I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
11
,
No
.
4
,
A
u
g
u
s
t
2021
,
p
p
.
3
4
2
4
~
3
4
3
3
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
11
i
4
.
pp
3
4
2
4
-
3
4
3
3
3424
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
The i
m
pa
ct
o
f
sen
ti
m
ent
ana
ly
sis
f
r
o
m
use
r on Face
b
o
o
k
t
o
enha
nced
the
se
rv
ice quality
Da
niel D.
Albes
t
a
,
M
icha
el
L
.
J
o
na
t
ha
n
,
M
uh
a
m
m
a
d J
a
w
ad
, O
k
t
o
v
ia
nu
s
H
a
rdia
wa
n
,
Der
w
in Su
ha
rt
o
no
Co
m
p
u
ter S
c
ien
c
e
De
p
a
rtm
e
n
t,
S
c
h
o
o
l
o
f
Co
m
p
u
ter S
c
ien
c
e
,
Bi
n
a
Nu
sa
n
tara
U
n
iv
e
rsity
,
Ja
k
a
rta,
In
d
o
n
e
si
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
8
,
2
0
2
0
R
ev
i
s
ed
Dec
2
2
,
2
0
2
0
A
cc
ep
ted
J
an
1
9
,
2
0
2
1
F
a
c
e
b
o
o
k
'
s
in
f
lu
e
n
c
e
o
n
th
e
m
o
d
e
rn
so
c
ial
m
e
d
ia
p
lat
f
o
r
m
is
u
n
d
o
u
b
ted
ly
e
n
o
rm
o
u
s.
W
h
il
e
it
h
a
s
g
o
tt
e
n
a
b
a
c
k
las
h
f
o
r
it
s
in
a
b
il
it
y
to
c
o
n
tro
l
it
s
in
f
lu
e
n
c
e
o
v
e
r
i
m
p
o
rtan
t
a
ff
a
irs,
th
e
re
a
re
stil
l
m
a
n
y
q
u
e
stio
n
s
re
g
a
rd
in
g
p
e
o
p
le'
s
p
e
rc
e
p
ti
o
n
o
f
F
a
c
e
b
o
o
k
a
n
d
t
h
e
ir
se
n
ti
m
e
n
t
o
v
e
r
F
a
c
e
b
o
o
k
.
T
h
is
p
a
p
e
r
'
s
ro
le
i
n
t
h
is
o
n
g
o
in
g
d
e
b
a
t
e
is
to
g
iv
e
a
g
li
m
p
se
o
f
p
e
o
p
le'
s
se
n
ti
m
e
n
t
a
n
d
p
e
rc
e
p
ti
o
n
o
f
F
a
c
e
b
o
o
k
in
re
c
e
n
t
ti
m
e
s.
B
y
c
o
ll
e
c
ti
n
g
sa
m
p
les
d
a
ta
f
ro
m
F
a
c
e
b
o
o
k
'
s
T
o
p
P
a
g
e
,
th
is
p
a
p
e
r
h
o
p
e
s
t
o
re
p
re
se
n
t
a
sig
n
if
ica
n
t
a
m
o
u
n
t
o
f
p
e
o
p
le'
s
a
sp
iratio
n
s
to
w
a
rd
s
th
is
c
o
m
p
a
n
y
.
B
y
p
ro
c
e
ss
in
g
th
e
d
a
ta
w
it
h
a
p
ro
c
e
ss
in
g
to
o
l
t
o
c
o
n
str
u
c
t
a
n
d
m
o
d
e
l
o
u
t
th
e
d
a
ta
a
n
d
a
se
n
ti
m
e
n
t
a
n
a
ly
z
e
r
to
o
l
h
e
l
p
s
d
e
term
in
e
th
e
se
n
ti
m
e
n
t,
th
is
p
a
p
e
r
c
a
n
d
e
d
u
c
e
a
6
0
0
-
c
o
m
m
e
n
t
w
o
rth
o
f
p
ro
c
e
ss
e
d
d
a
ta.
T
h
e
re
su
lt
s
f
ro
m
th
e
6
0
0
sa
m
p
led
c
o
m
m
e
n
t
s
c
o
n
c
lu
d
e
d
th
a
t
t
h
e
se
n
ti
m
e
n
ts
to
w
a
rd
s
F
a
c
e
b
o
o
k
a
re
4
1
.
5
0
%
n
e
g
a
ti
v
e
c
o
m
m
e
n
ts,
2
2
.
8
3
%
n
e
u
tral
c
o
m
m
e
n
ts,
a
n
d
3
5
.
6
7
%
p
o
siti
v
e
c
o
m
m
e
n
ts.
K
ey
w
o
r
d
s
:
Data
m
i
n
i
n
g
Face
b
o
o
k
Sen
ti
m
e
n
t a
n
a
l
y
s
is
Ser
v
ice
q
u
ali
t
y
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
:
Der
w
i
n
S
u
h
ar
to
n
o
C
o
m
p
u
ter
Scien
ce
Dep
ar
t
m
en
t,
Sch
o
o
l o
f
C
o
m
p
u
ter
Scie
n
ce
B
in
a
Nu
s
an
tar
a
U
n
i
v
er
s
it
y
K.
H.
S
y
ah
d
a
n
9
s
tr
ee
t
,
P
al
m
e
r
ah
,
1
1
4
8
0
,
W
est
J
ak
ar
ta,
I
n
d
o
n
esia
E
m
ail:
d
s
u
h
ar
to
n
o
@
b
i
n
u
s
.
ed
u
1.
I
NT
RO
D
UCT
I
O
N
S
en
ti
m
e
n
t a
n
al
y
s
i
s
i
n
[
1
]
is
a
t
ex
t
-
b
ased
d
ata
q
u
ar
r
y
in
g
m
et
h
o
d
.
A
p
p
lied
in
an
ar
r
a
y
o
f
c
h
a
r
s
i
m
p
l
ied
ASC
I
I
co
d
e
to
p
r
o
cu
r
e
co
r
e
a
i
m
:
T
o
tag
,
ex
tr
ac
t,
an
d
b
in
d
in
-
d
ep
th
s
u
b
j
ec
tiv
el
y
i
n
f
o
r
m
at
io
n
o
f
a
s
et
o
f
t
h
e
s
o
u
r
ce
o
f
h
id
h
i
n
t
o
n
i
n
f
o
,
s
p
ec
if
icall
y
i
n
a
s
n
ip
p
et
o
f
d
ig
it
al
in
f
o
r
m
atio
n
.
Millio
n
s
o
f
i
n
f
o
r
m
atio
n
cu
r
r
en
tl
y
s
tr
ea
m
o
u
t
f
r
o
m
th
e
o
n
li
n
e
s
o
cial
co
m
m
u
n
icatio
n
ap
p
lic
atio
n
s
u
c
h
as
Face
b
o
o
k
as
a
p
ar
t
o
f
b
ig
d
ata
co
m
p
lic
it
y
.
B
ased
o
n
th
e
r
es
e
ar
ch
f
ac
t,
u
p
to
Dec
e
m
b
er
2
0
1
9
,
Face
b
o
o
k
h
as
b
ee
n
h
itti
n
g
u
p
to
b
illi
o
n
s
o
f
m
o
n
t
h
l
y
ac
ti
v
e
ac
co
u
n
t
s
,
an
d
it
w
o
u
ld
k
ee
p
r
is
in
g
i
n
2
0
2
0
an
d
b
ey
o
n
d
.
B
ased
o
n
[
2
]
,
o
v
er
h
alf
a
m
illi
o
n
co
m
m
e
n
t
s
an
d
al
m
o
s
t
o
n
e
-
t
h
i
r
d
o
f
m
illi
o
n
o
f
p
o
s
ts
e
x
is
t
n
e
w
l
y
i
n
s
id
e
it
r
e
g
u
lar
l
y
.
Mo
s
tl
y
,
all
th
e
co
n
v
e
y
ed
d
ata
in
s
er
ted
b
y
t
h
e
u
s
er
m
o
d
eled
as
a
co
m
p
ilatio
n
o
f
an
i
n
ter
p
r
etatio
n
o
f
in
f
o
r
m
a
tio
n
c
alled
o
p
in
io
n
s
.
An
o
p
in
io
n
n
ee
d
ed
to
b
e
s
et
-
b
ase
d
p
r
o
ce
s
s
ed
,
in
v
ie
w
,
i
t
w
o
u
ld
b
e
en
h
an
ce
d
t
h
e
an
al
y
zi
n
g
p
r
o
g
r
ess
f
o
r
p
u
r
p
o
s
es,
b
u
t
th
e
au
t
h
o
r
s
'
f
ield
p
o
in
ted
to
th
e
b
u
s
in
e
s
s
co
n
ce
r
n
o
f
Fac
eb
o
o
k
.
E
n
o
r
m
o
u
s
o
p
in
io
n
s
p
r
o
d
u
ce
d
ea
ch
m
in
u
te
o
n
th
e
Face
b
o
o
k
s
co
o
p
m
a
y
h
av
e
b
ee
n
in
f
l
u
e
n
ci
n
g
t
h
e
d
ev
el
o
p
m
e
n
t o
f
Face
b
o
o
k
co
m
p
a
n
y
.
An
Op
i
n
io
n
ca
n
b
e
d
er
iv
ed
a
s
ex
p
licit
l
y
o
r
i
m
p
licitl
y
a
s
e
n
s
e
f
o
r
m
o
f
s
atir
e.
B
o
th
s
en
s
es
h
a
v
e
a
co
n
s
eq
u
e
n
t
o
n
t
h
e
d
ev
elo
p
m
en
t
o
f
t
h
e
co
m
p
a
n
y
,
ca
n
b
e
d
is
astro
u
s
l
y
o
r
tr
i
u
m
p
h
a
n
tl
y
d
eter
m
in
ed
b
y
t
h
e
ef
f
ec
tiv
e
n
e
s
s
o
f
t
h
e
o
p
in
io
n
it
s
elf
,
s
o
th
e
p
o
in
t
o
f
th
e
p
r
o
b
le
m
o
cc
u
r
r
ed
is
w
h
at
t
h
e
co
n
s
eq
u
en
ce
s
o
f
a
u
s
er
o
p
in
io
n
o
n
t
h
e
Face
b
o
o
k
p
lat
f
o
r
m
to
t
h
e
Face
b
o
o
k
s
er
v
ice
q
u
alit
y
it
s
el
f
,
ar
e
t
h
e
y
w
o
u
ld
m
ak
e
t
h
e
s
er
v
ice
b
e
w
o
r
s
e
n
i
n
g
o
r
b
etter
in
g
?
An
ef
f
icien
t
m
et
h
o
d
ca
n
ac
t
as
a
d
eli
m
iter
o
n
a
v
ie
w
,
e.
g
.
,
s
e
n
ti
m
en
t
a
n
d
in
ten
t
an
al
y
s
is
.
Se
n
ti
m
en
t
an
a
l
y
s
is
is
d
ea
lin
g
w
i
th
ex
p
lici
t
i
n
f
o
r
m
ati
o
n
an
d
d
e
n
o
tes
t
h
e
h
i
g
h
lig
h
t
o
b
j
ec
t
to
b
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
Th
e
imp
a
ct
o
f sen
timen
t a
n
a
lysi
s
fr
o
m
u
s
e
r
o
n
F
a
ce
b
o
o
k
to
…
(
Da
n
iel
D.
A
lb
esta
)
3425
d
eter
m
in
ed
i
f
it
i
s
clas
s
i
f
ied
as
th
e
p
o
s
it
iv
e,
n
eu
tr
al,
o
r
m
a
y
b
e
n
e
g
ati
v
e
s
e
n
ti
m
e
n
t.
T
h
e
co
n
ce
p
t
o
f
i
n
ten
t
an
al
y
s
is
v
eiled
i
n
s
id
e
[
3
]
ta
k
e
s
a
w
h
o
le
n
e
w
lev
el
i
n
d
ea
li
n
g
w
it
h
a
n
al
y
s
is
d
ata
b
y
d
o
in
g
a
n
al
y
tics
p
r
o
ce
d
u
r
es
ap
p
lied
in
d
iv
er
s
e
u
s
er
'
s
m
e
s
s
a
g
es
to
d
eter
m
i
n
e
w
h
et
h
er
it
h
as
a
n
y
in
ten
t
io
n
c
h
e
m
is
tr
y
ass
o
ciate
s
w
it
h
p
o
s
itiv
e
o
r
n
eg
ati
v
e
ar
g
u
m
e
n
tatio
n
.
As
m
e
n
tio
n
ed
b
ef
o
r
e
th
e
ap
p
licatio
n
o
f
b
o
th
an
al
y
s
is
t
y
p
e
h
a
v
e
th
e
p
o
ten
tial
to
p
er
f
o
r
m
h
u
g
e
co
n
s
eq
u
e
n
tia
l
f
o
r
t
h
e
co
m
p
an
y
(
Face
b
o
o
k
)
its
elf
,
e.
g
.
,
As
t
h
e
s
o
u
r
ce
tak
e
n
f
r
o
m
[
4
]
.
A
s
it
i
m
p
licitl
y
tells
u
s
t
h
at
Face
b
o
o
k
is
at
t
h
e
p
o
s
itio
n
o
f
t
h
e
lo
w
es
t
b
o
u
n
d
o
f
th
e
v
is
u
aliza
t
io
n
o
f
t
h
e
g
r
ap
h
ic
c
h
ar
t
p
r
o
v
id
ed
o
f
u
s
er
s
ati
s
f
ac
t
io
n
o
f
Face
b
o
o
k
s
er
v
ices
,
w
h
ich
m
ea
n
s
t
h
at
th
e
s
er
v
ice
a
s
t
h
e
p
r
i
m
er
f
ac
to
r
d
o
es
n
o
t
f
u
l
f
ill
t
h
e
q
u
al
if
ied
p
er
ce
n
tag
e
n
ee
d
ed
f
o
r
th
e
u
s
er
s
atis
f
ac
tio
n
r
ate.
