
h
as
a
m
o
r
e
b
alan
ce
d
d
is
tr
ib
u
tio
n
with
a
s
ig
n
if
ica
n
t
n
u
m
b
er
o
f
p
o
s
itiv
e
r
ev
iews,
wh
ich
s
u
g
g
ests
a
m
o
r
e
f
av
o
u
r
a
b
le
r
ec
e
p
tio
n
a
m
o
n
g
its
u
s
er
s
.
T
h
is
s
en
tim
en
t
d
is
tr
ib
u
tio
n
p
r
o
v
id
es
a
f
o
u
n
d
atio
n
f
o
r
an
aly
zin
g
u
s
er
b
eh
av
io
u
r
to
war
d
s
ea
ch
ap
p
licatio
n
an
d
u
n
d
e
r
s
tan
d
in
g
th
e
f
ac
to
r
s
th
at
m
ay
in
f
lu
en
ce
s
h
if
ts
in
u
s
er
en
g
a
g
em
en
t.
I
n
s
ig
h
ts
d
er
iv
e
d
f
r
o
m
th
is
lab
ellin
g
p
r
o
ce
s
s
ar
e
c
r
itical
f
o
r
s
u
b
s
eq
u
e
n
t
an
aly
s
es
f
o
cu
s
in
g
o
n
th
e
d
ec
lin
e
in
u
s
er
en
g
ag
em
e
n
t
with
T
h
r
ea
d
s
an
d
th
e
f
ac
to
r
s
c
o
n
tr
ib
u
tin
g
to
u
s
er
s
r
etu
r
n
in
g
to
X
af
ter
in
itially
leav
in
g
.
T
ab
le
3
.
Dis
tr
ib
u
tio
n
o
f
s
en
ti
m
en
t la
b
ellin
g
f
o
r
tr
ain
i
n
g
d
at
a
A
p
p
l
i
c
a
t
i
o
n
S
e
n
t
i
me
n
t
N
u
mb
e
r
o
f
d
a
t
a
X
/
Tw
i
t
t
e
r
P
o
si
t
i
v
e
1
0
.
1
9
9
N
e
u
t
r
a
l
1
.
1
7
2
N
e
g
a
t
i
v
e
1
7
.
1
4
2
Th
r
e
a
d
s
P
o
si
t
i
v
e
1
6
.
7
2
0
N
e
u
t
r
a
l
2
.
3
9
7
N
e
g
a
t
i
v
e
1
2
.
3
3
5
4
.
3
.
Sentim
ent
a
na
ly
s
is
T
h
e
s
en
tim
en
t
an
al
y
s
is
em
p
lo
y
s
th
e
SVM
class
if
icatio
n
m
eth
o
d
,
ca
teg
o
r
izin
g
u
s
er
r
e
v
iews
in
to
p
o
s
itiv
e,
n
eu
tr
al,
o
r
n
eg
ativ
e
s
en
tim
en
ts
.
T
h
e
SVM
'
s
p
er
f
o
r
m
an
ce
was
ass
ess
ed
u
s
in
g
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e,
an
d
ac
c
u
r
ac
y
m
etr
ic
s
,
with
k
ey
r
esu
lts
s
u
m
m
ar
ized
in
T
ab
le
4
.
B
ased
o
n
T
a
b
le
4
,
th
e
m
eth
o
d
s
h
o
ws
s
tr
o
n
g
r
esu
lts
in
id
e
n
tify
in
g
p
o
s
itiv
e
an
d
n
e
g
ativ
e
s
en
tim
en
t
s
f
o
r
X,
with
r
esp
ec
tiv
e
F1
-
s
c
o
r
es
o
f
8
1
a
n
d
8
8
%,
in
d
icatin
g
a
r
o
b
u
s
t
ab
ilit
y
to
class
if
y
th
ese
s
en
tim
en
ts
co
r
r
ec
tly
.
Ho
wev
er
,
it
f
ails
to
id
en
tify
n
eu
tr
al
s
en
t
im
en
ts
,
r
ef
lecte
d
in
a
0
%
s
co
r
e
ac
r
o
s
s
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e.
I
t
s
u
g
g
es
ts
th
at
th
e
SVM
co
u
ld
n
o
t
d
is
ce
r
n
a
n
y
n
eu
tr
al
r
ev
iews,
lik
ely
d
u
e
to
t
h
eir
u
n
d
er
r
e
p
r
esen
tatio
n
o
r
a
m
b
ig
u
o
u
s
lin
g
u
is
tic
f
ea
tu
r
es i
n
th
e
tr
ain
in
g
d
ata.
Fo
r
T
h
r
ea
d
s
,
w
h
ile
th
e
SVM
also
d
em
o
n
s
tr
ates
a
h
ig
h
r
ec
all
o
f
9
3
%
f
o
r
p
o
s
itiv
e
s
en
tim
en
ts
,
s
u
g
g
esti
n
g
it
ca
p
tu
r
es
th
e
m
ajo
r
ity
o
f
p
o
s
itiv
e
r
ev
iews,
th
e
p
r
ec
is
io
n
is
lo
wer
at
7
6
%,
in
d
icatin
g
s
o
m
e
non
-
p
o
s
itiv
e
s
en
tim
en
ts
ar
e
m
is
tak
en
ly
lab
elled
as
p
o
s
itiv
e.
L
ik
e
X,
T
h
r
ea
d
s
r
ev
iews
s
h
o
w
p
o
o
r
SVM
p
er
f
o
r
m
a
n
ce
o
n
n
e
u
tr
al
s
en
tim
en
ts
,
with
a
v
er
y
lo
w
r
ec
all
o
f
3
%,
e
m
p
h
a
s
izin
g
th
e
m
o
d
el'
s
co
n
s
is
ten
t
s
tr
u
g
g
le
with
n
e
u
tr
al
class
if
icatio
n
s
ac
r
o
s
s
p
latf
o
r
m
s
.
T
h
o
u
g
h
r
elativ
ely
e
f
f
ec
tiv
e,
n
eg
ativ
e
s
en
tim
en
t
d
etec
tio
n
in
T
h
r
ea
d
s
r
e
v
iews
is
wea
k
er
th
an
in
X,
wh
ich
m
ig
h
t
b
e
attr
ib
u
ted
to
less
d
is
tin
ctiv
e
lin
g
u
is
tic
cu
es
in
ex
p
r
ess
in
g
d
is
s
ati
s
f
ac
tio
n
o
n
T
h
r
ea
d
s
.
T
h
ese
f
in
d
in
g
s
u
n
d
er
s
co
r
e
a
s
ig
n
if
ican
t
class
im
b
alan
ce
an
d
th
e
n
ec
ess
ity
f
o
r
b
etter
tr
ain
in
g
d
ata
b
alan
ce
o
r
e
n
h
an
c
e
d
f
ea
tu
r
e
e
x
tr
ac
tio
n
to
im
p
r
o
v
e
class
if
icatio
n
ac
cu
r
ac
y
,
esp
ec
ially
f
o
r
n
eu
tr
al
s
en
tim
en
ts
.
B
ased
o
n
T
ab
le
5
,
th
e
r
esu
lts
f
o
r
X
in
d
icate
a
p
r
e
d
o
m
in
a
n
c
e
o
f
n
eg
ativ
e
s
en
tim
en
ts
co
n
s
i
s
ten
t
with
tr
ain
in
g
d
ata
p
e
r
f
o
r
m
an
ce
.
I
n
co
n
tr
ast,
T
h
r
ea
d
s
d
is
p
lay
e
d
a
m
ajo
r
ity
o
f
p
o
s
itiv
e
s
en
tim
en
t
s
in
th
e
test
in
g
p
h
ase
d
esp
ite
s
o
m
e
n
eu
tr
al
a
n
d
n
eg
ativ
e
f
ee
d
b
ac
k
.
