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.
9
,
No
.
4
,
A
u
g
u
s
t
201
9
,
p
p
.
3
2
4
7
~3
2
5
5
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v9
i
4
.
p
p
3
2
4
7
-
3255
3247
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
Dete
c
ting th
e
m
a
g
nitude
o
f
depres
sio
n in
T
w
itt
er users using
senti
m
en
t
a
na
ly
sis
J
ini
J
o
j
o
Ste
ph
en
,
P
ra
bu
P
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
,
Ch
rist
(De
e
m
e
d
Un
iv
e
rsit
y
)
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
3
1
,
2
0
1
8
R
ev
i
s
ed
A
p
r
1
,
2
0
1
9
A
cc
ep
ted
A
p
r
1
3
,
2
0
1
9
T
o
d
a
y
th
e
d
if
f
e
r
e
n
t
so
c
ial
n
e
tw
o
rk
in
g
sites
h
a
v
e
e
n
a
b
led
e
v
e
r
y
o
n
e
to
e
a
sily
e
x
p
re
ss
a
n
d
sh
a
re
th
e
ir
f
e
e
li
n
g
s
w
it
h
p
e
o
p
le
a
ro
u
n
d
t
h
e
w
o
rld
.
A
lo
t
o
f
p
e
o
p
le
u
se
tex
t
f
o
r
c
o
m
m
u
n
ica
t
in
g
,
w
h
ich
c
a
n
b
e
d
o
n
e
t
h
ro
u
g
h
d
if
f
e
re
n
t
so
c
ial
m
e
d
ia
m
e
ss
a
g
in
g
p
latf
o
r
m
s
a
v
a
i
lab
le
to
d
a
y
su
c
h
a
s
Tw
it
ter,
F
a
c
e
b
o
o
k
e
tc,
a
s
th
e
y
fi
n
d
it
e
a
sie
r
to
e
x
p
re
ss
th
e
ir
fe
e
li
n
g
s
th
ro
u
g
h
tex
t
in
ste
a
d
o
f
sp
e
a
k
in
g
th
e
m
o
u
t.
M
a
n
y
p
e
o
p
le
w
h
o
a
lso
su
f
fe
r
f
ro
m
stre
s
s
fi
n
d
it
e
a
sie
r
to
e
x
p
re
ss
th
e
ir
f
e
e
li
n
g
s
o
n
o
n
li
n
e
p
latf
o
r
m
,
a
s
o
v
e
r
th
e
re
th
e
y
c
a
n
e
x
p
re
ss
th
e
m
se
l
v
e
s
v
e
r
y
e
a
sil
y
.
S
o
if
th
e
y
a
re
a
lert
e
d
b
e
f
o
re
h
a
n
d
,
t
h
e
re
a
re
wa
y
s
to
o
v
e
rc
o
m
e
th
e
m
e
n
tal
p
ro
b
lem
s a
n
d
stre
ss
th
e
y
a
r
e
su
ff
e
rin
g
f
ro
m
.
De
p
re
ss
io
n
sta
n
d
s
o
u
t
t
o
b
e
o
n
e
o
f
th
e
m
o
st
w
e
ll
k
n
o
w
n
m
e
n
tal
h
e
a
lt
h
d
is
o
r
d
e
rs
a
n
d
a
m
a
jo
r
issu
e
f
o
r
m
e
d
i
c
a
l
a
n
d
m
e
n
t
a
l
h
e
a
lt
h
p
ra
c
ti
ti
o
n
e
rs.
L
e
g
it
im
a
t
e
c
h
e
c
k
in
g
c
a
n
h
e
lp
in
it
s
d
isc
o
v
e
ry
,
w
h
ich
c
o
u
ld
b
e
u
se
f
u
l
to
a
n
ti
c
i
p
a
te
a
n
d
p
re
v
e
n
t
d
e
p
re
ss
io
n
a
ll
-
t
o
g
e
th
e
r.
He
n
c
e
th
e
re
is
a
n
e
e
d
f
o
r
a
s
y
ste
m
,
w
h
ich
c
a
n
c
a
ter
to
su
c
h
issu
e
s
a
n
d
h
e
l
p
th
e
u
se
r.
T
h
e
p
u
r
p
o
se
o
f
th
is
p
a
p
e
r
is
to
p
ro
p
o
se
a
n
e
ffi
c
ien
t
m
e
th
o
d
t
h
a
t
c
a
n
d
e
tec
t
th
e
lev
e
l
o
f
d
e
p
re
ss
io
n
in
T
w
i
tt
e
r
u
se
rs.
S
e
n
ti
m
e
n
t
sc
o
re
s
c
a
lcu
late
d
c
a
n
b
e
c
o
m
b
in
e
d
w
it
h
d
if
f
e
re
n
t
e
m
o
ti
o
n
s
to
p
ro
v
id
e
a
b
e
t
ter
m
e
th
o
d
to
c
a
lcu
late
d
e
p
re
ss
io
n
sc
o
re
s.