I
t
g
iv
es
r
is
e
to
th
e
u
s
er
'
s
o
p
in
io
n
to
b
e
b
ad
en
o
u
g
h
f
o
r
th
e
co
m
p
a
n
y
;
at
t
h
is
i
n
s
ta
n
t,
t
h
e
en
ta
n
g
le
m
e
n
t
o
f
s
e
n
ti
m
e
n
t
a
n
al
y
s
i
s
o
n
m
il
lio
n
s
o
f
d
ata
e
v
o
lv
e
s
i
n
to
a
p
r
i
m
ar
y
es
s
e
n
tial
tas
k
to
h
a
n
d
le
co
r
r
u
p
ted
o
p
in
io
n
f
o
r
t
h
e
s
ak
e
o
f
Face
b
o
o
k
's
f
u
tu
r
e
d
ev
elo
p
m
en
t.
A
s
i
m
p
le
b
u
t
co
m
p
r
e
h
e
n
s
i
v
e
m
eth
o
d
is
n
ee
d
ed
as
a
d
eli
m
iter
d
esire
o
f
o
p
in
io
n
b
y
u
t
ilizi
n
g
t
h
e
s
en
ti
m
e
n
t
a
n
al
y
s
i
s
m
et
h
o
d
.
T
h
is
r
esear
c
h
elab
o
r
ates
o
n
t
h
e
an
al
y
tical
o
f
s
en
ti
m
en
t
o
b
j
ec
ts
i
m
p
l
ied
w
ith
i
n
Face
b
o
o
k
'
s
es
s
en
t
ial
ele
m
e
n
t
s
s
u
ch
as
p
o
s
t
s
a
n
d
co
m
m
e
n
tar
y
ab
o
u
t
Face
b
o
o
k
s
er
v
ic
es
as
a
s
o
u
r
ce
o
f
Sen
ti
m
e
n
t d
ata
as it is r
ep
r
ese
n
ted
in
t
h
e
[
5
]
.
2.
RE
L
AT
E
D
WO
RK
S
L
i
u
[
6
]
d
ef
i
n
es
th
e
s
e
n
ti
m
en
t
an
al
y
s
i
s
a
s
t
h
e
co
m
p
u
tatio
n
al
s
tu
d
y
o
f
o
p
in
io
n
s
,
s
e
n
ti
m
en
ts
,
a
n
d
e
m
o
tio
n
s
t
h
at
ar
e
co
m
m
u
n
icat
ed
th
r
o
u
g
h
t
h
e
te
x
t
m
ed
i
u
m
.
W
h
ile
B
alah
u
r
an
d
T
u
r
ch
i
[
7
]
d
ef
in
e
s
it a
s
t
h
e
tas
k
o
f
d
etec
tin
g
,
e
x
tr
ac
ti
n
g
,
a
n
d
c
lass
i
f
y
in
g
o
p
in
io
n
s
a
n
d
s
e
n
ti
m
en
ts
co
n
ce
r
n
i
n
g
d
if
f
er
en
t
to
p
ics,
as
ex
p
r
es
s
ed
i
n
tex
t
u
al
in
p
u
t.
T
h
e
d
esire
s
an
d
p
er
s
o
n
al
attr
ac
tiv
en
es
s
o
f
cu
s
to
m
er
s
s
te
m
f
r
o
m
a
n
e
m
o
tio
n
th
at
ar
is
es
eit
h
er
p
o
s
itiv
el
y
o
r
n
e
g
ati
v
el
y
in
wh
ich
it
p
r
o
v
id
es
a
n
ess
e
n
tial
f
ac
to
r
in
d
eter
m
i
n
i
n
g
a
d
ec
is
io
n
as
in
[
8
]
if
th
e
co
n
ten
t
o
f
th
e
u
s
er
co
m
m
e
n
t
g
ets
d
etail,
w
h
ic
h
m
ea
n
s
m
o
r
e
ab
s
tr
ac
t
les
s
,
w
o
u
ld
b
e
p
r
o
d
u
ce
d
m
o
r
e
e
m
o
tio
n
s
o
n
it,
b
ased
o
n
th
e
e
v
id
en
ce
o
cc
u
r
r
ed
.
A
s
s
tated
in
[
9
]
,
f
o
r
s
o
m
e
ca
s
e
s
,
th
er
e
i
s
a
ti
m
e
wh
en
t
h
e
ca
n
d
id
ates
-
p
eo
p
le
co
m
m
u
n
icate
c
h
an
n
el
u
tili
ze
d
Fa
ce
b
o
o
k
as
th
eir
o
t
h
er
co
m
m
u
n
icatio
n
m
ed
ia
i
n
M
ex
ico
.
E
v
e
n
th
o
u
g
h
s
o
cial
m
ed
ia
i
s
m
aj
o
r
ly
u
s
ed
a
s
p
ar
t o
f
t
h
e
p
o
liti
ca
l c
a
m
p
a
ig
n
,
in
th
is
er
a,
t
h
e
i
m
p
le
m
e
n
tati
o
n
o
f
t
h
e
s
e
n
ti
m
e
n
t
an
al
y
s
is
h
as
n
o
ch
a
n
ce
to
p
r
ed
ict
th
e
r
es
u
lt o
f
a
n
elec
tio
n
.
A
lt
h
o
u
g
h
t
h
e
an
al
y
tical
u
s
i
n
g
t
h
e
s
en
ti
m
en
ta
l
o
f
a
u
s
er
h
as
a
s
ig
n
i
f
ica
n
t
i
m
p
ac
t
o
n
th
e
la
test
d
ev
elo
p
m
en
t
s
,
th
i
s
w
o
u
ld
n
o
t
h
ap
p
en
if
it
d
o
es
n
o
t
h
a
v
e
a
m
et
h
o
d
th
at
is
ef
f
icie
n
t
i
n
th
e
p
r
o
ce
s
s
.
T
h
e
m
o
d
el
is
as
m
e
n
tio
n
ed
i
n
[
1
0
]
;
th
e
au
th
o
r
s
u
s
ed
an
ac
tio
n
-
o
b
j
ec
t
ap
p
r
o
ac
h
f
o
r
p
o
s
t
-
clas
s
if
icat
io
n
to
u
n
d
er
s
ta
n
d
s
o
cial
m
ed
ia
m
ar
k
et
in
g
,
i
m
p
l
ied
w
it
h
i
n
s
u
c
h
as
t
h
e
s
e
n
ti
m
en
tall
y
o
f
a
u
s
er
o
n
a
Face
b
o
o
k
b
r
an
d
p
ag
e
b
y
f
o
llo
w
in
g
s
o
m
e
o
f
th
e
co
d
in
g
d
ev
elo
p
m
e
n
t
s
tr
ate
g
ies
w
h
ic
h
co
n
s
i
s
t
o
f
t
w
o
s
tep
s
,
tag
g
in
g
,
an
d
in
te
g
r
atin
g
.
T
h
e
tag
g
i
n
g
o
b
j
ec
tiv
e
is
to
id
en
ti
f
y
an
d
t
h
e
n
s
p
lit
u
p
d
i
f
f
er
en
t
k
e
y
w
o
r
d
s
o
n
a
Face
b
o
o
k
p
o
s
t
o
r
co
m
m
e
n
ts
.
W
h
ile
in
te
g
r
atio
n
i
s
t
h
e
p
ar
t
w
h
er
e
th
e
y
clas
s
i
f
y
t
h
e
ta
g
g
i
n
g
r
esu
l
ts
t
h
at
t
h
e
au
t
h
o
r
s
co
n
clu
d
ed
w
er
e
t
h
at
to
r
u
n
a
s
u
cc
e
s
s
f
u
l
Face
b
o
o
k
pa
g
e,
th
e
m
ar
k
eti
n
g
tea
m
m
u
s
t
b
e
m
o
r
e
co
n
ce
r
n
ed
ab
o
u
t
w
h
at
th
i
n
g
s
co
m
m
o
n
l
y
s
h
ar
ed
.
A
lt
h
o
u
g
h
t
h
e
e
x
i
s
ti
n
g
d
ata
p
r
o
ce
s
s
in
g
ca
n
w
o
r
k
s
w
it
h
o
t
h
er
to
o
ls
a
s
i
n
[
1
1
]
,
th
e
a
u
th
o
r
s
ar
e
tr
y
i
n
g
to
ac
h
iev
e
h
o
w
to
u
s
e
o
p
en
s
o
u
r
ce
tech
n
o
lo
g
y
w
it
h
Had
o
o
p
b
ased
u
tili
za
tio
n
to
ca
p
tu
r
e
in
p
u
ts
ab
o
u
t
a
b
r
an
d
's
in
f
o
r
m
atio
n
a
n
d
f
ee
d
b
ac
k
th
r
o
u
g
h
Face
b
o
o
k
p
o
s
ts
a
n
d
co
m
m
e
n
ts
.
T
h
e
y
o
u
tli
n
ed
s
ix
s
tep
s
to
ac
q
u
ir
e
th
e
d
ata,
an
d
it
w
a
s
alr
ea
d
y
test
ed
w
it
h
s
ix
d
if
f
er
en
t
b
r
an
d
s
.
T
h
e
a
cc
u
r
ac
y
o
f
s
en
t
i
m
e
n
t
p
r
ed
icti
o
n
s
o
f
t
h
eir
tes
tin
g
r
an
g
e
s
f
r
o
m
5
3
.
3
3
%
u
p
to
7
6
.
7
6
%.
A
s
th
e
an
a
l
y
t
ical
u
s
in
g
th
e
s
en
ti
m
en
ta
l
o
f
a
u
s
er
,
b
ased
o
n
a
p
r
o
ce
s
s
b
y
ex
p
r
ess
i
n
g
t
h
e
u
s
er
o
p
in
io
n
s
in
a
f
ile,
f
o
llo
w
i
n
g
th
a
t,
it
wo
u
ld
co
n
ti
n
u
e
to
a
n
o
t
h
er
p
r
o
ce
s
s
,
w
h
ic
h
i
s
t
h
e
id
en
ti
f
icatio
n
an
d
ca
te
g
o
r
izati
o
n
,
th
e
s
e
ai
m
s
to
p
r
ed
ict
o
f
t
h
e
w
r
i
ter
's
att
itu
d
e,
w
h
et
h
er
it
is
a
l
iv
el
y
,
n
eu
tr
al,
o
r
m
a
y
b
e
n
e
g
ati
v
e
s
e
n
ti
m
e
n
t.
B
y
d
o
in
g
t
h
e
a
n
al
y
tical
p
r
o
ce
s
s
,
it
w
o
u
ld
b
e
ea
s
y
to
r
ec
o
g
n
iz
e
w
h
et
h
er
t
h
e
p
o
s
t
co
n
tain
s
a
n
y
s
e
n
ti
m
e
n
tal
p
o
la
r
it
y
v
alu
e,
also
to
k
n
o
w
o
f
wh
at
m
o
s
t
d
i
s
cu
s
s
ed
to
p
ic,
it
is
lik
el
y
to
ap
p
l
y
t
h
e
K
-
m
ea
n
s
cl
u
s
ter
i
n
g
m
et
h
o
d
w
ith
i
n
it.
A
l
s
o
,
th
e
an
al
y
tica
l
p
r
o
ce
s
s
b
y
u
s
i
n
g
a
u
s
er
s
e
n
ti
m
e
n
t
is
o
f
ten
u
s
ed
to
ev
alu
a
te
th
e
co
n
te
n
t
w
it
h
i
n
th
e
s
o
cial
m
ed
ia
p
latf
o
r
m
a
n
d
to
f
o
r
ec
ast
an
y
e
m
o
tio
n
t
h
at
o
cc
u
r
s
w
it
h
i
n
th
e
co
n
s
u
m
er
f
o
r
in
cid
en
t
s
th
at
ar
e
o
b
s
er
v
ed
o
n
a
f
u
ll
s
ca
le
i
n
r
ea
l
-
ti
m
e
[1
2
]
.
A
lth
o
u
g
h
s
e
n
ti
m
en
t
an
al
y
s
i
s
is
al
s
o
u
s
ed
to
p
r
ed
ict
p
er
s
o
n
alit
y
b
as
ed
o
n
u
s
er
s
b
eh
a
v
io
u
r
[
1
3
]
.
Sen
ti
m
e
n
t
a
n
al
y
s
is
d
o
es
h
av
e
a
s
ig
n
i
f
ican
t
i
m
p
ac
t
to
d
a
y
.
T
h
ey
ca
n
co
m
p
r
eh
e
n
d
o
th
er
p
er
s
o
n
all
y
f
r
o
m
t
h
eir
b
eh
av
io
r
[
1
4
]
.
Fro
m
p
r
ev
io
u
s
r
esear
ch
,
t
h
e
y
i
m
p
lied
an
ap
p
r
o
ac
h
w
it
h
i
n
th
e
a
n
al
y
s
i
s
w
it
h
a
lex
ico
n
alg
o
r
ith
m
.
T
h
e
f
u
n
d
a
m
e
n
tal
th
eo
r
y
w
it
h
i
n
t
h
is
ap
p
r
o
ac
h
r
ests
o
n
t
h
e
id
ea
,
w
h
ic
h
is
t
o
co
m
p
r
eh
e
n
d
th
e
co
n
ce
p
t
o
f
lex
ica
l
it
s
el
f
a
n
d
g
en
er
ate
s
o
m
e
le
x
ical
s
e
n
te
n
ce
s
as
p
iec
es
a
s
a
n
ess
e
n
tial
p
ar
t
o
f
lear
n
i
n
g
a
lan
g
u
a
g
e.
T
h
e
s
en
ti
m
e
n
t
an
a
l
y
s
is
an
d
L
e
x
ico
n
b
ased
d
ictio
n
ar
y
m
et
h
o
d
h
av
e
s
h
ar
ed
an
ef
f
ec
tiv
e
r
ate
o
f
ef
f
o
r
t
in
s
u
c
h
k
in
d
s
o
f
w
o
r
k
s
,
w
h
ic
h
p
r
o
d
u
ce
s
a
lo
t
o
f
f
u
n
ctio
n
a
l
b
en
ef
i
ts
[
1
5
]
.
Mo
r
eo
v
er
,
o
n
e
m
et
h
o
d
to
f
i
n
d
t
h
e
pe
r
s
o
n
alit
y
tr
ait
s
o
f
t
h
e
u
s
er
i
s
to
r
ea
d
a
tex
t
an
d
to
u
n
d
er
s
tan
d
th
e
m
.