T
h
is
v
ar
i
a
tio
n
u
n
d
er
s
co
r
es
th
e
p
latf
o
r
m
s
'
d
if
f
er
in
g
u
s
er
ex
p
er
ien
ce
s
an
d
p
o
te
n
tial a
r
ea
s
f
o
r
im
p
r
o
v
em
e
n
t,
p
ar
ticu
lar
l
y
in
en
h
an
cin
g
s
en
tim
en
t d
ete
ctio
n
alg
o
r
ith
m
s
.
T
ab
le
4
.
C
lass
if
icatio
n
p
er
f
o
r
m
an
ce
A
p
p
l
i
c
a
t
i
o
n
C
l
a
s
s
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
sc
o
r
e
(
%)
A
c
c
u
r
a
c
y
(
%)
X
/
Tw
i
t
t
e
r
P
o
si
t
i
v
e
84
78
81
8
3
.
5
7
N
e
u
t
r
a
l
0
0
0
N
e
g
a
t
i
v
e
84
92
88
Th
r
e
a
d
s
P
o
si
t
i
v
e
76
93
84
7
8
.
0
0
N
e
u
t
r
a
l
42
3
6
N
e
g
a
t
i
v
e
82
72
76
T
ab
le
5
.
Sen
tim
en
t a
n
aly
s
is
r
esu
lts
A
p
p
l
i
c
a
t
i
o
n
S
e
n
t
i
me
n
t
N
u
mb
e
r
o
f
d
a
t
a
X
/
Tw
i
t
t
e
r
P
o
si
t
i
v
e
2
.
2
4
9
N
e
u
t
r
a
l
0
N
e
g
a
t
i
v
e
4
.
8
8
0
Th
r
e
a
d
s
P
o
si
t
i
v
e
5
.
2
4
5
N
e
u
t
r
a
l
53
N
e
g
a
t
i
v
e
2
.
5
6
6
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
User
s
en
timen
t d
yn
a
mics in
s
o
cia
l m
ed
ia
:
a
c
o
mp
a
r
a
tive
a
n
a
lysi
s
o
f X
a
n
d
Th
r
ea
d
s
(
R
ezki
K
h
a
ir
u
n
n
a
s
)
453
4
.
4
.
Co
rr
el
a
t
io
n bet
wee
n X
a
nd
T
hrea
d
s
Fo
llo
win
g
th
e
s
en
tim
en
t
a
n
aly
s
is
,
th
e
s
tu
d
y
co
r
r
elate
d
t
h
ese
r
esu
lts
with
ap
p
licatio
n
u
s
ag
e
f
ac
to
r
s
ca
teg
o
r
ized
in
to
u
s
ab
ilit
y
,
f
ea
t
u
r
es,
d
esig
n
,
an
d
s
u
p
p
o
r
t.
T
h
e
an
aly
s
is
ex
am
in
ed
wh
eth
er
th
e
r
ev
iews
co
n
tain
ed
k
ey
wo
r
d
s
r
elate
d
to
th
ese
u
s
ag
e
f
ac
to
r
s
a
n
d
class
if
ied
th
e
m
i
n
to
p
o
s
itiv
e,
n
eg
ativ
e
,
o
r
n
eu
tr
al
s
en
tim
en
ts
b
ased
o
n
th
eir
co
n
ten
t.
T
h
e
m
ap
p
i
n
g
r
esu
lts
ar
e
s
u
m
m
ar
i
ze
d
in
T
ab
le
6
.
T
ab
le
6
p
r
esen
ts
th
e
d
is
tr
ib
u
tio
n
o
f
u
s
er
s
en
tim
en
ts
ac
r
o
s
s
u
s
ab
ilit
y
,
f
e
atu
r
es,
d
esig
n
,
an
d
s
u
p
p
o
r
t
f
o
r
th
e
a
p
p
licatio
n
s
X
a
n
d
T
h
r
ea
d
s
.
I
t'
s
im
p
o
r
tan
t
to
n
o
te
th
at
o
n
e
r
ev
iew
m
ay
a
d
d
r
ess
m
u
ltip
le
u
s
ag
e
f
ac
to
r
s
,
r
ef
lectin
g
co
m
p
lex
u
s
er
ex
p
e
r
ien
c
es
th
at
d
o
n
o
t
ea
s
ily
ca
teg
o
r
ize
in
to
u
n
iq
u
e
ca
teg
o
r
ies.
X
ex
h
ib
its
a
p
r
e
d
o
m
in
a
n
ce
o
f
n
e
g
ativ
e
s
en
tim
en
ts
ac
r
o
s
s
all
f
ac
to
r
s
,
with
ex
ce
p
tio
n
ally
h
ig
h
d
is
co
n
ten
t
n
o
ted
in
s
u
p
p
o
r
t
(
3
5
1
8
n
e
g
ativ
e
r
ev
iews)
an
d
u
s
ab
ilit
y
(
2
3
9
1
n
eg
ativ
e
r
ev
iews).
Desp
ite
r
ec
eiv
in
g
m
an
y
p
o
s
itiv
e
r
ev
iews,
th
e
h
ig
h
v
o
lu
m
e
o
f
n
e
g
ativ
e
f
ee
d
b
ac
k
h
ig
h
lig
h
ts
cr
itical
ar
ea
s
f
o
r
im
p
r
o
v
e
m
en
t
in
u
s
er
ex
p
er
ien
ce
.
T
h
r
ea
d
s
s
h
o
w
a
m
o
r
e
ev
e
n
d
is
tr
ib
u
tio
n
b
etwe
en
p
o
s
itiv
e
an
d
n
eg
ativ
e
s
en
tim
e
n
ts
ac
r
o
s
s
all
u
s
ag
e
f
ac
to
r
s
.
Ho
wev
er
,
e
v
en
with
a
b
alan
ce
d
f
ee
d
b
ac
k
p
r
o
f
ile,
n
eg
ativ
e
r
e
v
iews
clo
s
ely
m
atch
th
e
p
o
s
itiv
es,
esp
ec
ially
in
f
ea
tu
r
es
an
d
s
u
p
p
o
r
t,
in
d
icatin
g
ar
ea
s
wh
er
e
u
s
er
s
atis
f
ac
tio
n
co
u
ld
b
e
en
h
a
n
ce
d
.
A
s
m
all
b
u
t
n
o
tab
le
n
u
m
b
er
o
f
n
eu
tr
al
r
e
v
iews
s
u
g
g
ests
th
at
s
o
m
e
u
s
er
s
r
em
ain
in
d
if
f
er
en
t
o
r
u
n
s
atis
f
ied
with
ce
r
tain
asp
ec
ts
o
f
th
e
ap
p
licatio
n
,
wh
i
ch
co
u
ld
s
ig
n
al
a
n
ee
d
f
o
r
tar
g
eted
im
p
r
o
v
em
en
ts
.
Fig
u
r
e
2
illu
s
tr
ates
th
e
co
r
r
elat
io
n
b
etwe
en
u
s
er
s
en
tim
e
n
ts
o
n
u
s
ab
ilit
y
,
d
esig
n
,
f
ea
tu
r
es,
a
n
d
s
u
p
p
o
r
t
f
o
r
a
p
p
licatio
n
s
X
an
d
T
h
r
e
ad
s
.
C
o
r
r
elatio
n
s
r
an
g
e
f
r
o
m
-
1
to
1
,
with
+1
in
d
icatin
g
a
p
er
f
ec
t
p
o
s
itiv
e
r
elatio
n
s
h
ip
,
-
1
s
ig
n
if
y
in
g
a
p
er
f
ec
t
n
e
g
ativ
e
r
elatio
n
s
h
ip
,
a
n
d
0
s
h
o
win
g
n
o
r
elatio
n
s
h
ip
.