A
l
s
o
,
th
e
s
a
m
e
f
o
r
[
1
6
]
,
w
h
ich
u
s
i
n
g
Face
b
o
o
k
b
ec
au
s
e
it
ex
p
lai
n
s
w
h
ic
h
is
ex
ce
ed
i
n
g
l
y
k
n
o
w
n
w
ell
all
o
v
er
th
e
w
o
r
ld
,
th
es
e
p
latf
o
r
m
s
h
o
ld
a
v
ital
r
o
le
in
p
er
s
o
n
alit
y
an
al
y
s
is
b
ased
o
n
u
s
er
s
'
ac
ti
v
it
ies.
B
ec
au
s
e
th
e
co
n
ce
p
t
o
f
p
er
s
o
n
alit
y
is
a
litt
le
b
it
co
m
p
lica
ted
,
it
w
o
u
ld
p
r
ese
n
tl
y
b
e
a
n
i
s
s
u
e
k
n
o
w
n
to
b
e
c
h
a
llen
g
in
g
to
b
e
s
o
l
v
ed
.
A
s
t
h
e
i
s
s
u
e
w
h
ic
h
ca
n
n
o
t
b
e
ea
s
y
to
b
e
s
o
lv
ed
,
d
o
cu
m
en
tatio
n
co
m
p
r
e
h
en
s
io
n
ca
n
b
e
p
u
zz
led
o
u
t
b
y
u
s
i
n
g
th
e
s
u
p
er
v
is
ed
n
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
4
,
A
u
g
u
s
t
2021
:
3
4
2
4
-
3433
3426
u
n
s
u
p
er
v
is
ed
m
et
h
o
d
o
f
th
e
m
ac
h
in
e
lear
n
in
g
alg
o
r
it
h
m
[
1
7
]
.
Natu
r
al
lan
g
u
a
g
e
p
r
o
ce
s
s
in
g
is
o
n
e
o
f
t
h
e
m
w
h
ic
h
i
m
p
le
m
e
n
ted
in
[
1
8
]
.
I
t
is
co
m
m
o
n
l
y
u
s
ed
f
o
r
a
s
i
m
p
le
w
a
y
to
i
m
p
le
m
e
n
t
s
en
ti
m
en
t
an
al
y
s
is
w
h
e
n
th
er
e
is
a
s
m
all
c
h
a
n
ce
th
at
le
ar
n
in
g
s
y
n
tax
w
o
u
ld
b
e
n
ec
es
s
ar
y
.
B
ased
o
n
th
e
p
r
ev
io
u
s
p
ap
er
s
th
at
d
is
cu
s
s
ed
th
e
v
ar
io
u
s
ap
p
licatio
n
s
o
f
s
e
n
ti
m
en
t
a
n
al
y
s
i
s
o
n
m
u
l
tip
le
d
if
f
er
e
n
t
s
u
b
j
ec
ts
,
all
o
f
th
e
m
h
a
v
e
s
o
m
e
w
h
at
th
e
s
a
m
e
s
tep
b
y
s
tep
th
at
r
esea
r
ch
er
s
g
e
n
er
all
y
u
s
ed
w
h
e
n
r
esear
ch
i
n
g
t
h
is
s
u
b
j
ec
t.
T
h
e
i
m
p
le
m
en
ta
tio
n
o
f
s
en
ti
m
e
n
t
a
n
al
y
s
i
s
v
ar
ies
f
r
o
m
it
s
u
s
a
g
e
to
p
r
ed
ict
p
er
s
o
n
alit
y
m
o
d
elli
n
g
g
at
h
er
ed
f
r
o
m
Face
b
o
o
k
[
1
9
]
,
to
ex
p
lo
r
in
g
its
u
s
a
g
e
o
n
A
r
ab
ic
s
lan
g
[
2
0
]
,
to
its
ap
p
licatio
n
in
e
-
lear
n
i
n
g
[
2
1
]
,
an
d
m
o
r
e.
T
h
e
o
th
er
ap
p
r
o
ac
h
is
to
u
s
e
Se
n
ti
C
ir
cle
an
d
L
ex
ic
o
n
-
B
ased
alg
o
r
it
h
m
s
as
i
n
[
2
2
]
im
p
le
m
e
n
ti
n
g
s
en
ti
m
e
n
t
a
n
al
y
s
i
s
in
s
e
m
a
n
ti
c
co
n
tex
t
u
al
in
t
h
e
T
w
i
tter
p
lat
f
o
r
m
i
n
2
0
1
6
,
w
h
ic
h
i
s
s
u
p
p
o
r
ted
b
y
t
h
e
Se
m
icir
cle
w
o
r
k
f
lo
w
m
o
d
el.
T
o
m
a
k
e
th
e
alg
o
r
it
h
m
m
u
c
h
b
etter
p
r
o
ce
s
s
i
n
g
.
B
esid
es,
th
er
e
is
a
w
a
y
to
i
m
p
r
o
v
is
e
ag
a
in
s
t
s
en
ti
m
en
t
a
n
a
l
y
s
i
s
a
s
i
n
[
23
]
w
it
h
th
e
s
e
n
t
en
ce
t
y
p
e
class
i
f
icatio
n
w
it
h
t
h
e
i
m
p
le
m
en
tatio
n
o
f
t
h
e
B
iLST
M
-
C
R
E
a
n
d
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
et
w
o
r
k
(
C
NN)
alg
o
r
ith
m
in
2
0
1
7
.
I
t
h
as
a
v
ar
iet
y
o
f
al
g
o
r
ith
m
s
to
h
elp
b
r
ea
k
d
o
w
n
p
r
o
b
le
m
s
s
u
c
h
a
s
co
-
r
a
n
k
in
g
,
b
ac
k
-
p
r
o
p
ag
atio
n
,
an
d
o
t
h
er
alg
o
r
i
th
m
s
th
at
s
h
ar
e
t
h
e
w
a
y
i
t
wo
r
k
s
.
T
h
er
e
ar
e
s
till
m
an
y
o
t
h
er
w
a
y
s
o
f
u
s
i
n
g
s
en
ti
m
e
n
t
an
a
l
y
s
is
as
[
24
]
th
e
r
e
is
a
u
n
iq
u
e
m
et
h
o
d
o
f
u
tili
z
in
g
t
h
e
h
y
b
r
id
cu
ck
o
o
s
ea
r
ch
m
et
h
o
d
in
th
e
y
ea
r
2
0
1
7
.
No
t
o
n
l
y
b
y
i
m
p
le
m
e
n
ti
n
g
al
g
o
r
ith
m
s
s
u
c
h
as
K
-
m
ea
n
,
c
u
ck
o
o
s
ea
r
ch
,
an
d
o
th
er
alg
o
r
ith
m
s
t
h
at
r
ese
m
b
lan
ce
to
it,
th
e
i
m
p
le
m
en
tatio
n
o
f
ar
ch
i
tectu
r
e
m
o
d
els
s
u
c
h
as
th
e
h
y
b
r
id
cu
ck
o
o
s
ea
r
ch
m
et
h
o
d
f
lo
w
ch
ar
t
m
o
d
e
l.
T
h
er
e
is
als
o
an
o
th
er
w
a
y
i
n
t
h
e
ap
p
licati
o
n
o
f
th
e
s
e
n
ti
m
e
n
t
a
n
al
y
s
i
s
t
h
at
i
s
w
i
th
[
25
]
th
e
i
m
p
le
m
en
ta
tio
n
o
f
g
e
n
er
al
k
n
o
w
led
g
e
(
co
m
m
o
n
s
e
n
s
e
k
n
o
w
led
g
e)
in
to
a
n
atten
tiv
e
lo
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
(
L
ST
M
)
in
2
0
1
8
,
w
h
ich
h
a
s
a
n
al
g
o
r
i
th
m
o
f
d
ee
p
n
e
u
r
al
n
et
w
o
r
k
an
d
h
as
its
ar
c
h
itect
u
r
al
m
o
d
el
f
o
r
s
e
m
a
n
tic
n
et
w
o
rk
.
A
d
m
i
tted
l
y
,
t
h
er
e
ar
e
s
u
p
p
o
r
tin
g
m
eth
o
d
s
to
i
m
p
le
m
en
t
t
h
e
ap
p
lied
alg
o
r
ith
m
t
h
at
i
s
th
e
i
m
p
le
m
en
ta
tio
n
o
f
t
h
e
m
eth
o
d
: T
ar
g
et
-
lev
el
atte
n
tio
n
,
Sen
t
ic
L
ST
M,
an
d
o
th
er
s
i
m
ilar
m
e
t
h
o
d
s
.
B
ased
o
n
th
e
p
r
ec
ed
in
g
r
esear
ch
ed
,
m
i
x
ed
m
et
h
o
d
s
an
d
ap
p
lian
ce
s
ap
p
r
o
ac
h
ed
h
a
v
e
b
ee
n
d
o
n
e
an
d
co
n
s
u
m
m
ated
;
al
l
o
f
th
e
m
h
av
e
ap
p
r
o
p
r
iaten
ess
a
n
d
ap
p
licab
ilit
y
to
b
e
ap
p
lied
to
v
ar
io
u
s
er
r
an
d
s
.
Fro
m
p
r
ev
io
u
s
r
esear
ch
,
s
e
n
ti
m
en
t
an
al
y
s
i
s
co
m
m
o
n
l
y
e
x
is
t
s
o
n
t
h
e
Feed
b
ac
k
ac
tiv
it
y
in
t
h
e
s
c
o
p
e
o
f
s
er
v
ice
ap
p
s
(
e.
g
.
,
Face
b
o
o
k
)
.
Mo
s
t
o
f
Fa
ce
b
o
o
k
'
s
u
s
er
s
h
a
v
e
co
m
m
u
n
icatio
n
al
i
n
ter
ac
ted
t
h
r
o
u
g
h
t
h
e
n
e
w
s
p
o
s
t
s
t
h
at
h
av
e
b
ee
n
p
o
s
ted
b
y
t
y
p
in
g
t
h
eir
th
o
u
g
h
t
s
o
f
th
e
co
m
m
e
n
t
s
ec
tio
n
in
s
tead
r
ath
er
th
an
d
o
in
g
it
w
it
h
p
er
s
o
n
al
ch
at
.
Fro
m
t
h
e
p
r
ev
io
u
s
s
t
u
d
ies,
o
n
e
o
f
t
h
e
s
o
cial
m
ed
ia
p
latf
o
r
m
s
u
s
ed
to
p
er
f
o
r
m
te
x
t
p
r
o
ce
s
s
in
g
w
a
s
Face
b
o
o
k
.
Fu
r
th
er
m
o
r
e,
it
ex
p
lain
s
th
a
t
an
y
a
u
to
m
at
icall
y
g
en
er
ated
co
n
te
n
t
ap
p
licatio
n
h
as
a
f
ea
t
u
r
e
th
at
is
ca
p
ab
le
o
f
b
ein
g
as g
u
id
a
n
ce
f
o
r
d
ed
u
cin
g
th
e
c
h
ar
ac
ter
b
eh
a
v
io
r
o
f
th
e
u
s
er
.
3.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
m
et
h
o
d
o
f
w
o
r
k
in
g
ca
n
b
e
co
m
p
o
s
ed
o
f
th
r
ee
p
r
i
m
er
o
b
j
ec
tiv
es,
w
h
ic
h
d
iv
id
e
i
n
to
v
ar
ian
ts
o
f
p
r
o
m
i
n
en
t
d
iv
er
g
e
s
e
g
m
e
n
tat
i
o
n
s
-
t
h
e
d
ata
s
et
co
llectio
n
s
e
g
m
en
t
,
th
e
d
ata
p
r
e
-
p
r
o
ce
s
s
in
g
s
eg
m
e
n
t
,
an
d
t
h
e
an
al
y
ze
d
d
ata
v
i
s
u
a
lizatio
n
s
e
g
m
e
n
t.
T
o
o
p
e
r
ate
th
e
alg
o
r
it
h
m
s
o
f
t
h
e
m
e
th
o
d
o
lo
g
y
,
as
u
tili
ze
d
t
h
e
P
y
th
o
n
in
te
g
r
ated
d
ev
elo
p
m
e
n
t
en
v
ir
o
n
m
e
n
t
(
P
y
t
h
o
n
I
DE
v
er
.
3
.
7
.
7
.
)
as
th
e
b
ase
o
f
t
h
e
p
r
o
g
r
am
m
in
g
lan
g
u
ag
e
to
co
n
d
u
ct
t
h
e
ex
p
er
i
m
en
t
s
w
it
h
th
e
P
y
t
h
o
n
p
ac
k
a
g
e
in
d
e
x
(
P
I
P
)
as
th
e
r
ep
o
s
ito
r
y
o
f
t
h
e
s
o
f
t
w
ar
e.
B
esid
es
t
h
at,
th
e
m
eth
o
d
o
f
w
o
r
k
in
g
h
elp
ed
b
y
w
it
h
th
e
a
s
s
i
s
ta
n
ce
o
f
w
eb
-
b
ased
ap
p
licatio
n
s
u
c
h
as o
p
en
-
d
o
cu
m
e
n
t
f
o
r
m
a
t
b
ased
o
n
J
u
p
y
ter
-
n
o
teb
o
o
k
f
o
r
W
in
d
o
w
s
p
latf
o
r
m
(
J
SON
)
,
tex
t
-
a
n
al
y
s
i
s
an
d
m
ac
h
in
e
lear
n
in
g
w
eb
-
b
ased
s
er
v
ice
(
Mo
n
k
e
y
L
ea
r
n
o
n
Mo
n
k
e
y
L
ea
r
n
.
co
m
)
,
Face
b
o
o
k
d
ata
co
m
m
en
t
's
e
x
tr
ac
to
r
s
v
ia
w
eb
-
b
ased
s
er
v
ice
s
,
an
d
Mic
r
o
s
o
f
t
E
x
ce
l
2
0
1
6
as
th
e
d
ata
co
n
tain
er
.
Fo
r
th
e
in
f
o
r
m
atio
n
,
it
ap
p
lied
th
e
m
et
h
o
d
o
f
w
o
r
k
i
n
g
b
ased
o
n
th
e
ex
is
ti
n
g
m
e
th
o
d
s
f
r
o
m
t
h
e
in
ter
n
et,
t
h
e
m
et
h
o
d
[2
6
]
a
p
p
lied
b
ased
o
n
a
GitHu
b
P
o
s
t
.