W
h
ile
co
r
r
elatio
n
d
o
es
n
o
t
im
p
ly
ca
u
s
atio
n
,
it
o
f
f
er
s
in
s
ig
h
ts
in
to
h
o
w
u
s
er
s
en
tim
en
ts
to
war
d
s
o
n
e
a
p
p
lic
atio
n
m
ay
r
elate
to
s
en
tim
en
ts
to
war
d
s
an
o
th
er
.
T
ab
le
6
.
Ma
p
p
in
g
r
esu
lts
o
f
r
e
v
iews with
ap
p
licatio
n
u
s
ag
e
f
ac
to
r
s
A
p
p
l
i
c
a
t
i
o
n
S
e
n
t
i
me
n
t
A
p
p
l
i
c
a
t
i
o
n
u
s
a
g
e
f
a
c
t
o
r
s
U
sab
i
l
i
t
y
F
e
a
t
u
r
e
s
D
e
si
g
n
S
u
p
p
o
r
t
X
/
Tw
i
t
t
e
r
P
o
si
t
i
v
e
8
5
9
5
8
6
4
9
7
8
4
0
N
e
u
t
r
a
l
0
0
0
0
N
e
g
a
t
i
v
e
2
3
9
1
1
7
0
3
1
4
3
8
2
6
7
8
To
t
a
l
3
2
5
0
2
2
8
9
1
9
3
5
3
5
1
8
Th
r
e
a
d
s
P
o
si
t
i
v
e
8
5
9
7
8
5
5
4
3
6
0
4
N
e
u
t
r
a
l
35
35
18
27
N
e
g
a
t
i
v
e
1
0
4
2
8
5
9
4
7
8
9
4
7
To
t
a
l
1
9
3
6
1
6
7
9
1
0
3
9
1
5
7
8
Fig
u
r
e
2
.
C
o
r
r
elatio
n
an
aly
s
is
o
f
s
en
tim
en
t a
n
d
ap
p
licatio
n
u
s
ag
e
f
ac
to
r
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
5
:
447
-
4
5
6
454
Fro
m
th
e
co
r
r
elatio
n
m
atr
ix
,
it
is
ev
id
en
t
th
at
th
er
e
is
a
n
eg
ativ
e
co
r
r
elatio
n
b
etwe
e
n
p
o
s
itiv
e
s
en
tim
en
ts
o
n
th
e
u
s
ab
ilit
y
o
f
ap
p
licatio
n
X
an
d
n
eg
ativ
e
s
en
tim
en
ts
o
n
th
e
u
s
ab
ilit
y
o
f
T
h
r
ea
d
s
,
s
u
g
g
esti
n
g
an
in
v
er
s
e
r
elatio
n
s
h
ip
b
etwe
en
u
s
er
s
atis
f
ac
tio
n
ac
r
o
s
s
th
ese
two
ap
p
licatio
n
s
.
Similar
ly
,
p
o
s
itiv
e
s
en
tim
en
ts
ab
o
u
t
th
e
f
ea
tu
r
es
a
n
d
s
u
p
p
o
r
t
o
f
a
p
p
licatio
n
X
co
r
r
elate
n
e
g
a
tiv
ely
with
n
eg
ativ
e
s
en
tim
en
t
s
ab
o
u
t
th
e
f
ea
tu
r
es
an
d
s
u
p
p
o
r
t
o
f
T
h
r
ea
d
s
.
T
h
is
i
n
d
icate
s
th
at
u
s
er
s
wh
o
ap
p
r
ec
iate
th
e
f
ea
tu
r
es
an
d
s
u
p
p
o
r
t
o
f
a
p
p
licatio
n
X
ten
d
to
v
iew
th
ese
asp
ec
ts
less
f
av
o
u
r
ab
ly
in
T
h
r
ea
d
s
.
5.
DIS
CU
SS
I
O
N
AND
I
M
P
L
I
CATI
O
N
S
I
n
ad
d
r
ess
in
g
th
e
g
ap
s
id
e
n
tifie
d
in
p
r
e
v
io
u
s
r
esear
ch
o
n
u
s
er
s
en
tim
en
t
an
d
en
g
a
g
em
en
t
in
s
o
cial
m
ed
ia,
th
is
s
tu
d
y
p
r
o
v
id
es
a
n
u
an
ce
d
u
n
d
er
s
tan
d
in
g
o
f
h
o
w
u
s
er
s
en
tim
en
ts
d
ir
ec
tly
c
o
r
r
elate
with
s
h
if
ts
in
p
latf
o
r
m
u
s
ag
e
,
esp
ec
ially
in
t
h
e
co
m
p
etitiv
e
d
y
n
a
m
ics b
etw
ee
n
p
latf
o
r
m
s
lik
e
X
a
n
d
T
h
r
e
ad
s
.
W
h
ile
ex
is
tin
g
liter
atu
r
e
h
as
o
f
ten
h
ig
h
lig
h
ted
th
e
v
o
latilit
y
o
f
u
s
er
en
g
ag
em
en
t,
o
u
r
an
aly
s
is
d
elv
es
d
ee
p
e
r
in
to
th
e
im
m
e
d
iate
im
p
ac
ts
o
f
u
s
er
d
is
s
atis
f
ac
tio
n
o
n
o
n
e
p
latf
o
r
m
b
en
ef
itin
g
a
n
o
th
er
,
alb
eit
tem
p
o
r
ar
i
ly
,
if
th
e
n
ewc
o
m
er
f
ails
to
m
ain
tain
s
u
p
er
io
r
s
er
v
ice
an
d
co
n
tin
u
o
u
s
in
n
o
v
atio
n
.
Ou
r
f
in
d
in
g
s
s
u
g
g
est
a
co
m
p
lex
r
e
latio
n
s
h
ip
b
etwe
en
p
latf
o
r
m
f
ea
t
u
r
es,
u
s
er
s
atis
f
ac
tio
n
,
an
d
e
n
g
ag
e
m
en
t
d
y
n
a
m
ics.
I
n
itial
p
o
s
itiv
e
r
ec
ep
tio
n
to
war
d
s
T
h
r
ea
d
s
,
d
r
iv
en
b
y
n
e
g
ativ
e
s
en
tim
en
ts
to
war
d
s
X,
u
n
d
e
r
s
co
r
es
th
e
in
f
l
u
en
ce
o
f
u
s
er
p
er
ce
p
tio
n
o
n
p
la
tf
o
r
m
co
m
p
etitio
n
.
Ho
wev
er
,
as
T
h
r
ea
d
s
f
ailed
to
s
u
s
tain
u
s
er
en
g
a
g
em
en
t,
o
u
r
s
tu
d
y
illu
s
tr
ates
th
e
cr
itical
n
e
ed
f
o
r
p
latf
o
r
m
s
to
co
n
tin
u
o
u
s
ly
ad
ap
t a
n
d
im
p
r
o
v
e
b
ased
o
n
u
s
er
f
ee
d
b
ac
k
to
r
etain
th
eir
u
s
er
b
ase.
T
h
e
s
tu
d
y
em
p
l
o
y
ed
s
en
tim
e
n
t
an
aly
s
is
th
r
o
u
g
h
ML
,
p
r
im
ar
ily
f
o
c
u
s
in
g
o
n
u
s
er
r
e
v
iews
f
r
o
m
th
e
Go
o
g
le
Play
an
d
Ap
p
Sto
r
e
.
W
h
ile
ef
f
ec
tiv
e,
th
is
m
eth
o
d
h
as
lim
itatio
n
s
in
f
u
lly
ca
p
tu
r
in
g
th
e
n
u
an
ce
s
o
f
h
u
m
an
em
o
ti
o
n
s
,
s
u
ch
as
s
a
r
ca
s
m
,
an
d
m
ay
n
o
t
co
m
p
r
e
h
en
s
iv
ely
r
ep
r
esen
t
th
e
g
lo
b
al
u
s
er
b
ase.
T
h
e
m
eth
o
d
o
l
o
g
y
,
ce
n
tr
ed
o
n
a
b
r
o
ad
s
elec
tio
n
o
f
k
ey
wo
r
d
s
an
d
ap
p
licatio
n
u
s
ag
e
f
ac
to
r
s
,
m
a
y
n
o
t e
n
c
o
m
p
ass
th
e
f
u
ll sp
ec
tr
u
m
o
f
r
ea
s
o
n
s
wh
y
u
s
er
s
m
ig
h
t c
h
o
o
s
e
to
en
g
a
g
e
with
o
r
ab
an
d
o
n
a
p
latf
o
r
m
.
F
u
tu
r
e
r
esear
ch
c
o
u
ld
in
co
r
p
o
r
ate
d
iv
er
s
e
d
ata
s
o
u
r
c
es
to
ad
d
r
ess
th
ese
l
im
itatio
n
s
,
s
u
ch
as
d
i
r
ec
t
u
s
er
s
u
r
v
ey
s
an
d
in
ter
v
iews.
T
h
is
ap
p
r
o
ac
h
wo
u
ld
allo
w
f
o
r
a
r
ich
er
an
d
m
o
r
e
d
etailed
u
n
d
er
s
tan
d
in
g
o
f
u
s
er
m
o
tiv
at
io
n
s
an
d
r
ea
ctio
n
s
,
p
o
ten
tially
o
f
f
er
in
g
i
n
s
ig
h
ts
m
o
r
e
r
ef
lectiv
e
o
f
d
if
f
er
en
t
r
eg
i
o
n
al
co
n
te
x
ts
an
d
n
u
an
ce
d
u
s
er
ex
p
er
ie
n
ce
s
.
C
o
n
clu
s
iv
ely
,
th
is
r
esear
c
h
h
ig
h
lig
h
ts
th
at
s
u
s
tain
ed
u
s
er
en
g
ag
em
e
n
t
in
s
o
cial
m
e
d
ia
p
latf
o
r
m
s
r
eq
u
ir
es
m
o
r
e
th
a
n
in
itial
u
s
er
ac
q
u
is
itio
n
;
it
n
ec
ess
itates
a
r
elen
tles
s
f
o
cu
s
o
n
e
n
h
an
ci
n
g
u
s
er
ex
p
er
ie
n
ce
an
d
q
u
ick
ly
ad
a
p
tin
g
to
t
h
eir
ev
o
lv
in
g
n
ee
d
s
.
Fu
tu
r
e
s
tu
d
ies
s
h
o
u
ld
e
x
p
lo
r
e
t
h
e
lo
n
g
-
ter
m
ef
f
ec
ts
o
f
p
latf
o
r
m
s
tr
ateg
ies
o
n
u
s
er
r
eten
tio
n
an
d
s
atis
f
ac
tio
n
,
p
o
ten
tially
g
u
id
in
g
m
o
r
e
tailo
r
ed
a
n
d
ef
f
ec
tiv
e
en
h
an
ce
m
e
n
ts
in
p
latf
o
r
m
d
ev
elo
p
m
en
t.
B
y
b
r
o
ad
en
in
g
th
e
s
co
p
e
o
f
d
ata
a
n
d
in
c
o
r
p
o
r
atin
g
ad
v
a
n
ce
d
a
n
aly
tical
tech
n
iq
u
es,
f
u
r
th
er
r
esear
c
h
ca
n
p
r
o
v
id
e
d
ee
p
er
in
s
ig
h
ts
in
to
th
e
in
tr
icate
d
y
n
am
ics
o
f
u
s
er
s
en
tim
en
t
an
d
p
latf
o
r
m
s
u
cc
ess
.
6.
CO
NCLU
SI
O
N
Af
ter
d
o
m
in
atin
g
as
T
witter
,
n
o
w
r
eb
r
a
n
d
ed
as
X,
th
e
p
latf
o
r
m
witn
ess
ed
s
ig
n
if
ican
t
c
o
m
p
e
titi
o
n
f
r
o
m
Me
ta's
T
h
r
ea
d
s
,
wh
ich
,
d
esp
ite
a
s
tr
o
n
g
s
tar
t,
s
aw
a
q
u
ick
d
ec
lin
e
in
u
s
er
en
g
ag
em
e
n
t.
T
h
is
s
tu
d
y
r
ev
ea
ls
a
n
u
an
ce
d
d
y
n
a
m
ic
b
etwe
en
X
an
d
T
h
r
ea
d
s
,
wh
er
e
in
itial
d
is
s
atis
f
ac
tio
n
with
X
d
u
e
to
co
n
tr
o
v
er
s
ial
ch
an
g
es
co
n
tr
ib
u
ted
to
e
ar
ly
p
o
s
itiv
e
s
en
tim
en
ts
to
war
d
s
T
h
r
ea
d
s
.
H
o
wev
er
,
as
T
h
r
ea
d
s
'
u
s
er
en
g
ag
em
en
t
wan
e
d
,
X
b
eg
an
to
r
ec
o
v
er
its
u
s
er
b
ase.
Ou
r
f
in
d
in
g
s
in
d
icate
th
at
p
o
s
i
tiv
e
s
en
tim
en
ts
to
war
d
f
ea
tu
r
es
,
u
s
ab
ilit
y
,
d
esig
n
,
an
d
s
u
p
p
o
r
t
in
o
n
e
p
latf
o
r
m
o
f
ten
co
r
r
elate
with
d
is
s
atis
f
ac
ti
o
n
in
th
ese
ar
ea
s
o
n
th
e
r
iv
al
p
latf
o
r
m
,
s
u
g
g
esti
n
g
th
at
en
h
an
ce
m
e
n
ts
in
o
n
e
a
p
p
ca
n
n
e
g
ativ
ely
im
p
ac
t
p
e
r
c
ep
tio
n
s
o
f
th
e
o
th
er
.
No
ta
b
ly
,
th
is
r
elatio
n
s
h
ip
is
u
n
d
er
s
co
r
e
d
b
y
n
eg
ativ
e
co
r
r
e
latio
n
s
s
u
ch
as
-
0
.
0
6
0
7
7
5
a
n
d
-
0
.
0
4
9
7
1
9
b
etwe
en
th
e
u
s
ab
ili
ty
an
d
f
ea
tu
r
es
o
f
X
an
d
T
h
r
ea
d
s
,
r
esp
ec
tiv
ely
.
W
h
ile
th
ese
in
s
ig
h
ts
ar
e
v
alu
ab
l
e,
th
e
s
tu
d
y
'
s
lim
itatio
n
s
in
clu
d
e
a
n
ar
r
o
w
d
ata
s
et
th
at
m
ig
h
t
n
o
t
f
u
lly
ca
p
tu
r
e
th
e
f
lu
id
d
y
n
am
ics
o
f
s
o
cial
m
e
d
ia
tr
en
d
s
an
d
u
s
er
b
eh
av
i
o
u
r
ch
an
g
es
p
o
s
t
-
an
aly
s
is
.
Mo
r
eo
v
er
,
th
e
s
en
tim
en
t
an
al
y
s
is
u
s
ed
m
ay
n
o
t
f
u
lly
g
r
asp
th
e
co
m
p
lex
ities
o
f
h
u
m
an
e
m
o
ti
o
n
d
u
e
to
th
e
b
r
o
ad
k
ey
wo
r
d
s
elec
tio
n
.