T
h
e
aim
ed
m
et
h
o
d
o
f
w
o
r
k
i
n
g
at
th
e
th
r
ee
s
elec
tiv
e
l
y
Face
b
o
o
k
'
s
p
o
s
t
s
co
m
m
en
ts
:
1
st
P
o
s
t
,
Face
b
o
o
k
Of
f
icial
P
ag
e
-
h
ttp
s
://
www
.
Face
b
o
o
k
.
co
m
/Faceb
o
o
k
/
v
id
eo
s
/1
9
0
4
0
3
4
5
2
2
8
0
2
3
8
/
2
nd
P
o
s
t
,
Ma
r
k
Z
u
c
k
er
b
er
g
Of
f
icial
P
ag
e
-
h
ttp
s
://
www
.
Face
b
o
o
k
.
co
m
/z
u
c
k
/p
o
s
ts
/1
0
1
1
1
7
0
7
3
7
3
6
3
1
1
9
1
/
3
rd
P
o
s
t
,
Ma
r
k
Z
u
ck
er
b
er
g
O
f
f
icial
P
ag
e
-
h
ttp
s
:/
/
www
.
Face
b
o
o
k
.
co
m
/z
u
c
k
/p
o
s
ts
/1
0
1
1
1
4
6
2
1
0
2
2
0
2
1
0
1
/
W
h
ich
al
l o
f
th
e
m
ac
ted
a
s
cla
r
it
y
o
f
d
ata
r
eso
u
r
ce
s
.
As it
an
al
y
ze
d
,
it
d
er
iv
e
d
a
m
u
ch
p
o
ten
tial a
r
r
a
y
o
f
th
e
r
a
w
d
ata
f
r
o
m
it
as
th
e
p
r
im
ar
y
s
o
u
r
ce
s
,
w
h
ich
ar
e
lo
ad
ed
b
y
ap
p
r
o
x
i
m
atel
y
6
0
0
co
m
m
e
n
t
s
co
m
b
i
n
ed
as
th
e
s
a
m
p
le
r
a
w
d
ata
to
b
e
a
n
al
y
ze
d
f
u
r
t
h
er
m
o
r
e.
3
.
1
.
Da
t
a
c
o
llect
io
n seg
m
ent
As
it
u
s
ed
an
o
n
l
in
e
al
g
o
r
ith
m
o
f
P
y
th
o
n
th
at
ca
n
g
e
n
er
ate
th
e
s
en
ti
m
e
n
t
g
r
ap
h
f
r
o
m
a
co
m
m
e
n
t
s
cr
ap
p
er
w
eb
s
i
te
(
lik
e
Data
E
x
tr
ac
to
r
.
io
)
,
w
h
ic
h
s
cr
ap
p
ed
th
e
u
s
er
co
m
m
en
t
s
th
r
o
u
g
h
m
u
ltip
le
Face
b
o
o
k
P
ag
es,
as
m
e
n
tio
n
ed
ab
o
v
e.
T
h
e
u
ti
lized
w
eb
s
cr
ap
i
n
g
liter
all
y
i
n
th
e
f
o
r
m
o
f
a
u
to
m
a
tic
to
o
ls
as
it
is
m
u
c
h
ea
s
ier
an
d
ac
ce
s
s
ib
le
r
ath
er
t
h
an
th
e
m
a
n
u
al
p
r
o
ce
s
s
,
w
h
i
ch
is
m
u
c
h
m
o
r
e
co
m
p
lex
i
tie
s
in
its
p
r
o
ce
d
u
r
al
o
cc
u
r
r
ed
.
I
n
th
e
a
u
to
m
atic
to
o
ls
u
s
ed
,
t
h
e
to
o
l
w
o
u
ld
lo
ad
th
e
i
n
p
u
tted
U
R
L
s
a
n
d
r
en
d
er
th
e
en
tire
ai
m
ed
p
ag
e.
T
h
e
to
o
l
w
o
u
ld
g
e
n
er
ate
th
e
d
es
ir
ed
r
esu
lt
b
y
i
n
s
er
tin
g
th
e
th
r
ee
UR
L
s
o
f
th
e
d
ataset
i
n
ea
r
lier
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
Th
e
imp
a
ct
o
f sen
timen
t a
n
a
lysi
s
fr
o
m
u
s
e
r
o
n
F
a
ce
b
o
o
k
to
…
(
Da
n
iel
D.
A
lb
esta
)
3427
m
en
tio
n
ed
in
a
n
ef
f
icie
n
t
a
n
d
q
u
ick
f
ea
s
ib
le
f
o
r
m
at
w
it
h
o
u
t
an
y
co
d
es
in
v
o
l
v
ed
w
i
th
i
n
it
.
A
s
t
h
e
co
m
m
e
n
t
s
ex
tr
ac
ted
,
m
o
r
eo
v
er
,
co
n
v
er
te
d
in
to
a
co
m
m
a
s
ep
ar
at
ed
v
alu
e
(
C
SV)
f
i
le
f
o
r
m
at
ted
.
Fig
u
r
e
1
i
n
th
is
ca
s
e,
b
y
th
e
w
eb
s
ite
'
s
f
ea
tu
r
e
s
,
t
h
e
t
h
r
ee
v
ar
ia
n
ts
o
f
p
o
s
ts
co
m
m
e
n
t
s
ar
e
i
m
p
le
m
en
ted
as
a
s
in
g
le
s
o
u
r
ce
o
f
th
e
d
ata.
Fo
r
th
e
ele
m
e
n
t
o
f
a
u
th
e
n
tici
t
y
it
s
el
f
,
t
h
e
u
tili
ze
d
d
atase
ts
b
ased
o
n
th
e
t
h
r
ee
UR
L
s
s
o
u
r
ce
ab
o
v
e,
th
er
e
i
s
less
,
o
r
n
o
d
ata
ch
an
g
ed
d
u
r
in
g
th
e
d
ata
s
cr
ap
e
p
r
o
ce
s
s
,
as it
w
o
u
ld
k
ee
p
th
e
d
ata
in
te
g
r
it
y
o
v
er
ti
m
e.
Fig
u
r
e
1
.
Sa
m
p
le
o
f
co
m
b
i
n
ed
o
f
th
r
ee
Face
b
o
o
k
p
o
s
t's
co
m
m
en
ts
d
ata
E
ac
h
o
f
t
h
e
s
a
m
p
le
d
ata
o
u
tp
u
t
g
e
n
er
ates
b
y
t
h
e
p
r
o
g
r
a
m
,
w
h
ic
h
f
o
r
f
u
r
t
h
er
p
r
o
ce
s
s
i
n
g
t
o
lo
ad
th
e
d
ata
f
o
r
m
t
h
e
g
i
v
e
n
f
ile,
o
r
j
u
s
t
r
ea
d
f
r
o
m
th
e
ca
c
h
e
alr
ea
d
y
p
r
e
-
p
r
o
ce
s
s
ed
f
ile.
A
l
s
o
,
th
er
e
is
a
d
is
ti
n
ctio
n
b
et
w
ee
n
tes
tin
g
p
r
o
ce
s
s
i
n
g
a
n
d
tr
ain
in
g
d
ata.
T
h
e
y
ar
e
b
ein
g
eli
m
i
n
ated
as
th
e
(
C
SV)
f
ile
f
o
r
m
at
ted
w
as
f
u
ll
o
f
e
m
p
t
y
e
n
tr
ies
w
it
h
t
h
e
s
u
p
p
o
r
t
o
f
th
e
p
r
ac
tice
o
f
f
u
n
ctio
n
ed
p
r
o
p
er
ties
s
u
c
h
a
s
d
ata
m
o
d
el,
w
o
r
d
lis
t,
o
th
er
s
i
m
ilar
p
r
o
p
er
ties
f
u
n
ctio
n
ed
to
i
m
p
o
r
t
th
e
o
u
tp
u
tted
r
a
w
d
ata
o
f
v
ar
ia
n
t
o
f
d
ata
s
e
ts
t
h
at
r
ep
r
esen
ted
in
t
h
e
p
er
ce
n
tag
e
o
f
n
eg
at
iv
e
co
m
m
e
n
ts
,
n
eu
tr
al
co
m
m
e
n
t
s
,
o
r
p
o
s
itiv
e
co
m
m
e
n
ts
,
r
ep
r
esen
ted
i
n
Fig
u
r
e
2
.
Fro
m
t
h
e
f
ir
s
t
p
o
s
t,
it
p
u
r
p
o
s
el
y
u
s
e
s
th
e
p
o
s
t
s
f
illed
w
it
h
th
e
m
o
s
t
n
eg
a
tiv
e
co
m
m
en
ts
,
p
o
s
itiv
e
co
m
m
e
n
t
s
,
an
d
m
i
x
ed
co
m
m
en
ts
t
h
at
h
a
v
e
b
ee
n
s
h
o
w
i
n
g
s
eq
u
en
tial
v
i
s
u
alize
.
T
h
e
g
r
ap
h
ical
in
Fig
u
r
e
3
is
ex
p
o
r
ted
b
y
t
h
e
i
m
p
le
m
en
tati
o
n
o
f
P
lo
tl
y
's
P
y
t
h
o
n
g
r
ap
h
i
n
g
lib
r
ar
y
,
w
h
ic
h
is
ca
lled
b
y
u
s
i
n
g
t
h
e
r
en
d
er
er
s
f
r
a
m
e
w
o
r
k
)
to
g
e
n
er
ate
th
e
g
r
ap
h
ic
ch
ar
t
o
f
t
h
e
r
a
w
d
ata.
I
n
o
r
d
er
to
co
llect
t
h
e
v
is
u
ali
za
tio
n
g
r
ap
h
ical,
it
i
m
p
lied
b
y
u
s
i
n
g
P
y
t
h
o
n
co
d
es i
m
p
le
m
e
n
ted
in
J
u
p
y
ter
-
n
o
teb
o
o
k
I
DE
.
Fig
u
r
e
2
.
A
co
m
b
i
n
ed
s
a
m
p
le
o
f
th
r
ee
Face
b
o
o
k
p
o
s
t's
co
m
m
en
ts
d
ata
tu
p
le
s
v
i
s
u
a
lizatio
n
s
3
.
2
.
D
a
t
a
pre
-
pro
ce
s
s
ing
s
eg
m
e
nt
T
h
e
s
am
p
le
Face
b
o
o
k
P
o
s
t'
s
C
o
m
m
e
n
t
r
a
w
d
ata
f
ir
s
tl
y
p
r
e
-
p
r
o
ce
s
s
ed
b
y
u
tili
zi
n
g
t
h
e
P
I
P
lib
r
a
r
ies
in
cl
u
d
e
P
an
d
as,
Nu
m
P
y
,
P
lo
t
l
y
,
an
d
Sci
k
it
-
lear
n
l
ib
r
ar
y
al
o
n
g
w
it
h
t
h
e
i
m
p
le
m
e
n
tatio
n
o
f
o
th
er
ad
d
itio
n
al
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
4
,
A
u
g
u
s
t
2021
:
3
4
2
4
-
3433
3428
lib
r
ar
ies.
P
an
d
as
co
r
r
ec
tl
y
i
m
p
le
m
en
ted
f
o
r
o
p
en
-
s
o
u
r
ce
d
a
ta
an
al
y
s
is
a
n
d
m
a
n
ip
u
lat
io
n
to
o
ls
s
u
ch
as
f
o
r
o
p
en
ed
a
.
csv
ex
ten
s
io
n
f
ile
as
in
th
e
ca
s
e
an
d
f
o
r
d
ata
f
r
am
i
n
g
a
n
d
lab
elin
g
o
f
t
h
e
s
a
m
p
le
r
aw
d
ata.
Nu
m
P
y
is
s
u
itab
le
as
cu
l
tiv
a
tin
g
f
o
r
m
ath
e
m
atica
l
f
u
n
ctio
n
s
,
w
h
ic
h
l
ater
u
s
ed
.
P
lo
tl
y
b
est
d
ea
l i
n
m
ai
n
l
y
f
o
r
g
r
ap
h
ica
l
v
is
u
aliza
t
io
n
b
ased
o
n
th
e
e
x
i
s
tin
g
d
ata.
Sci
k
it
-
lear
n
m
ar
v
e
l
o
u
s
w
it
h
lear
n
i
n
g
o
r
v
alid
atio
n
p
r
o
ce
s
s
o
cc
u
r
r
ed
in
th
e
a
n
al
y
z
in
g
p
r
o
ce
s
s
.
T
h
ese
lib
r
ar
ies
ar
e
m
an
d
ato
r
y
f
o
r
t
h
e
ex
p
er
i
m
e
n
t
as
it
lo
ad
s
m
a
n
y
cr
it
ical
f
u
n
c
tio
n
s
to
g
en
er
ate
th
e
d
ata
a
s
ai
m
ed
.
Fo
llo
w
i
n
g
th
e
r
a
w
d
ata
ar
e
d
o
n
e
i
m
p
o
r
ted
;
if
t
h
e
r
a
w
d
ata
wan
t
to
b
e
p
r
esen
t
to
th
e
p
u
b
lic,
it r
eq
u
ir
e
s
a
co
m
p
l
ete
p
r
o
ce
d
u
r
e
to
d
is
p
lay
t
h
e
r
a
w
d
ata
en
t
ir
el
y
clea
r
.
3
.
2
.
1
.
D
a
t
a
s
et
cle
a
ns
ing
T
h
e
o
b
j
ec
tiv
e
o
f
d
ataset
clea
n
s
i
n
g
s
eg
m
e
n
t
is
to
e
x
tr
ac
t
a
v
alu
e
o
f
t
h
e
r
a
w
d
ata
s
tr
in
g
s
co
n
tain
e
d
f
r
o
m
t
h
e
Face
b
o
o
k
p
o
s
ts
w
h
ic
h
u
s
e
iter
atio
n
m
et
h
o
d
to
id
en
tify
,
s
ea
r
ch
,
a
n
d
s
ep
ar
ated
ea
ch
w
o
r
d
o
cc
u
r
r
ed
in
th
e
s
elec
ti
v
e
s
en
ten
ce
o
n
th
e
d
ata
o
f
t
u
p
le
-
n
-
also
b
ei
n
g
c
lean
s
ed
f
r
o
m
a
n
y
v
ar
ia
n
ts
o
f
u
n
iq
u
e
ch
ar
ac
ter
s
,
escap
ed
ch
ar
ac
ter
s
,
an
d
th
e
r
est
its
el
f
.
A
s
w
it
h
t
h
e
h
elp
o
f
u
ti
lit
y
o
f
R
e
g
ex
lib
r
ar
y
f
u
n
ctio
n
s
,
e.
g
.
,
escap
e
ch
ec
k
ed
an
d
co
m
p
iled
f
u
n
ct
io
n
s
,
f
o
llo
w
i
n
g
th
e
iter
atio
n
,
e.
g
.
,
u
s
i
n
g
la
m
b
d
a
f
u
n
ctio
n
(
)
w
h
ic
h
tak
e
a
n
ar
g
u
m
e
n
t
o
f
r
:
r
eg
ex
to
e
x
ec
u
t
e
d
its
f
u
n
ctio
n
w
it
h
th
e
u
s
er
-
d
ef
i
n
ed
b
ased
ex
p
r
ess
io
n
(
"
,
"
,
":"
,
"
\
"
,
"
=
",
an
d
th
e
r
est
its
el
f
)
to
m
ak
e
a
li
s
t
o
f
a
w
o
r
d
as
d
esire
d
,
f
o
llo
w
in
g
t
h
e
d
ata
s
a
v
ed
an
d
g
en
er
ated
i
n
an
in
ter
p
r
ets
o
f
a
s
ep
ar
ated
ar
r
ay
o
f
w
o
r
d
s
.
I
f
i
t
a
s
u
cc
es
s
,
t
h
en
i
t
w
o
u
ld
t
h
r
o
w
an
o
u
tp
u
t c
o
n
s
is
t o
f
a
clea
n
ed
,
s
ep
ar
ated
ar
r
ay
o
f
w
o
r
d
s
d
ata
f
o
r
ap
p
r
o
x
i
m
atel
y
6
0
0
a
r
r
ay
s
o
f
w
o
r
d
s
.
As
th
e
al
g
o
r
ith
m
s
ar
e
ex
ec
u
ted
,
it
g
en
e
r
ates
th
e
f
o
llo
w
i
n
g
alg
o
r
ith
m
's p
r
o
d
u
ct,
as t
h
e
y
r
e
p
r
esen
t
in
Fig
u
r
e
4
.
Fig
u
r
e
3
.
Sa
m
p
le
o
f
t
h
e
g
r
ap
h
i
c
ch
ar
t
o
f
co
m
b
in
ed
o
f
t
h
r
ee
F
ac
eb
o
o
k
p
o
s
t'
s
co
m
m
e
n
ts
d
ata
tu
p
les
v
is
u
aliza
t
io
n
s
Fig
u
r
e
4
.
Sa
m
p
le
o
f
t
h
e
Face
b
o
o
k
p
o
s
t'
s
co
m
m
e
n
t
s
d
ata
f
o
ll
o
w
i
n
g
t
h
e
clea
n
s
i
n
g
p
r
o
ce
s
s
3
.
2
.
2
.
D
a
t
a
t
o
k
enizing
a
nd
s
t
e
mm
ing
T
h
e
o
b
j
ec
tiv
e
o
f
d
ata
to
k
en
izi
n
g
o
r
k
n
o
w
n
a
s
lex
i
n
g
(
lex
ica
l
an
al
y
s
is
)
an
d
s
te
m
m
in
g
s
e
g
m
en
t
,
is
to
co
n
v
er
t
a
s
eq
u
e
n
ce
o
f
ch
ar
ac
t
er
s
th
at
o
cc
u
r
r
ed
in
to
a
f
o
r
m
o
f
a
s
eq
u
en
ce
o
f
to
k
en
s
(
s
tr
i
n
g
s
w
it
h
an
as
s
ig
n
ed
an
d
th
u
s
id
e
n
ti
f
ied
m
ea
n
i
n
g
a
s
w
ik
ip
ed
ia.
o
r
g
s
o
u
r
ce
s
aid
)
.
T
h
ese
p
r
o
ce
s
s
es
m
a
k
e
a
p
ar
titi
o
n
ed
o
f
tex
t
d
ata
a
s
a
s
eq
u
en
ce
o
f
w
o
r
d
s
.
W
h
ic
h
co
n
s
is
ts
o
f
an
id
en
ti
f
ier
(
x
,
y
,
z)
,
a
k
ey
w
o
r
d
(
ca
s
e,
b
r
ea
k
,
r
etu
r
n
)
,
a
s
ep
ar
ato
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
Th
e
imp
a
ct
o
f sen
timen
t a
n
a
lysi
s
fr
o
m
u
s
e
r
o
n
F
a
ce
b
o
o
k
to
…
(
Da
n
iel
D.
A
lb
esta
)
3429
(
[
,
{,
;)
,
an
o
p
er
ato
r
(
+,
-
,
=)
,
a
liter
al
(
1
.
0
0
e6
4
,
"
d
ata
"
,
tr
u
e)
o
r
a
co
m
m
e
n
t
(
li
n
e,
b
lo
ck
)
;
ea
ch
w
o
r
d
in
t
h
e
r
ed
u
ce
d
tex
t
d
ata
class
if
y
i
n
t
o
o
n
e
o
r
m
o
r
e
s
te
m
s
.
T
h
e
w
o
r
d
th
at
id
en
tif
ie
s
as
a
"
w
o
r
d
"
is
ch
ec
k
ed
in
th
i
s
p
r
o
ce
s
s
.
T
h
e
tex
t
p
r
o
ce
s
s
in
g
w
o
u
ld
o
cc
u
r
in
th
e
s
e
s
tep
s
an
d
in
v
o
lv
e
o
n
e
o
f
t
h
e
m
o
s
t
co
m
m
o
n
lib
r
ar
ies
th
a
t
ex
is
t
in
P
y
t
h
o
n
,
w
h
ic
h
i
s
th
e
n
atu
r
al
la
n
g
u
a
g
e
to
o
l k
it
(
N
L
T
K)
.
I
t h
as a
f
u
n
ctio
n
n
a
m
ed
N
L
T
K.
w
o
r
d
_
to
k
en
ize
f
u
n
ctio
n
.
T
h
e
f
u
n
c
tio
n
w
o
r
k
as
th
e
w
o
r
d
_
to
k
e
n
ize
m
o
d
u
le
is
i
m
p
o
r
ted
f
r
o
m
t
h
e
NL
T
K
lib
r
ar
y
;
f
o
llo
w
i
n
g
w
it
h
th
e
ar
g
u
m
e
n
t o
f
"
tex
t"
in
i
tialized
w
it
h
ea
ch
r
o
w
o
f
d
ata
tex
t i
n
s
id
e
it,
w
it
h
i
n
t
h
e
r
o
w
(
)
f
u
n
ctio
n
it
s
el
f
; t
h
e
r
o
w
(
)
f
u
n
ctio
n
is
p
ass
ed
i
n
wo
r
d
_
to
k
en
ize
m
o
d
u
le
a
n
d
r
ep
r
esen
t
s
it
o
u
tp
u
ts
.
E
ac
h
r
o
w
o
f
d
ata
r
ed
u
ce
s
in
to
a
m
i
n
i
m
alize
d
th
e
r
ed
u
n
d
an
c
y
o
f
w
o
r
d
,
th
e
n
ar
e
j
o
in
ed
b
ac
k
a
s
a
lis
t
o
f
o
n
e
o
r
m
o
r
e
s
te
m
s
b
ec
au
s
e
th
e
te
x
t
o
f
d
ata
is
in
t
h
e
f
o
r
m
o
f
E
n
g
li
s
h
,
th
e
s
te
m
m
i
n
g
m
et
h
o
d
d
o
n
e
u
s
i
n
g
t
h
e
P
o
tter
s
Ste
m
m
er
al
g
o
r
ith
m
i
n
t
h
e
p
r
o
ce
s
s
.
T
h
e
r
esu
lt
r
ep
r
esen
t
s
i
n
Fi
g
u
r
e
5
,
w
ith
t
h
e
f
o
u
r
-
co
l
u
m
n
v
ar
ia
b
les to
d
is
tin
g
u
i
s
h
ed
th
e
p
r
o
ce
s
s
ed
d
ata.
Fig
u
r
e
5
.
Sa
m
p
le
o
f
t
h
e
Face
b
o
o
k
p
o
s
t'
s
co
m
m
e
n
t
s
d
ata
f
o
ll
o
w
i
n
g
t
h
e
to
k
e
n
izi
n
g
an
d
s
te
m
m
i
n
g
p
r
o
ce
s
s
3
.
2
.
3
.
Co
ns
t
ruct
t
he
wo
rdlis
t
Fo
llo
w
i
n
g
th
e
ca
n
d
id
ate
d
ata
af
ter
th
e
to
k
en
ized
an
d
s
te
m
m
ed
p
r
o
ce
d
u
r
e,
as
th
e
y
r
ep
r
esen
te
d
i
n
Fig
u
r
e
6
o
cc
u
r
r
ed
,
th
e
ca
n
d
id
ate
d
ata
s
u
p
p
o
s
ed
to
co
u
n
t
as
it
w
o
u
ld
p
r
o
d
u
ce
th
e
i
n
f
o
r
m
at
io
n
ab
o
u
t
th
e
m
o
s
t
co
m
m
o
n
o
cc
u
r
r
en
ce
o
f
th
e
wo
r
d
s
co
n
ca
ten
ated
in
th
e
te
s
ti
n
g
s
a
m
p
le
s
e
n
ten
ce
.
T
h
e
ca
n
d
id
ate
d
ata
s
u
p
p
o
s
ed
to
co
u
n
t
as
it
w
o
u
ld
p
r
o
d
u
ce
t
h
e
i
n
f
o
r
m
atio
n
w
it
h
m
o
r
e
r
est
r
ict
q
u
ali
f
icatio
n
w
it
h
t
y
p
ical
E
n
g
l
is
h
s
to
p
w
o
r
d
s
(
ad
d
itio
n
al
r
eq
u
ir
e
m
e
n
t
ad
d
ed
)
.
Ho
w
e
v
er
as
t
h
e
p
r
ev
io
u
s
l
y
o
b
j
ec
tiv
e
is
to
d
eter
m
in
e
w
h
et
h
er
t
h
e
d
ataset
i
s
as
in
ter
p
r
et
o
f
th
e
p
ar
t o
f
s
en
ti
m
e
n
t a
n
a
l
y
s
is
(
p
o
s
iti
v
e,
n
e
u
tr
al
o
r
n
eg
ati
v
e)
cl
u
s
ter
,
a
w
o
r
d
s
u
c
h
as "
n
o
t"
an
d
"
n
'
t"
co
m
e
s
b
i
g
d
ea
l
a
s
it
ca
n
in
f
l
u
en
ce
t
h
e
r
es
u
lti
n
g
p
r
o
ce
s
s
o
f
t
h
e
e
x
p
er
i
m
e
n
t
o
f
s
e
n
ti
m
e
n
t
a
n
al
y
s
i
s
s
ig
n
i
f
ica
n
tl
y
.
Hen
ce
it b
ig
d
ea
ls
w
i
th
t
h
ese,
th
en
t
h
e
w
o
r
d
s
(
"
n
o
t"
an
d
"
n
'
t
"
)
w
o
u
ld
b
e
w
h
ite
lis
ted
i
n
th
e
w
h
iteli
s
t
v
ar
iab
le.
Fig
u
r
e
6
.
Sa
m
p
le
o
f
t
h
e
Face
b
o
o
k
p
o
s
t'
s
co
m
m
e
n
t
s
d
ata
f
o
ll
o
w
i
n
g
t
h
e
ca
lc
u
latio
n
o
f
w
o
r
d
o
cc
u
r
r
en
ce
s
p
r
o
ce
s
s
Fo
llo
w
i
n
g
th
e
ca
n
d
id
ate
d
ata
af
ter
b
ein
g
lis
ted
o
f
all
t
h
e
o
cc
u
r
r
en
ce
o
f
w
o
r
d
s
an
d
s
to
r
ed
all
th
e
ca
n
d
id
ate
d
ata,
as
t
h
e
y
r
ep
r
esen
t
i
n
Fig
u
r
e
7
,
v
is
u
alize
d
all
th
e
d
is
t
in
ct
o
cc
u
r
r
en
ce
o
f
all
w
o
r
d
s
i
m
p
lied
o
n
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
4
,
A
u
g
u
s
t
2021
:
3
4
2
4
-
3433
3430
Face
b
o
o
k
p
o
s
t
co
m
m
en
t
s
d
ata.
T
h
e
g
r
ap
h
is
g
e
n
er
ated
b
y
th
e
u
ti
lizatio
n
o
f
t
h
e
P
lo
tl
y
lib
r
ar
y
o
f
t
h
e
P
y
th
o
n
,
w
h
ic
h
h
as
a
g
r
ea
t
d
ea
l
w
it
h
g
r
ap
h
ic
an
al
y
tical
as
t
h
e
in
ter
p
r
etatio
n
o
f
th
e
s
elec
ti
v
e
ca
n
d
id
ate
d
ata.
T
h
e
w
o
r
d
r
o
u
g
h
l
y
o
r
d
er
ed
ev
en
th
o
u
g
h
alr
ea
d
y
s
h
o
w
n
t
h
e
o
cc
u
r
r
en
ce
o
f
ea
ch
o
f
th
e
w
o
r
d
s
.
I
t
n
ee
d
s
to
b
e
s
im
p
li
f
ied
to
k
n
o
w
th
at
t
h
er
e
is
a
co
n
n
ec
tio
n
b
et
w
ee
n
w
o
r
d
o
cc
u
r
r
en
ce
a
n
d
th
e
s
e
n
ti
m
e
n
t.