T
o
ad
d
r
ess
th
ese
g
ap
s
,
f
u
tu
r
e
r
esear
c
h
s
h
o
u
ld
d
el
v
e
d
ee
p
er
in
to
s
en
tim
en
t a
n
aly
s
is
at
m
o
r
e
g
r
an
u
lar
lev
els
an
d
co
n
s
id
er
d
iv
er
s
e
d
em
o
g
r
a
p
h
ic
f
ac
to
r
s
to
u
n
d
er
s
tan
d
b
etter
wh
at
d
r
iv
es
u
s
er
p
r
ef
er
en
ce
s
an
d
s
atis
f
ac
tio
n
ac
r
o
s
s
d
if
f
er
en
t so
cial
m
ed
ia
p
latf
o
r
m
s
.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
e
a
u
t
h
o
r
s
s
i
n
c
e
r
e
l
y
t
h
a
n
k
t
h
e
M
i
n
i
s
t
r
y
o
f
C
o
m
m
u
n
i
c
a
ti
o
n
a
n
d
I
n
f
o
r
m
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
I
n
d
o
n
e
s
i
a
(
K
O
M
I
NF
O
)
,
f
o
r
p
r
o
v
i
d
i
n
g
t
h
e
s
c
h
o
l
a
r
s
h
i
p
a
n
d
f
i
n
a
n
c
i
a
l
s
u
p
p
o
r
t
t
h
a
t
m
a
d
e
t
h
i
s
s
t
u
d
y
a
n
d
r
e
s
e
a
r
c
h
p
o
s
s
i
b
l
e
.
T
h
is
a
s
s
i
s
t
a
n
c
e
h
a
s
b
e
e
n
i
n
s
t
r
u
m
e
n
tal
i
n
f
a
c
i
li
t
a
ti
n
g
t
h
e
p
u
r
s
u
i
t
o
f
a
ca
d
e
m
i
c
e
n
d
e
a
v
o
u
r
s
a
n
d
c
o
n
t
r
i
b
u
t
i
n
g
t
o
c
o
m
p
l
e
t
i
n
g
t
h
i
s
p
a
p
e
r
.
T
h
e
a
u
t
h
o
r
s
s
i
n
ce
r
el
y
a
p
p
r
e
c
i
at
e
t
h
e
o
p
p
o
r
t
u
n
i
t
i
es
a
n
d
r
es
o
u
r
c
e
s
p
r
o
v
i
d
e
d
b
y
Ko
m
i
n
f
o
,
w
h
i
c
h
h
a
v
e
c
o
n
t
r
i
b
u
t
e
d
s
i
g
n
i
f
i
c
a
n
t
l
y
t
o
t
h
e
a
d
v
a
n
c
e
m
e
n
t
o
f
k
n
o
w
l
e
d
g
e
a
n
d
t
h
e
s
u
c
c
es
s
f
u
l
c
o
m
p
le
t
i
o
n
o
f
t
h
i
s
p
a
p
e
r
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
User
s
en
timen
t d
yn
a
mics in
s
o
cia
l m
ed
ia
:
a
c
o
mp
a
r
a
tive
a
n
a
lysi
s
o
f X
a
n
d
Th
r
ea
d
s
(
R
ezki
K
h
a
ir
u
n
n
a
s
)
455
RE
F
E
R
E
NC
E
S
[
1
]
M
.
A
.
H
a
b
i
b
a
n
d
M
.
A
.
H
.
A
n
i
k
,
“
I
mp
a
c
t
s
o
f
c
o
v
i
d
-
1
9
o
n
t
r
a
n
s
p
o
r
t
m
o
d
e
s
a
n
d
mo
b
i
l
i
t
y
b
e
h
a
v
i
o
r
:
a
n
a
l
y
s
i
s
o
f
p
u
b
l
i
c
d
i
sc
o
u
r
se
i
n
t
w
i
t
t
e
r
,
”
T
r
a
n
s
p
o
rt
a
t
i
o
n
Re
s
e
a
r
c
h
Re
c
o
rd
,
v
o
l
.
2
6
7
7
,
n
o
.
4
,
p
p
.
6
5
–
7
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
7
7
/
0
3
6
1
1
9
8
1
2
1
1
0
2
9
9
2
6
.
[
2
]
L.
P
o
p
h
a
l
,
“
S
h
o
u
l
d
y
o
u
a
d
d
t
h
r
e
a
d
s
t
o
y
o
u
r
so
c
i
a
l
m
e
d
i
a
st
r
a
t
e
g
y
?
,
”
I
n
f
o
rm
a
t
i
o
n
T
o
d
a
y
,
v
o
l
.
4
0
,
n
o
.
7
,
p
p
.
3
9
–
4
0
,
2
0
2
3
.
[
3
]
D
.
F
.
C
a
r
r
,
“
T
h
r
e
a
d
s
a
p
p
u
sa
g
e
d
o
w
n
7
9
%
a
f
t
e
r
a
m
o
n
t
h
,
”
S
i
m
i
l
a
r
We
b
.
A
c
c
e
ss
e
d
:
F
e
b
.
1
2
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
si
m
i
l
a
r
w
e
b
.
c
o
m/
b
l
o
g
/
i
n
s
i
g
h
t
s
/
s
o
c
i
a
l
-
m
e
d
i
a
-
n
e
w
s/
t
h
r
e
a
d
s
-
f
i
r
st
-
mo
n
t
h
/
[
4
]
B
.
L
i
u
,
S
e
n
t
i
m
e
n
t
a
n
a
l
y
si
s
a
n
d
o
p
i
n
i
o
n
m
i
n
i
n
g
.
M
o
r
g
a
n
&
C
l
a
y
p
o
o
l
P
u
b
l
i
s
h
e
r
s,
2
0
1
2
.
[
5
]
C
.
A
.
I
g
l
e
si
a
s
a
n
d
A
.
M
o
r
e
n
o
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
si
s
f
o
r
s
o
c
i
a
l
m
e
d
i
a
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
9
,
n
o
.
2
3
,
N
o
v
.
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
9
2
3
5
0
3
7
.
[
6
]
M
.
C
.
R
a
h
ma
d
a
n
,
A
.
N
.
H
i
d
a
y
a
n
t
o
,
D
.
S
.
E
k
a
sar
i
,
B
.
P
u
r
w
a
n
d
a
r
i
,
a
n
d
Th
e
r
e
si
a
w
a
t
i
,
“
S
e
n
t
i
m
e
n
t
a
n
a
l
y
si
s
a
n
d
t
o
p
i
c
mo
d
e
l
l
i
n
g
u
si
n
g
t
h
e
l
d
a
me
t
h
o
d
r
e
l
a
t
e
d
t
o
t
h
e
f
l
o
o
d
d
i
sast
e
r
i
n
j
a
k
a
r
t
a
o
n
t
w
i
t
t
e
r
,
”
i
n
2
0
2
0
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
f
o
rm
a
t
i
c
s,
M
u
l
t
i
m
e
d
i
a
,
C
y
b
e
r
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
(
I
C
I
M
C
I
S
)
,
I
EEE,
N
o
v
.
2
0
2
0
,
p
p
.
1
2
6
–
130
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
M
C
I
S
5
1
5
6
7
.
2
0
2
0
.
9
3
5
4
3
2
0
.
[
7
]
M
u
ss
a
l
i
m
u
n
,
E.
H
.
K
h
a
s
b
y
,
G
.
I
.
D
z
i
k
r
i
l
l
a
h
,
a
n
d
M
u
l
j
o
n
o
,
“
C
o
m
p
a
r
i
so
n
o
f
k
-
n
e
a
r
e
s
t
n
e
i
g
h
b
o
r
(
K
-
N
N
)
a
n
d
n
a
ï
v
e
b
a
y
e
s
a
l
g
o
r
i
t
h
m
f
o
r
se
n
t
i
me
n
t
a
n
a
l
y
s
i
s
o
n
g
o
o
g
l
e
p
l
a
y
s
t
o
r
e
t
e
x
t
u
a
l
r
e
v
i
e
w
s
,
”
i
n
2
0
2
1
8
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
C
o
m
p
u
t
e
r
a
n
d
E
l
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
(
I
C
I
T
AC
E
E)
,
I
EEE,
S
e
p
.
2
0
2
1
,
p
p
.
1
8
0
–
1
8
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
TA
C
EE5
3
1
8
4
.
2
0
2
1
.
9
6
1
7
2
1
7
.
[
8
]
B
.
R
.
S
,
S
.
L.
G
.
M
o
s
e
s,
G
.
C
h
i
n
n
a
d
u
r
a
i
,
J.
V
.
A
n
a
n
d
,
V
.
J
a
n
a
k
i
r
a
m
a
n
,
a
n
d
P
.
A
n
a
n
d
,
“
S
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
f
o
r
i
ma
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
t
h
e
Asi
a
t
i
c
S
o
c
i
e
t
y
o
f
Mu
m
b
a
i
,
v
o
l
.
9
7
,
n
o
.
4
,
2
0
2
3
.
[
9
]
E.
A
.
S
u
k
ma,
A
.
N
.
H
i
d
a
y
a
n
t
o
,
A
.
I
.
P
a
n
d
e
s
e
n
d
a
,
A
.
N
.
Y
a
h
y
a
,
P
.
W
i
d
h
a
r
t
o
,
a
n
d
U
.
R
a
h
a
r
d
j
a
,
“
S
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s
o
f
t
h
e
n
e
w
i
n
d
o
n
e
si
a
n
g
o
v
e
r
n
m
e
n
t
p
o
l
i
c
y
(
o
mn
i
b
u
s
l
a
w
)
o
n
so
c
i
a
l
me
d
i
a
t
w
i
t
t
e
r
,
”
i
n
2
0
2
0
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
f
o
rm
a
t
i
c
s
,
Mu
l
t
i
m
e
d
i
a
,
C
y
b
e
r
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
(
I
C
I
MC
I
S
)
,
N
o
v
.
2
0
2
0
,
p
p
.
1
5
3
–
158
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
M
C
I
S
5
1
5
6
7
.
2
0
2
0
.
9
3
5
4
2
8
7
.
[
1
0
]
C
.
S
a
n
a
v
i
o
,
E
.
T
i
g
n
o
n
e
,
a
n
d
E.
Er
c
o
l
e
ssi
,
“
E
n
t
a
n
g
l
e
me
n
t
c
l
a
ss
i
f
i
c
a
t
i
o
n
v
i
a
w
i
t
n
e
ss
o
p
e
r
a
t
o
r
s
g
e
n
e
r
a
t
e
d
b
y
s
u
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
,
”
T
h
e
Eu
r
o
p
e
a
n
P
h
y
s
i
c
a
l
J
o
u
r
n
a
l
Pl
u
s
,
v
o
l
.
1
3
8
,
n
o
.
1
0
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
4
0
/
e
p
j
p
/
s1
3
3
6
0
-
023
-
0
4
5
4
6
-
5.
[
1
1
]
A
.
A
c
í
n
,
D
.
B
r
u
ß
,
M
.
Le
w
e
n
s
t
e
i
n
,
a
n
d
A
.
S
a
n
p
e
r
a
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
m
i
x
e
d
t
h
r
e
e
-
q
u
b
i
t
s
t
a
t
e
s,
”
P
h
y
si
c
a
l
R
e
v
i
e
w
L
e
t
t
e
rs
,
v
o
l
.
8
7
,
n
o
.
4
,
p
.
0
4
0
4
0
1
,
J
u
l
.
2
0
0
1
,
d
o
i
:
1
0
.
1
1
0
3
/
P
h
y
s
R
e
v
Le
t
t
.
8
7
.
0
4
0
4
0
1
.
[
1
2
]
A
.
B
h
a
l
l
a
,
“
C
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
s
i
s
o
f
t
e
x
t
c
l
a
s
s
i
f
i
c
a
t
i
o
n
u
s
i
n
g
s
v
m
,
n
a
ï
v
e
b
a
y
e
s
,
a
n
d
k
n
n
m
o
d
e
l
s
,
”
i
n
2
0
2
3
5
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
v
e
n
t
i
v
e
R
e
s
e
a
r
c
h
i
n
C
o
m
p
u
t
i
n
g
A
p
p
l
i
c
a
t
i
o
n
s
(
I
C
I
R
C
A
)
,
A
u
g
.
2
0
2
3
,
p
p
.
8
7
8
–
8
8
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
R
C
A
5
7
9
8
0
.
2
0
2
3
.
1
0
2
2
0
7
2
8
.
[
1
3
]
M
.
D
.
H
.
J
a
sy
,
S
.
A
l
H
a
sa
n
,
M
.
I
.
K
.
S
a
g
o
r
,
A
.
N
o
ma
n
,
a
n
d
J.
M
.
J
i
,
“
A
p
e
r
f
o
r
ma
n
c
e
e
v
a
l
u
a
t
i
o
n
o
f
s
e
n
t
i
m
e
n
t
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
p
p
l
y
i
n
g
sv
m,
k
n
n
,
a
n
d
n
a
i
v
e
b
a
y
e
s,”
i
n
2
0
2
1
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
i
n
g
,
N
e
t
w
o
rk
i
n
g
,
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
s
&
E
n
g
i
n
e
e
ri
n
g
S
c
i
e
n
c
e
s
A
p
p
l
i
c
a
t
i
o
n
s (C
o
N
T
ES
A)
,
I
EEE,
D
e
c
.
2
0
2
1
,
p
p
.
5
6
–
60
,
d
o
i
:
1
0
.
1
1
0
9
/
C
o
N
TESA
5
2
8
1
3
.
2
0
2
1
.
9
6
5
7
1
1
5
.
[
1
4
]
M
.
S
.
S
h
a
q
i
r
i
,
T
.
I
l
j
a
z
i
,
L.
K
a
m
b
e
r
i
,
a
n
d
R
.
R
a
ma
n
i
-
H
a
l
i
l
i
,
“
D
i
f
f
e
r
e
n
c
e
s
b
e
t
w
e
e
n
t
h
e
c
o
r
r
e
l
a
t
i
o
n
c
o
e
f
f
i
c
i
e
n
t
s
p
e
a
r
so
n
,
k
e
n
d
a
l
l
a
n
d
sp
e
a
r
ma
n
,
”
i
n
5
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
ren
c
e
o
f
N
a
t
u
r
a
l
S
c
i
e
n
c
e
a
n
d
M
a
t
h
e
m
a
t
i
c
s
,
Te
t
o
v
o
,
2
0
2
3
,
p
p
.
3
9
2
-
397
.
[
1
5
]
T.
G
n
a
mb
s
,
“
A
b
r
i
e
f
n
o
t
e
o
n
t
h
e
s
t
a
n
d
a
r
d
e
r
r
o
r
o
f
t
h
e
p
e
a
r
so
n
c
o
r
r
e
l
a
t
i
o
n
,
”
C
o
l
l
a
b
ra
:
Ps
y
c
h
o
l
o
g
y
,
v
o
l
.
9
,
n
o
.
1
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
1
5
2
5
/
c
o
l
l
a
b
r
a
.
8
7
6
1
5
.
[
1
6
]
H
.
A
l
-
O
k
l
a
h
,
T
.
M
.
S
a
i
d
,
a
n
d
T
.
A
l
o
d
a
t
,
I
n
t
r
o
d
u
c
t
i
o
n
t
o
S
t
a
t
i
s
t
i
c
s
M
a
d
e
E
a
s
y
,
R
i
y
a
d
h
,
S
a
u
d
i
A
r
a
b
i
a
:
K
i
n
g
S
a
u
d
U
n
i
v
e
r
s
i
t
y
P
r
e
s
s
,
2
0
1
4
.