E
ac
h
li
s
t
o
f
th
e
i
n
d
iv
id
u
al
w
o
r
d
in
t
h
e
p
r
ev
io
u
s
g
r
ap
h
i
s
s
to
r
ed
,
also
co
n
n
ec
ted
w
it
h
i
n
th
e
b
as
e
[
em
o
tio
n
]
,
w
h
ic
h
r
es
u
lts
i
n
s
ev
er
al
o
cc
u
r
r
en
ce
s
w
o
r
d
s
ex
i
s
ted
,
w
ith
t
h
e
[
t
h
an
k
s
]
w
o
r
d
v
ar
iab
le
is
t
h
e
m
o
s
t o
c
cu
r
r
en
ce
w
o
r
d
(
u
p
to
m
o
r
e
th
a
n
7
0
r
ep
etitio
n
s
)
.
Fig
u
r
e
7
.
Sa
m
p
le
o
f
t
h
e
g
r
ap
h
i
c
ch
ar
t o
f
th
e
o
cc
u
r
r
e
n
ce
o
f
t
h
e
Face
b
o
o
k
p
o
s
t'
s
co
m
m
e
n
ts
d
ata
v
is
u
aliza
tio
n
4.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
N
T
h
is
s
t
u
d
y
m
et
h
o
d
in
v
o
lv
ed
F
ac
eb
o
o
k
'
s
p
o
s
t
s
,
an
d
co
m
m
e
n
t
s
ar
e
ev
al
u
ated
w
it
h
a
h
eld
-
o
u
t
test
s
et,
o
f
w
h
ic
h
6
0
0
p
o
s
ts
an
d
co
m
m
en
ts
s
a
m
p
les
d
ata.
T
h
is
p
o
s
ts
an
d
co
m
m
e
n
ts
u
p
lo
ad
ed
in
a
r
an
g
e
ti
m
e
o
f
ea
r
l
y
2
0
2
0
;
th
ese
d
ata
ev
alu
ate
n
e
ar
th
e
d
ate
th
ese
p
o
s
ts
p
o
s
ted
to
m
ak
e
it
ea
s
ier
to
s
ee
Face
b
o
o
k
s
er
v
ices
i
m
p
r
o
v
e
m
en
t
t
h
at
is
r
e
f
lecte
d
f
r
o
m
t
h
ese
p
o
s
ts
a
n
d
co
m
m
e
n
t
s
.
T
h
e
s
ce
n
ar
io
s
ar
e
d
iv
id
e
in
t
o
th
r
ee
p
h
ases
,
an
d
ea
ch
o
f
t
h
e
p
h
a
s
es
r
ep
r
esen
ts
th
e
p
o
s
t
p
o
s
ted
at
a
d
if
f
er
en
t
t
i
m
e.
T
h
e
Fi
g
u
r
e
8
r
ep
r
esen
t
s
t
h
e
p
o
s
t
o
n
J
an
u
ar
y
3
0
,
2
0
2
0
;
Fig
u
r
e
9
r
ep
r
esen
ts
th
e
p
o
s
t
o
n
F
eb
r
u
ar
y
2
6
,
2
0
2
0
;
Fig
u
r
e
10
r
e
p
r
esen
ts
th
e
p
o
s
t
o
n
Ma
r
ch
2
5
,
2020.
It
s
h
o
w
ed
i
n
Fi
g
u
r
e
10
th
at
t
h
is
p
o
s
t
ac
q
u
ir
es
m
o
r
e
wo
r
d
s
as
a
n
eg
ati
v
e
w
o
r
d
;
th
e
s
e
s
tatis
t
ics
tell
th
at
th
e
q
u
ali
t
y
o
f
th
e
s
er
v
ice
s
o
n
J
an
u
ar
y
3
0
,
2
0
2
0
,
m
o
r
e
s
aid
to
h
av
e
d
ec
r
ea
s
ed
.
Al
s
o
,
in
Fig
u
r
e
9
,
ea
ch
w
o
r
d
th
at
h
a
s
m
a
n
y
t
y
p
e
s
o
f
s
en
ti
m
en
t
r
ep
r
esen
tatio
n
ar
e
s
u
m
m
ar
ized
,
an
d
t
h
e
q
u
alit
y
o
f
t
h
e
s
e
r
v
ices
o
n
Feb
r
u
ar
y
2
6
,
2
0
2
0
,
y
et
s
till
r
ea
p
i
n
g
n
e
g
ati
v
e
r
ep
lies
-
i
n
Fi
g
u
r
e
10
,
alr
ea
d
y
s
h
o
w
n
t
h
at
o
n
Ma
r
ch
2
5
,
2
0
2
0
,
th
e
m
o
s
t
co
llected
w
o
r
d
is
th
e
w
o
r
d
th
at
r
ep
r
esen
ts
th
e
p
o
s
iti
v
e
s
en
t
i
m
e
n
t
.
I
t
s
ig
n
ed
th
at
t
h
e
d
ata
d
is
tr
ib
u
tio
n
h
a
s
a
r
an
d
o
m
p
atter
n
.
So
,
f
r
o
m
th
at
th
r
ee
-
p
h
ase
ca
n
b
e
s
u
m
m
ar
ized
,
th
e
q
u
alit
y
o
f
t
h
e
s
e
r
v
ices
o
n
t
h
e
d
at
e
m
en
tio
n
ed
is
in
cr
ea
s
in
g
an
d
r
ea
p
in
g
p
o
s
iti
v
e
r
ep
lies
.
T
h
e
i
m
p
licatio
n
s
o
f
th
is
r
esear
ch
w
il
l
u
n
d
o
u
b
ted
l
y
b
e
u
s
e
f
u
l f
o
r
th
e
d
ev
e
lo
p
m
en
t o
f
th
e
Face
b
o
o
k
ap
p
in
ter
m
s
o
f
t
h
e
q
u
alit
y
o
f
s
er
v
ice
p
r
o
v
id
ed
to
Face
b
o
o
k
u
s
er
s
.
Fig
u
r
e
8
.
Sa
m
p
le
o
f
s
e
n
ti
m
e
n
t
an
al
y
s
is
o
f
th
e
Face
b
o
o
k
p
o
s
t
's co
m
m
en
t
s
d
ata
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
Th
e
imp
a
ct
o
f sen
timen
t a
n
a
lysi
s
fr
o
m
u
s
e
r
o
n
F
a
ce
b
o
o
k
to
…
(
Da
n
iel
D.
A
lb
esta
)
3431
Fig
u
r
e
9
.
Sa
m
p
le
o
f
s
e
n
ti
m
e
n
t
an
al
y
s
is
o
f
th
e
Face
b
o
o
k
p
o
s
t
's co
m
m
en
t
s
d
ata
Fig
u
r
e
10
.
Sa
m
p
le
o
f
s
e
n
ti
m
e
n
t a
n
al
y
s
is
o
f
t
h
e
Face
b
o
o
k
p
o
s
t
'
s
co
m
m
e
n
ts
d
ata
I
n
d
ir
ec
tl
y
,
th
e
a
s
s
es
s
m
en
t
o
f
s
er
v
ices
t
h
at
u
ti
lize
th
e
co
n
ce
p
t
o
f
an
al
y
s
i
s
b
ased
o
n
s
en
ti
m
e
n
tal
u
s
er
s
h
as
q
u
ite
a
co
m
p
le
x
it
y
i
n
t
h
e
an
al
y
s
is
t
h
at
is
n
o
t
v
er
y
co
m
p
licated
,
w
it
h
th
e
s
u
p
p
o
r
t
o
f
p
y
th
o
n
p
r
o
g
r
a
m
m
i
n
g
b
ase
th
at
i
m
p
le
m
e
n
ts
n
at
u
r
al
lan
g
u
a
g
e
p
r
o
ce
s
s
in
g
alg
o
r
it
h
m
an
d
f
u
n
ctio
n
s
i
n
m
ac
h
i
n
e
lear
n
in
g
o
f
N
L
T
K
,
an
d
Scik
it
-
lear
n
lib
r
ar
y
.
T
h
er
e
ar
e
t
w
o
s
h
o
r
tco
m
i
n
g
s
o
f
t
h
e
im
p
le
m
e
n
ted
alg
o
r
it
h
m
,
r
es
u
lt
in
g
f
r
o
m
th
e
d
ata
d
is
tr
ib
u
tio
n
p
r
o
ce
s
s
in
t
h
is
s
t
u
d
y
,
w
h
ich
is
t
h
e
s
k
e
w
ed
d
ata
s
u
c
h
as
th
e
v
ar
iab
le
s
[
p
o
s
t]
an
d
[
ac
co
u
n
t]
in
Fig
u
r
e
9
.
I
t
also
h
ap
p
en
s
s
i
m
ilar
l
y
to
p
o
s
iti
v
e
a
n
d
n
e
u
tr
al
co
m
m
en
t
s
;
t
h
i
s
s
h
o
r
tco
m
i
n
g
w
o
u
ld
lead
to
t
h
e
d
is
tin
g
u
is
h
p
r
o
b
lem
at
ic
b
et
w
e
en
th
e
p
o
s
iti
v
e,
n
eu
tr
al,
n
o
r
n
eg
ati
v
e
co
m
m
en
t
s
f
r
o
m
o
n
e
a
n
o
th
er
.
Fo
llo
w
ed
b
y
th
e
i
n
co
m
p
lete
an
al
y
tica
l
p
r
o
ce
s
s
,
w
h
ic
h
h
a
s
n
o
t
i
n
cl
u
d
ed
in
th
e
d
ata
p
r
o
ce
s
s
in
g
m
et
h
o
d
,
is
t
h
e
d
eter
m
i
n
atio
n
o
f
d
ata
p
r
ec
is
io
n
.
W
ith
o
u
t
t
h
e
p
r
ec
is
io
n
m
eth
o
d
in
v
o
l
v
e
d
,
it
also
w
o
u
ld
lead
to
th
e
d
ata
d
is
tr
u
s
t
an
d
in
co
n
s
is
te
n
t
p
r
o
b
lem
a
tic
f
o
r
th
e
u
s
er
w
h
o
an
a
l
y
ze
d
.
Nev
er
t
h
eles
s
,
th
e
s
tr
o
n
g
p
o
in
t
o
f
th
e
s
e
is
less
co
m
p
lex
i
t
y
ti
m
e,
m
o
r
e
co
m
f
o
r
tab
le
to
b
e
co
d
ed
an
d
im
p
le
m
e
n
ted
,
also
g
en
er
ates
a
s
i
m
p
le
b
u
t
s
tr
ai
g
h
t
f
o
r
w
ar
d
g
r
ap
h
ic
s
r
ath
er
th
an
o
t
h
er
alg
o
r
ith
m
s
s
u
ch
as
Naï
v
e
B
a
y
es
f
o
r
th
e
d
ata
class
i
f
icatio
n
m
et
h
o
d
o
r
G
lo
Ve
-
tr
ain
ed
m
o
d
el
w
it
h
w
o
r
d
2
v
ec
f
o
r
m
a
t.
5.
C
O
N
C
L
U
SIO
N
As
t
h
is
r
esear
ch
p
ap
er
is
co
m
p
leted
,
it
r
ev
ea
ls
t
h
e
i
m
p
licati
o
n
t
h
at
o
cc
u
r
s
as
it
is
p
r
ese
n
t
ed
in
t
h
e
au
th
o
r
s
'
c
u
r
r
en
t
r
esear
ch
.
T
h
e
r
esu
lt
o
f
t
h
is
p
ap
er
s
h
o
w
s
an
i
m
p
r
o
v
e
m
e
n
t
ad
v
is
o
r
f
o
r
Face
b
o
o
k
'
s
s
er
v
ices
q
u
alit
y
f
u
t
u
r
e
f
r
o
m
a
g
li
m
p
s
e
o
f
p
eo
p
le'
s
s
en
ti
m
e
n
t
a
n
d
p
er
ce
p
tio
n
o
f
Face
b
o
o
k
i
n
r
ec
en
t
t
i
m
es.
T
h
i
s
cu
r
r
en
t
s
tu
d
y
w
o
u
ld
p
r
ed
ict
th
e
i
m
p
r
o
v
e
m
e
n
t
ad
v
ice
o
f
Face
b
o
o
k
's
s
er
v
ices
d
e
v
elo
p
m
e
n
t
i
n
t
h
e
f
u
tu
r
e
.
T
h
e
f
u
tu
r
e
d
ev
elo
p
m
en
t
s
o
f
t
h
i
s
s
t
u
d
y
m
a
y
u
tili
ze
a
lar
g
e
te
s
ti
n
g
d
ataset,
w
h
ich
w
o
u
ld
allo
w
t
h
e
t
est
t
o
p
r
ed
ict
m
o
r
e
ac
cu
r
atel
y
as
i
m
p
r
o
v
e
m
en
t
a
d
v
ice
f
o
r
Face
b
o
o
k
's
s
er
v
ices
d
ev
elo
p
m
e
n
t
.
F
u
r
th
er
m
o
r
e,
t
h
e
r
esear
ch
w
ill
b
e
co
n
d
u
cted
i
n
ter
m
s
o
f
p
r
ec
is
io
n
o
f
d
ata
p
r
o
ce
s
s
i
n
g
ac
cu
r
ac
y
,
w
h
ic
h
in
c
lu
d
es
t
h
r
ee
m
ai
n
f
ac
to
r
s
i
n
d
eter
m
in
i
n
g
th
e
lev
e
l
o
f
s
en
ti
m
en
tal
ac
cu
r
ac
y
o
f
t
h
e
u
s
er
,
n
a
m
el
y
ac
c
u
r
ac
y
,
R
ec
all,
an
d
F
1
Sco
r
e
f
ac
to
r
.
B
y
f
o
cu
s
in
g
o
n
t
h
ese
f
ac
to
r
s
,
it
w
i
ll r
esu
lt i
n
a
f
a
ir
,
co
r
r
ec
t,
an
d
ac
cu
r
ate
an
al
y
tic
p
r
o
ce
s
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
4
,
A
u
g
u
s
t
2021
:
3
4
2
4
-
3433
3432
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
an
k
s
to
th
e
ass
is
ta
n
ce
f
r
o
m
B
in
a
Nu
s
an
tar
a
Un
iv
er
s
it
y
a
s
th
e
au
t
h
o
r
s
'
ed
u
ca
tio
n
al
g
u
i
d
an
ce
an
d
s
u
p
p
o
r
ts
all
th
e
r
esear
c
h
es i
n
v
o
lv
ed
in
th
is
p
ap
er
.
RE
F
E
R
E
NC
E
S
[1
]
G
u
p
ta,
S
h
a
sh
a
n
k
,
"
S
e
n
ti
m
e
n
t
A
n
a
l
y
sis:
Co
n
c
e
p
t,
A
n
a
ly
sis,
a
n
d
Ap
p
li
c
a
ti
o
n
s,"
T
o
w
a
rd
sd
a
t
a
sc
ien
c
e
.
c
o
m
,
[
On
li
n
e
]
.
Av
a
il
a
b
le
:
h
tt
p
s://
to
w
a
rd
sd
a
tas
c
ie
n
c
e
.
c
o
m
/se
n
ti
m
e
n
t
-
a
n
a
l
y
sis
-
c
o
n
c
e
p
t
-
a
n
a
ly
sis
-
a
n
d
-
a
p
p
l
ica
ti
o
n
s
-
6
c
9
4
d
6
f
5
8
c
1
7
.
[2
]
No
y
e
s,
Da
n
,
"
T
h
e
T
o
p
2
0
V
a
lu
a
b
le F
a
c
e
b
o
o
k
S
tati
stics
-
Up
d
a
ted
Ja
n
u
a
ry
2
0
2
0
,
"
ze
p
h
o
ri
a
.
c
o
m
,
[
On
l
i
n
e
]
.
A
v
a
il
a
b
le
:
h
tt
p
s:/
/ze
p
h
o
ria.co
m
/t
o
p
-
15
-
v
a
lu
a
b
le
-
F
a
c
e
b
o
o
k
-
sta
ti
stics
.
[3
]
P
a
t
h
a
k
,
L
a
li
t,
M
u
lch
a
n
d
a
n
i,
S
a
n
jan
a
,
Ka
te,
M
a
y
u
ri,
Kh
a
t
w
a
n
i,
Ka
jal,
Kh
e
d
k
a
r,
S
u
jata
,
"
S
e
n
ti
m
e
n
t
a
n
d
In
ten
t
A
n
a
l
y
si
s
f
o
r
Bu
sin
e
ss
In
telli
g
e
n
c
e
,
"
2
0
1
7
I
EE
E
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Po
we
r,
C
o
n
tr
o
l,
S
ig
n
a
ls
a
n
d
In
stru
me
n
ta
ti
o
n
E
n
g
i
n
e
e
rin
g
(
ICPCS
I),
v
o
l
.
6
,
n
o
.
1
,
2
0
1
8
,
p
p
.
3
4
8
-
3
5
4
,
d
o
i:
1
0
.
1
5
6
8
0
/IJIRCCE.
2
0
1
8
.
0
6
0
1
0
5
9
.
[4
]
Rich
ter,
F
e
li
x
,
"
T
o
x
ic
Co
n
ten
t
Ru
n
s
Ra
m
p
a
n
t
o
n
F
a
c
e
b
o
o
k
,"
S
ta
ti
st
a
.
c
o
m
,
[
On
li
n
e
]
A
v
a
il
a
b
le
:
h
tt
p
s:/
/www
.
sta
ti
sta
.
c
o
m
/ch
a
rt/
1
3
8
7
5
/F
a
c
e
b
o
o
k
s
-
sp
rin
g
-
c
lea
n
in
g
/
,
[
a
c
c
e
ss
e
d
M
a
rc
h
2
,
2
0
2
0
]
.
[5
]
Rich
ter,
F
e
li
x
.
"
F
a
c
e
b
o
o
k
Ke
e
p
s
o
n
G
ro
w
in
g
,
"
S
ta
ti
sta
.
c
o
m
,
[
On
li
n
e
]
Av
a
il
a
b
le
:
h
tt
p
s:/
/www
.
sta
ti
sta
.
c
o
m
/ch
a
rt/
1
0
0
4
7
/F
a
c
e
b
o
o
k
s
-
m
o
n
th
ly
-
a
c
ti
v
e
-
u
se
r
s
[6
]
L
iu
,
B.
,
“
S
e
n
ti
m
e
n
t
a
n
a
l
y
sis
a
n
d
su
b
jec
ti
v
it
y
,
”
Ha
n
d
b
o
o
k
o
f
n
a
tu
ra
l
la
n
g
u
a
g
e
p
r
o
c
e
ss
in
g
,
v
o
l
.
2
,
n
o
.
20
1
0
,
p
p
.
6
2
7
-
6
6
6
,
2
0
1
0
.
[7
]
Ba
lah
u
r,
A
.
,
a
n
d
T
u
rc
h
i
,
M
.
,
“
Co
m
p
a
ra
ti
v
e
e
x
p
e
ri
m
e
n
ts
u
sin
g
su
p
e
rv
ise
d
lea
rn
in
g
a
n
d
m
a
c
h
in
e
tran
sla
ti
o
n
f
o
r
m
u
lt
il
in
g
u
a
l
se
n
ti
m
e
n
t
a
n
a
ly
sis,
”
Co
mp
u
ter
S
p
e
e
c
h
a
n
d
L
a
n
g
u
a
g
e
,
v
o
l.
2
8
,
n
o
.
1
,
p
p
.
5
6
-
7
5
,
2
0
1
4
.
[8
]
F
ra
n
z
o
n
i
,
V.,
L
i
,
Y.,
a
n
d
M
e
n
g
o
n
i,
P
.
,
“
A
p
a
th
-
b
a
se
d
m
o
d
e
l
f
o
r
e
m
o
ti
o
n
a
b
stra
c
ti
o
n
o
n
F
a
c
e
b
o
o
k
u
sin
g
se
n
ti
m
e
n
t
a
n
a
ly
sis
a
n
d
tax
o
n
o
m
y
k
n
o
w
led
g
e
,
”
Pro
c
e
e
d
in
g
s
o
f
th
e
I
n
ter
n
a
t
i
o
n
a
l
Co
n
fer
e
n
c
e
o
n
W
e
b
In
telli
g
e
n
c
e
-
W
I,
2
0
1
7
,
p
p
.
9
4
7
-
9
5
2
,
d
o
i:
1
0
.
1
1
4
5
/3
1
0
6
4
2
6
.
3
1
0
9
4
2
0
.
[9
]
S
a
n
d
o
v
a
l
-
A
lma
z
a
n
,
R.
,
a
n
d
V
a
l
le
-
Cru
z
,
D.,
“
F
a
c
e
b
o
o
k
im
p
a
c
t
a
n
d
se
n
ti
m
e
n
t
a
n
a
l
y
sis
o
n
p
o
li
ti
c
a
l
c
a
m
p
a
ig
n
s,”
Pro
c
e
e
d
in
g
s
o
f
t
h
e
1
9
th
A
n
n
u
a
l
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Dig
i
t
a
l
Go
v
e
rn
me
n
t
Res
e
a
rc
h
G
o
v
e
rn
a
n
c
e
in
th
e
Da
t
a
Ag
e
–
D
g
o
,
2
0
1
8
,
p
p
.
1
-
7
,
d
o
i:
1
0
.
1
1
4
5
/
3
2
0
9
2
8
1
.
3
2
0
9
3
2
8
.
[1
0
]
P
letik
o
sa
,
Ir
e
n
a
a
n
d
M
ich
a
h
e
ll
e
s,
F
lo
rian
,
"
Un
d
e
rsta
n
d
i
n
g
so
c
ial
m
e
d
ia
m
a
r
k
e
ti
n
g
:
A
c
a
s
e
st
u
d
y
o
n
to
p
ics
,
c
a
teg
o
ries
a
n
d
se
n
ti
m
e
n
t
o
n
a
F
a
c
e
b
o
o
k
b
ra
n
d
p
a
g
e
,
"
2
0
1
1
,
d
o
i
:1
0
.
1
1
4
5
/
2
1
8
1
0
3
7
.
2
1
8
1
0
6
6
.
[1
1
]
S
.
S
.
Da
sg
u
p
ta,
S
.
Na
tara
jan
,
K.
K.
Ka
ip
a
,
S
.
K.
Bh
a
tt
a
c
h
e
rj
e
e
a
n
d
A
.
V
isw
a
n
a
th
a
n
,
"
S
e
n
ti
m
e
n
t
a
n
a
ly
sis
o
f
F
a
c
e
b
o
o
k
d
a
ta
u
sin
g
Ha
d
o
o
p
b
a
se
d
o
p
e
n
so
u
rc
e
tec
h
n
o
lo
g
ies
,
"
2
0
1
5
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
Da
ta
S
c
ien
c
e
a
n
d
A
d
v
a
n
c
e
d
An
a
lytics
(
DS
AA
)
,
2
0
1
5
,
p
p
.
1
-
3.
[1
2
]
Ro
d
ríg
u
e
z
,
A
.
,
A
r
g
u
e
ta,
C.
,
a
n
d
Ch
e
n
,
Y.
L
.
,
“
A
u
to
m
a
ti
c
d
e
tec
ti
o
n
o
f
h
a
te
sp
e
e
c
h
o
n
f
a
c
e
b
o
o
k
u
sin
g
se
n
ti
m
e
n
t
a
n
d
e
m
o
ti
o
n
a
n
a
ly
sis
,”
2
0
1
9
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Arti
fi
c
ia
l
I
n
telli
g
e
n
c
e
in
In
fo
rm
a
t
io
n
a
n
d
Co
mm
u
n
ica
ti
o
n
(
ICAII
C),
20
1
9
,
p
p
.
1
6
9
-
1
7
4
.
[1
3
]
Yo
o
,
S
.
,
S
o
n
g
,
J.,
a
n
d
J
e
o
n
g
,
O.,
“
S
o
c
ial
m
e
d
ia
c
o
n
ten
ts
b
a
se
d
se
n
ti
m
e
n
t
a
n
a
ly
sis
a
n
d
p
re
d
icti
o
n
sy
ste
m
,
”
Exp
e
rt
S
y
ste
ms
wit
h
Ap
p
li
c
a
ti
o
n
s,
v
o
l
.
1
0
5
,
p
p
.
1
0
2
-
1
1
1
,
2
0
1
8
.
[1
4
]
Ta
d
e
ss
e
,
M
.
M
.
,
L
in
,
H.,
X
u
,
B.
,
a
n
d
Ya
n
g
,
L
.
,
“
P
e
rso
n
a
li
ty
p
re
d
ictio
n
s
b
a
se
d
o
n
u
se
r
b
e
h
a
v
io
r
o
n
th
e
f
a
c
e
b
o
o
k
so
c
ial
m
e
d
ia p
latf
o
r
m
,
”
IEE
E
Acc
e
ss
,
v
o
l.
6
,
p
p
.
6
1
9
5
9
-
6
1
9
6
9
,
2
0
1
8
.
[1
5
]
Ak
ter,
S
.
,
a
n
d
A
z
iz,
M
.
T
.
,
“
S
e
n
ti
m
e
n
t
a
n
a
l
y
sis
o
n
f
a
c
e
b
o
o
k
g
ro
u
p
u
sin
g
L
e
x
ico
n
b
a
se
d
a
p
p
r
o
a
c
h
,
”
In
2
0
1
6
3
rd
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
El
e
c
trica
l
En
g
i
n
e
e
rin
g
a
n
d
I
n
fo
r
ma
ti
o
n
Co
mm
u
n
ica
t
io
n
T
e
c
h
n
o
l
o
g
y
(
ICEE
ICT
)
,
2
0
1
6
,
p
p
.
1
-
4
.
[1
6
]
Im
r
a
n
,
A
.
,
F
a
i
y
a
z
,
M
.
,
a
n
d
Ak
h
tar,
F
.
,
“
A
n
e
n
h
a
n
c
e
d
a
p
p
ro
a
c
h
f
o
r
q
u
a
n
ti
tativ
e
p
re
d
ictio
n
o
f
p
e
rso
n
a
li
ty
in
f
a
c
e
b
o
o
k
p
o
sts,”
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ed
u
c
a
ti
o
n
a
n
d
M
a
n
a
g
e
me
n
t
E
n
g
i
n
e
e
rin
g
(
IJ
EM
E),
v
o
l.
8
,
n
o
.
2
,
p
p
.
8
-
1
9
,
2
0
1
8
.
[1
7
]
Ba
g
h
e
ri,
H.,
a
n
d
Isla
m
,
M
.
J.,
“
S
e
n
ti
m
e
n
t
a
n
a
ly
sis o
f
t
w
it
ter d
a
ta,”
a
rXiv p
re
p
ri
n
t
a
rX
iv:1
7
1
1
.
1
0
3
7
7
,
2
0
1
7
.
[1
8
]
S
k
o
w
ro
n
,
M
.
,
T
k
a
lčič
,
M
.
,
F
e
rw
e
rd
a
,
B.
,
a
n
d
S
c
h
e
d
l,
M
.
,
“
F
u
si
n
g
so
c
ial
m
e
d
ia
c
u
e
s:
p
e
rso
n
a
li
ty
p
re
d
ic
ti
o
n
f
ro
m
tw
it
ter
a
n
d
in
sta
g
ra
m
,
”
In
Pro
c
e
e
d
in
g
s
o
f
t
h
e
2
5
t
h
i
n
ter
n
a
ti
o
n
a
l
c
o
n
fer
e
n
c
e
c
o
mp
a
n
i
o
n
o
n
w
o
rld
wi
d
e
we
b
,
2
0
1
6
,
p
p
.
1
0
7
-
1
0
8
.
[1
9
]
M
a
rk
o
v
ik
j,
D.,
G
iev
s
k
a
,
S
.
,
Ko
s
in
sk
i,
M
.
,
a
n
d
S
ti
ll
w
e
ll
,
D.
J.,
“
M
in
i
n
g
f
a
c
e
b
o
o
k
d
a
ta
f
o
r
p
re
d
ic
ti
v
e
p
e
rso
n
a
li
ty
mo
d
e
ll
in
g
,
”
In
S
e
v
e
n
t
h
In
ter
n
a
ti
o
n
a
l
AA
AI
C
o
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
ia
,
2
0
1
3
.
[2
0
]
S
o
li
m
a
n
,
T
.
H.,
El
m
a
sr
y
,
M
.
A
.
,
He
d
a
r,
A
.
,
a
n
d
Do
ss
,
M
.
M
.