[
1
7
]
K
.
H
a
me
l
i
,
T
e
k
n
i
k
a
t
st
a
t
i
st
i
k
o
re
m
e
s
h
u
m
ë
n
d
r
y
sh
o
r
e
m
e
a
p
l
i
k
i
m
n
ë
s
p
ss
.
O
p
e
n
S
o
u
r
c
e
,
2
0
1
5
.
[
1
8
]
A
.
M
.
R
a
h
a
t
,
A
.
K
a
h
i
r
,
a
n
d
A
.
K
.
M
.
M
a
s
u
m,
“
C
o
mp
a
r
i
s
o
n
o
f
n
a
i
v
e
b
a
y
e
s
a
n
d
s
v
m
a
l
g
o
r
i
t
h
m
b
a
se
d
o
n
se
n
t
i
me
n
t
a
n
a
l
y
si
s
u
s
i
n
g
r
e
v
i
e
w
d
a
t
a
se
t
,
”
i
n
2
0
1
9
8
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
S
y
s
t
e
m
Mo
d
e
l
i
n
g
a
n
d
A
d
v
a
n
c
e
m
e
n
t
i
n
R
e
se
a
rc
h
T
re
n
d
s
(
S
MA
RT)
,
2
0
1
9
,
p
p
.
2
6
6
–
270
,
d
o
i
:
1
0
.
1
1
0
9
/
S
M
A
R
T
4
6
8
6
6
.
2
0
1
9
.
9
1
1
7
5
1
2
.
[
1
9
]
S
.
A
m
r
i
e
,
S
.
K
u
r
n
i
a
w
a
n
,
J
.
H
.
W
i
n
d
i
a
t
m
a
j
a
,
a
n
d
Y
.
R
u
l
d
e
v
i
y
a
n
i
,
“
A
n
a
l
y
s
i
s
o
f
g
o
o
g
l
e
p
l
a
y
s
t
o
r
e
’
s
s
e
n
t
i
m
e
n
t
r
e
v
i
e
w
o
n
i
n
d
o
n
e
s
i
a
’
s
p
2
p
f
i
n
t
e
c
h
p
l
a
t
f
o
r
m
,
”
i
n
2
0
2
2
I
E
E
E
D
e
l
h
i
S
e
c
t
i
o
n
C
o
n
f
e
r
e
n
c
e
(
D
E
L
C
O
N
)
,
F
e
b
.
2
0
2
2
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
D
E
L
C
O
N
5
4
0
5
7
.
2
0
2
2
.
9
7
5
3
1
0
8
.
[
2
0
]
S
.
K
u
m
a
r
,
N
.
A
.
Jai
l
a
n
i
,
A
.
R
.
S
i
n
g
h
,
a
n
d
S
.
P
a
n
c
h
a
l
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
si
s
o
n
o
n
l
i
n
e
r
e
v
i
e
w
s
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
n
l
t
k
,
”
i
n
2
0
2
2
6
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
T
re
n
d
s
i
n
E
l
e
c
t
r
o
n
i
c
s
a
n
d
I
n
f
o
rm
a
t
i
c
s
(
I
C
O
EI
)
,
I
EEE,
A
p
r
.
2
0
2
2
,
p
p
.
1
1
8
3
–
1
1
8
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
O
EI
5
3
5
5
6
.
2
0
2
2
.
9
7
7
6
8
5
0
.
[
2
1
]
A
.
P
.
P
i
m
p
a
l
k
a
r
a
n
d
R
.
J
.
R
.
R
a
j
,
“
I
n
f
l
u
e
n
c
e
o
f
p
r
e
-
p
r
o
c
e
ss
i
n
g
s
t
r
a
t
e
g
i
e
s o
n
t
h
e
p
e
r
f
o
r
ma
n
c
e
o
f
m
l
c
l
a
ss
i
f
i
e
r
s
e
x
p
l
o
i
t
i
n
g
t
f
-
i
d
f
a
n
d
b
o
w
f
e
a
t
u
r
e
s
,
”
AD
C
AI
J
:
Ad
v
a
n
c
e
s
i
n
D
i
st
ri
b
u
t
e
d
C
o
m
p
u
t
i
n
g
a
n
d
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
J
o
u
rn
a
l
,
v
o
l
.
9
,
n
o
.
2
,
p
p
.
4
9
–
6
8
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
4
2
0
1
/
A
D
C
A
I
J2
0
2
0
9
2
4
9
6
8
.
[
2
2
]
Z.
H
u
a
n
g
a
n
d
M
.
B
e
n
y
o
u
c
e
f
,
“
A
s
y
s
t
e
mat
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
o
f
m
o
b
i
l
e
a
p
p
l
i
c
a
t
i
o
n
u
sa
b
i
l
i
t
y
:
a
d
d
r
e
ss
i
n
g
t
h
e
d
e
s
i
g
n
p
e
r
s
p
e
c
t
i
v
e
,
”
U
n
i
v
e
rs
a
l
Ac
c
e
ss
i
n
t
h
e
I
n
f
o
rm
a
t
i
o
n
S
o
c
i
e
t
y
,
v
o
l
.
2
2
,
n
o
.
3
,
p
p
.
7
1
5
–
7
3
5
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
2
0
9
-
0
2
2
-
0
0
9
0
3
-
w.
[
2
3
]
D
.
A
n
a
n
d
y
a
,
I
n
d
a
r
i
n
i
,
a
n
d
A
.
T
.
S
e
p
t
i
a
n
i
,
“
T
h
e
f
o
r
m
a
t
i
o
n
o
f
c
u
s
t
o
m
e
r
s
a
t
i
s
f
a
c
t
i
o
n
i
n
s
o
c
i
a
l
m
e
d
i
a
,
t
h
e
r
o
l
e
o
f
f
r
e
q
u
e
n
c
y
,
a
n
d
d
u
r
a
t
i
o
n
o
f
u
s
e
,
”
i
n
T
h
e
1
7
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
s
i
u
m
o
n
M
a
n
a
g
e
m
e
n
t
(
I
N
S
Y
M
A
2
0
2
0
)
,
P
a
r
i
s
,
A
t
l
a
n
t
i
s
P
r
e
s
s
,
2
0
2
0
,
d
o
i
:
1
0
.
2
9
9
1
/
a
e
b
m
r
.
k
.
2
0
0
1
2
7
.
0
1
8
.
[
2
4
]
B
.
M
.
M
a
r
t
i
n
e
z
a
n
d
L.
E.
M
c
A
n
d
r
e
w
s,
“
T
h
e
i
n
f
l
u
e
n
c
e
o
f
m
o
b
i
l
e
a
p
p
l
i
c
a
t
i
o
n
d
e
s
i
g
n
f
e
a
t
u
r
e
s
o
n
u
s
e
r
s’
st
i
c
k
i
n
e
ss
i
n
t
e
n
t
i
o
n
s
a
s
med
i
a
t
e
d
b
y
e
m
o
t
i
o
n
a
l
r
e
sp
o
n
se,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Re
t
a
i
l
&
D
i
s
t
ri
b
u
t
i
o
n
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
4
9
,
n
o
.
1
1
,
p
p
.
1
4
9
7
–
1
5
1
1
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
8
/
I
JR
D
M
-
06
-
2
0
2
0
-
0
2
3
2
.
[
2
5
]
N
.
L
.
R
a
n
e
,
A
.
A
c
h
a
r
i
,
a
n
d
S
.
P
.
C
h
o
u
d
h
a
r
y
,
“
E
n
h
a
n
c
i
n
g
c
u
s
t
o
mer
l
o
y
a
l
t
y
t
h
r
o
u
g
h
q
u
a
l
i
t
y
o
f
s
e
r
v
i
c
e
:
e
f
f
e
c
t
i
v
e
s
t
r
a
t
e
g
i
e
s
t
o
i
m
p
r
o
v
e
c
u
s
t
o
m
e
r
s
a
t
i
sf
a
c
t
i
o
n
,
e
x
p
e
r
i
e
n
c
e
,
r
e
l
a
t
i
o
n
s
h
i
p
,
a
n
d
e
n
g
a
g
e
me
n
t
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
Re
s
e
a
r
c
h
J
o
u
rn
a
l
o
f
M
o
d
e
r
n
i
z
a
t
i
o
n
i
n
E
n
g
i
n
e
e
ri
n
g
T
e
c
h
n
o
l
o
g
y
a
n
d
S
c
i
e
n
c
e
,
v
o
l
.
5
,
n
o
.
5
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
5
6
7
2
6
/
I
R
JM
ETS
3
8
1
0
4
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Re
z
k
i
K
h
a
irun
n
a
s
is
p
u
rs
u
in
g
a
m
a
ste
r'
s
in
in
fo
rm
a
ti
o
n
t
e
c
h
n
o
l
o
g
y
a
t
th
e
Un
iv
e
rsity
o
f
In
d
o
n
e
sia
(UI).
He
o
b
tai
n
e
d
h
is
b
a
c
h
e
lo
r'
s
d
e
g
re
e
i
n
in
fo
rm
a
ti
o
n
sy
ste
m
s
a
n
d
tec
h
n
o
l
o
g
y
fr
o
m
t
h
e
Ba
n
d
u
n
g
I
n
st
it
u
te
o
f
Tec
h
n
o
lo
g
y
(IT
B)
i
n
2
0
1
8
.
He
h
a
s
sin
c
e
b
e
e
n
a
c
ti
v
e
ly
e
n
g
a
g
e
d
a
s
a
n
IT
Co
n
su
lt
a
n
t,
le
v
e
ra
g
in
g
h
is
e
x
p
e
rti
se
to
tac
k
le
c
o
m
p
lex
c
h
a
ll
e
n
g
e
s
in
t
h
e
in
d
u
stry
.
He
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
re
z
k
i.
k
h
a
ir
u
n
n
a
s@
u
i.
a
c
.
i
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
5
:
447
-
4
5
6
456
J
e
r
i
Apria
n
sy
a
h
P
a
g
u
a
is
a
se
a
so
n
e
d
b
a
n
k
in
g
p
r
o
fe
ss
io
n
a
l
wit
h
a
b
a
c
h
e
lo
r'
s
d
e
g
re
e
in
I
n
fo
rm
a
ti
c
Tec
h
n
o
l
o
g
y
fr
o
m
t
h
e
Un
i
v
e
rsity
o
f
Be
n
g
k
u
l
u
a
n
d
is
c
u
rre
n
tl
y
p
u
rsu
in
g
a
M
a
ste
r
o
f
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
a
t
th
e
Un
iv
e
rsity
o
f
In
d
o
n
e
sia
.
Be
y
o
n
d
h
is
p
r
o
fe
ss
io
n
a
l
e
n
d
e
a
v
o
u
rs
,
he
is
d
e
e
p
l
y
imm
e
rse
d
in
re
se
a
rc
h
,
fo
c
u
sin
g
o
n
i
n
fo
rm
a
ti
o
n
re
tri
e
v
a
l
,
IT
a
d
o
p
t
io
n
,
k
n
o
wle
d
g
e
m
a
n
a
g
e
m
e
n
t,
d
a
ta
m
a
n
a
g
e
m
e
n
t,
a
n
d
p
ro
jec
t
m
a
n
a
g
e
m
e
n
t
.
He
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
jeri.
a
p
rian
sy
a
h
@
u
i.
a
c
.
i
d
.
G
h
in
a
Fi
tr
iy
a
h
o
ld
s
a
b
a
c
h
e
l
o
r'
s
d
e
g
re
e
i
n
a
p
p
li
e
d
c
o
m
p
u
ter
sc
ien
c
e
fro
m
t
h
e
S
tate
P
o
ly
tec
h
n
ic
o
f
Cy
b
e
r
a
n
d
Cr
y
p
t
o
with
a
m
a
jo
r
i
n
c
y
b
e
rse
c
u
rit
y
in
2
0
2
0
.
S
h
e
is
p
u
rsu
i
n
g
a
m
a
ste
r'
s
d
e
g
re
e
a
t
th
e
Un
iv
e
rsity
o
f
In
d
o
n
e
sia
'
s
F
a
c
u
lt
y
o
f
C
o
m
p
u
t
e
r
S
c
ien
c
e
.
Wi
th
e
x
p
e
rien
c
e
in
c
y
b
e
rse
c
u
rit
y
a
n
d
c
y
b
e
r
in
c
i
d
e
n
t
h
a
n
d
li
n
g
,
sh
e
is
p
u
rsu
in
g
re
se
a
rc
h
in
n
e
two
rk
se
c
u
rit
y
,
c
o
m
p
u
ter
f
o
re
n
sic
s,
k
n
o
wle
d
g
e
m
a
n
a
g
e
m
e
n
t,
a
n
d
in
c
i
d
e
n
t
re
sp
o
n
se
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
g
h
in
a
.
f
it
riy
a
@
u
i.
a
c
.
id
.
Yo
v
a
Rul
d
e
v
iy
a
n
i
h
o
l
d
s
b
a
c
h
e
lo
r'
s
a
n
d
m
a
ste
r'
s
d
e
g
re
e
s
in
c
o
m
p
u
ter
sc
ien
c
e
fro
m
th
e
Un
i
v
e
rsity
o
f
I
n
d
o
n
e
sia
a
n
d
c
u
rre
n
tl
y
se
rv
e
s
a
s
a
n
a
ss
o
c
iate
p
ro
f
e
ss
o
r
a
t
th
e
sa
m
e
in
stit
u
ti
o
n
.
He
r
re
se
a
rc
h
in
tere
sts
e
n
c
o
m
p
a
ss
Da
tab
a
se
sy
ste
m
s,
b
u
sin
e
ss
in
tel
li
g
e
n
c
e
,
e
n
terp
rise
re
so
u
rc
e
p
lan
n
in
g
,
e
-
g
o
v
e
r
n
m
e
n
t,
a
n
d
so
ft
wa
re
d
e
v
e
lo
p
m
e
n
t.
Wi
t
h
e
x
p
e
rti
se
in
IS
/I
T
m
a
n
a
g
e
m
e
n
t
&
g
o
v
e
r
n
a
n
c
e
,
so
ftwa
re
e
n
g
in
e
e
ri
n
g
,
a
n
d
d
a
ta
sc
ien
c
e
&
a
n
a
ly
ti
c
s.
S
h
e
h
a
s
m
a
d
e
sig
n
ifi
c
a
n
t
a
c
a
d
e
m
ic co
n
tri
b
u
ti
o
n
s
th
r
o
u
g
h
n
u
m
e
ro
u
s
p
u
b
li
c
a
ti
o
n
s
a
n
d
re
se
a
rc
h
p
ro
jec
ts.
He
r
d
e
d
ica
ti
o
n
to
a
d
v
a
n
c
in
g
k
n
o
wle
d
g
e
a
n
d
in
n
o
v
a
ti
o
n
in
a
re
a
s
su
c
h
a
s
E
-
g
o
v
e
rn
m
e
n
t
a
n
d
s
o
ftwa
re
e
n
g
i
n
e
e
rin
g
e
sta
b
li
sh
e
s
h
e
r
a
s
a
p
r
o
m
in
e
n
t
f
ig
u
re
in
c
o
m
p
u
ter
sc
ien
c
e
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
yov
a
@c
s.u
i.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.