,
“
S
e
n
ti
m
e
n
t
a
n
a
l
y
sis
o
f
A
r
a
b
ic
sla
n
g
c
o
m
m
e
n
ts
o
n
f
a
c
e
b
o
o
k
,
”
In
te
rn
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Co
m
p
u
ter
s a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
1
2
,
n
o
.
5
,
p
p
.
3
4
7
0
-
3
4
7
8
,
2
0
1
4
.
[2
1
]
Da
sg
u
p
ta,
S
.
S
.
,
Na
tara
jan
,
S
.
,
Ka
ip
a
,
K.
K.,
Bh
a
tt
a
c
h
e
rjee
,
S
.
K.,
a
n
d
V
isw
a
n
a
th
a
n
,
A
.
,
“
S
e
n
ti
m
e
n
t
a
n
a
l
y
sis
o
f
F
a
c
e
b
o
o
k
d
a
ta
u
sin
g
Ha
d
o
o
p
b
a
se
d
o
p
e
n
so
u
rc
e
tec
h
n
o
lo
g
ies
,
”
In
2
0
1
5
IEE
E
I
n
ter
n
a
t
io
n
a
l
Co
n
f
e
re
n
c
e
o
n
Da
ta
S
c
ien
c
e
a
n
d
A
d
v
a
n
c
e
d
An
a
lytics
(
DS
AA
),
2
0
1
5
,
p
p
.
1
-
3
.
[2
2
]
S
a
if
,
H.,
He
,
Y.,
F
e
rn
a
n
d
e
z
,
M
.
,
a
n
d
A
lan
i
,
H.,
“
Co
n
tex
tu
a
l
se
m
a
n
ti
c
s
f
o
r
se
n
ti
m
e
n
t
a
n
a
l
y
sis
o
f
Tw
it
te
r,
”
In
fo
rm
a
t
io
n
Pro
c
e
ss
in
g
a
n
d
M
a
n
a
g
e
me
n
t,
v
o
l.
5
2
,
n
o
.
1
,
p
p
.
5
-
1
9
,
2
0
1
6
.
[2
3
]
Ch
e
n
,
T
.
,
X
u
,
R.
,
He
,
Y.,
a
n
d
W
a
n
g
,
X
.
,
“
Im
p
ro
v
in
g
se
n
ti
m
e
n
t
a
n
a
ly
sis
v
ia
se
n
ten
c
e
t
y
p
e
c
las
sif
ica
ti
o
n
u
sin
g
BiL
S
T
M
-
CRF
a
n
d
CNN
,
”
Exp
e
rt S
y
ste
ms
wit
h
A
p
p
l
ica
ti
o
n
s,
v
o
l.
7
2
,
p
p
.
2
2
1
-
2
3
0
,
2
0
0
1
7
.
[2
4
]
P
a
n
d
e
y
,
A
.
C.
,
R
a
jp
o
o
t,
D.
S
.
,
a
n
d
S
a
ra
s
w
a
t,
M
.
,
“
Tw
it
ter
s
e
n
ti
m
e
n
t
a
n
a
ly
sis
u
sin
g
h
y
b
rid
c
u
c
k
o
o
se
a
rc
h
m
e
th
o
d
,”
In
fo
rm
a
t
io
n
Pro
c
e
ss
i
n
g
a
n
d
M
a
n
a
g
e
me
n
t,
v
o
l.
5
3
,
n
o
.
4
,
p
p
.
7
6
4
-
7
7
9
,
2
0
1
7
.
[2
5
]
M
a
,
Y.,
P
e
n
g
,
H.
,
a
n
d
Ca
m
b
ria
,
E
.
,
“
T
a
rg
e
ted
a
sp
e
c
t
-
b
a
se
d
se
n
ti
m
e
n
t
a
n
a
ly
sis
v
ia
e
m
b
e
d
d
in
g
c
o
m
m
o
n
se
n
se
kn
o
w
led
g
e
in
to
a
n
a
tt
e
n
ti
v
e
L
S
TM
,
”
In
Pr
o
c
e
e
d
in
g
s o
f
th
e
AA
AI
Co
n
fer
e
n
c
e
o
n
Arti
fi
c
i
a
l
I
n
telli
g
e
n
c
e
,
2
0
1
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
Th
e
imp
a
ct
o
f sen
timen
t a
n
a
lysi
s
fr
o
m
u
s
e
r
o
n
F
a
ce
b
o
o
k
to
…
(
Da
n
iel
D.
A
lb
esta
)
3433
[2
6
]
Zab
ło
c
k
i,
M
a
rc
in
,
"
Ju
p
y
ter
No
teb
o
o
k
+
P
y
th
o
n
C
o
d
e
o
f
Tw
it
ter
S
e
n
ti
m
e
n
t
A
n
a
l
y
sis
,"
Gith
u
b
.
c
o
m
,
[
O
n
li
n
e
]
Av
a
il
a
b
le
:
h
tt
p
s://
g
it
h
u
b
.
c
o
m
/ma
r
rrc
in
/m
l
-
t
w
it
ter
-
se
n
ti
m
e
n
t
-
a
n
a
ly
s
is.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Da
n
i
e
l
De
m
e
tr
i
u
s
Alb
e
sta
i
s
a
m
o
ti
v
a
ted
p
e
rso
n
to
d
o
stu
d
y
in
th
e
d
a
tab
a
se
f
ield
,
e
sp
e
c
iall
y
in
th
e
m
u
lt
ip
le
su
b
jec
ts
re
late
d
t
o
th
e
Da
tab
a
se
A
d
m
in
istratio
n
a
n
d
S
y
ste
m
A
n
a
l
y
si
s.
T
a
k
e
e
d
u
c
a
ti
o
n
a
l
c
o
u
rse
s
o
n
t
h
e
Bin
a
Nu
sa
n
tara
Un
iv
e
rsity
,
a
n
d
h
e
g
o
t
g
u
id
a
n
c
e
o
n
h
is
p
ra
c
ti
c
e
,
w
h
ich
in
c
lu
d
e
s th
e
Big
Da
ta co
m
p
re
h
e
n
siv
e
w
it
h
in
it
.
No
t
o
n
ly
th
a
t,
b
u
t
Da
n
iel
a
lso
h
a
s a
sk
il
l
in
th
e
UI/
U
X
De
sig
n
o
f
a
n
a
p
p
li
c
a
ti
o
n
h
e
m
a
d
e
o
n
t
h
e
Bin
a
Nu
sa
n
tara
F
e
stiv
a
l
(Bif
e
st)
a
n
n
u
a
l
e
v
e
n
t.
Cu
rre
n
tl
y
,
h
e
w
o
rk
s
o
n
th
e
n
e
w
r
e
se
a
r
c
h
p
a
p
e
r,
w
h
ich
sp
e
c
if
ic
a
ll
y
a
b
o
u
t
Big
D
a
ta
a
n
d
se
n
ti
m
e
n
t
a
n
a
l
y
sis
f
lo
w
w
it
h
in
t
h
e
IM
Db
c
o
n
ten
ts.
He
is
p
re
se
n
tl
y
f
in
ish
in
g
h
is
Ba
c
h
e
lo
r
o
f
S
c
ien
c
e
in
Co
m
p
u
ter
S
c
ien
c
e
,
a
n
d
f
ro
m
th
is
p
o
i
n
t
f
o
rw
a
rd
,
th
e
a
m
b
it
io
n
h
e
h
a
s
is
to
b
e
a
d
a
ta
e
n
g
in
e
e
r
in
a
n
in
f
o
rm
a
ti
o
n
tec
h
n
o
lo
g
y
(I
T
)
d
e
p
a
rtme
n
t.
M
ich
a
e
l
Lio
n
g
J
o
n
a
th
a
n
,
stu
d
y
a
t
Bin
a
Nu
sa
n
tara
Un
iv
e
rsity
f
o
r
a
lm
o
st t
w
o
y
e
a
rs.
In
th
e
se
p
a
st
y
e
a
rs
,
h
e
d
e
d
ica
ted
h
im
se
lf
to
lea
rn
d
a
tab
a
se
a
n
d
h
o
w
it
w
o
rk
s
w
it
h
in
th
e
c
o
m
p
u
ter
sc
ien
c
e
w
o
rld
.
Un
ti
l
n
o
w
,
h
e
is
a
lso
w
o
rk
in
g
a
s
a
f
u
ll
-
ti
m
e
ju
n
i
o
r
p
ro
g
ra
m
m
e
r
a
t
Bin
a
Nu
sa
n
tara
Un
iv
e
rsit
y
a
l
w
a
y
s
to
k
e
e
p
u
p
a
n
d
lea
rn
in
g
m
o
re
a
b
o
u
t
d
a
tab
a
se
w
h
e
n
o
n
th
e
o
th
e
r
si
d
e
try
in
g
to
f
in
d
m
o
re
e
x
p
e
rien
c
e
s
o
f
h
a
v
in
g
a
c
a
re
e
r.
W
h
il
e
p
u
rsu
i
n
g
h
is
c
a
re
e
r,
c
u
rre
n
tl
y
,
h
e
is
c
o
m
p
letin
g
a
n
d
a
im
in
g
f
o
r
h
is Bac
h
e
lo
r
o
f
C
o
m
p
u
ter S
c
ien
c
e
.
M
u
h
a
m
m
a
d
J
a
w
a
d
is
a
Bin
a
Nu
sa
n
tara
Un
iv
e
rsit
y
lea
rn
e
r
w
h
o
is
c
u
rre
n
tl
y
u
n
d
e
rg
o
i
n
g
h
is
b
a
c
h
e
l
o
r'
s
d
e
g
re
e
in
c
o
m
p
u
ter
sc
i
e
n
c
e
.
T
h
e
in
tere
st
h
e
h
a
s
is
in
th
e
f
ield
re
late
d
to
th
e
In
tern
e
t
o
f
T
h
in
g
s (Io
T
)
a
n
d
o
th
e
r
f
ield
s su
c
h
a
s so
c
ial
m
e
d
ia an
d
d
ig
it
a
l
m
a
rk
e
ti
n
g
.
O
k
t
o
v
ia
n
u
s
H
a
r
d
ia
w
a
n
is
a
Bin
a
Nu
sa
n
tara
Un
iv
e
rsit
y
lea
rn
e
r
-
b
a
se
d
a
t
Ja
k
a
rta,
In
d
o
n
e
sia
,
a
n
d
a
t
th
e
a
g
e
o
f
e
l
e
v
e
n
,
h
e
w
a
s
g
e
n
u
in
e
ly
k
e
e
n
o
n
th
e
c
o
d
in
g
th
in
g
s.
I
n
tro
d
u
c
e
d
t
o
th
e
sy
ste
m
o
f
th
e
c
o
m
p
u
ter
h
a
s,
b
y
h
is u
n
c
le,
m
a
k
e
h
im
g
o
t
in
tere
ste
d
in
th
a
t.
He
w
il
l
stil
l
re
c
a
ll
t
h
e
f
e
e
li
n
g
th
a
t
h
e
h
a
d
to
lea
rn
h
o
w
m
a
c
h
in
e
s
a
p
p
li
e
d
w
it
h
in
t
h
e
c
o
m
p
u
ter,
w
h
y
it
is
n
e
e
d
e
d
,
a
n
d
w
h
a
t
th
e
c
a
p
a
b
il
it
y
it
h
a
s.
T
h
a
t
m
a
k
e
s
h
im
in
tere
ste
d
in
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
M
a
th
e
m
a
ti
c
s.
Af
ter
g
ra
d
u
a
ted
f
ro
m
h
ig
h
sc
h
o
o
l,
h
e
to
o
k
a
c
o
m
p
u
ter sc
ien
c
e
m
a
jo
r.
A
t
Bin
a
Nu
sa
n
tara
Un
iv
e
rsit
y
,
h
e
lea
rn
e
d
to
A
n
a
ly
sis
o
f
A
l
g
o
r
it
h
m
s,
Da
ta
S
tru
c
tu
re
s,
P
ro
g
ra
m
m
in
g
L
a
n
g
u
a
g
e
,
a
n
d
M
a
th
e
m
a
ti
c
s.
He
h
a
s
in
tere
ste
d
in
Da
tab
a
s
e
s
y
s
tem
s
re
lat
e
d
to
S
y
ste
m
A
n
a
l
y
sis
,
a
n
d
P
ro
g
ra
m
m
in
g
f
o
c
u
se
d
o
n
m
o
b
il
e
p
ro
g
ra
m
m
in
g
.
De
r
w
in
S
u
h
a
r
to
n
o
is
a
f
a
c
u
lt
y
m
e
m
b
e
r
o
f
Bin
a
Nu
sa
n
tara
Un
iv
e
rsit
y
,
In
d
o
n
e
sia
.
He
g
o
t
h
is
P
h
.
D.
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
f
ro
m
Un
iv
e
rsita
s
In
d
o
n
e
sia
in
2
0
1
8
.
His
re
se
a
rc
h
f
ield
s
a
r
e
n
a
tu
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
.
Re
c
e
n
tl
y
,
h
e
is
c
o
n
ti
n
u
a
ll
y
re
se
a
rc
h
in
g
a
rg
u
m
e
n
tatio
n
m
in
in
g
a
n
d
p
e
rso
n
a
li
ty
re
c
o
g
n
it
io
n
.
He
a
c
ti
v
e
l
y
in
v
o
lv
e
s
in
th
e
In
d
o
n
e
sia
A
s
so
c
iatio
n
o
f
Co
m
p
u
tatio
n
a
l
L
in
g
u
isti
c
s
(IN
A
C
L
),
a
n
a
ti
o
n
a
l
sc
ien
ti
f
ic
a
s
so
c
iatio
n
in
I
n
d
o
n
e
sia
.
He
h
a
s
h
is
p
ro
f
e
ss
io
n
a
l
m
e
m
b
e
rsh
ip
s
in
A
CM
,
INS
T
IC
C,
a
n
d
IA
C
T
.
He
a
lso
tak
e
s
th
e
ro
le
o
f
r
e
v
ie
we
r
in
se
v
e
ra
l
in
tern
a
ti
o
n
a
l
c
o
n
f
e
re
n
c
e
s a
n
d
jo
u
r
n
a
l
s.
Evaluation Warning : The document was created with Spire.PDF for Python.