T
h
is p
ro
c
e
ss
w
il
l
h
e
lp
und
e
rsc
o
re
v
a
rio
u
s
a
sp
e
c
ts
o
f
d
e
p
re
ss
io
n
th
a
t
h
a
v
e
n
o
t
b
e
e
n
u
n
d
e
rst
o
o
d
p
re
v
io
u
sly
.
T
h
e
m
a
in
a
i
m
is
to
p
ro
v
id
e
a
se
n
se
o
f
u
n
d
e
rsta
n
d
i
n
g
re
g
a
rd
in
g
d
e
p
re
ss
io
n
lev
e
ls
in
d
if
fe
re
n
t
u
se
rs
a
n
d
h
o
w
th
e
sc
o
re
s
c
a
n
b
e
c
o
rre
late
d
to
th
e
m
a
in
d
a
ta.
K
ey
w
o
r
d
s
:
Dep
r
ess
io
n
E
m
o
tio
n
al
i
n
te
g
r
it
y
Sen
ti
m
e
n
t a
n
a
l
y
s
is
T
w
it
ter
d
ata
W
eig
h
ted
av
er
a
g
e
s
co
r
in
g
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
J
in
i J
o
jo
Step
h
en
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
C
h
r
i
s
t
(
Dee
m
ed
T
o
B
e
Un
iv
er
s
it
y
)
,
Ho
s
u
r
Ma
in
R
o
ad
,
B
an
g
alo
r
e
-
5
6
0
0
2
9
,
I
n
d
ia.
E
m
ail:
j
in
i.s
tep
h
e
n
@
c
s
.
ch
r
i
s
tu
n
iv
er
s
it
y
.
in
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
g
r
o
w
in
g
u
s
e
o
f
s
o
cial
m
ed
ia
b
y
a
m
o
r
e
s
i
g
n
i
fican
t
s
ec
to
r
o
f
s
o
ciety
s
tr
o
n
g
l
y
i
n
cr
ea
s
es
t
h
e
p
o
s
s
ib
ilit
y
o
f
u
tili
zi
n
g
th
e
in
t
er
n
et
as
a
to
o
l
to
ex
p
lo
r
e
th
e
w
o
r
ld
an
d
ex
p
r
es
s
o
n
e
’
s
o
p
i
n
io
n
s
.
A
cc
o
r
d
in
g
to
a
s
u
r
v
e
y
d
o
n
e
i
n
2
0
1
4
,
7
4
p
er
ce
n
t
1
o
f
p
eo
p
le
u
s
e
s
o
cial
n
et
w
o
r
k
i
n
g
s
ite
s
in
o
n
e
o
r
th
e
o
th
er
w
a
y
.
So
cial
n
et
w
o
r
k
in
g
s
ites
a
llo
w
u
s
er
s
to
co
m
m
u
n
icate
o
v
er
th
e
in
ter
n
e
t a
n
d
s
h
ar
e
t
h
eir
v
ie
w
s
,
id
ea
s
,
an
d
th
o
u
g
h
t
s
.
An
ess
e
n
tial
p
ar
t
o
f
o
u
r
in
f
o
r
m
at
io
n
g
at
h
er
i
n
g
b
eh
a
v
io
r
h
as
al
w
a
y
s
b
ee
n
to
d
eter
m
i
n
e
w
h
a
t
o
th
er
s
th
i
n
k
.
W
ith
t
h
e
g
r
o
w
in
g
a
v
ailab
ili
t
y
o
f
o
p
in
io
n
-
r
ic
h
s
o
u
r
ce
s
lik
e
s
o
cial
n
et
w
o
r
k
i
n
g
s
i
tes
o
r
p
er
s
o
n
al
b
lo
g
s
,
n
e
w
o
p
p
o
r
tu
n
ities
h
a
v
e
co
m
e
u
p
as
th
e
u
s
er
s
ca
n
n
o
w
d
ili
g
e
n
tl
y
u
s
e
th
e
i
n
f
o
r
m
atio
n
to
e
x
p
lo
r
e
an
d
u
n
d
er
s
tan
d
th
e
o
p
in
io
n
s
o
f
o
th
er
s
.
O
n
e
o
f
t
h
e
m
o
s
t
w
id
el
y
u
s
ed
s
o
cial
n
et
w
o
r
k
i
n
g
s
ites
is
T
w
i
tter
,
w
it
h
its
3
0
0
m
i
llio
n
u
s
er
s
2
,
T
w
i
tter
h
a
s
b
ec
o
m
e
s
u
ch
a
b
ig
p
lat
f
o
r
m
f
o
r
e
x
p
r
ess
in
g
o
n
e
’
s
v
ie
w
s
,
t
h
at
r
esear
c
h
er
s
h
a
v
e
n
o
w
b
eg
u
n
to
u
s
e
it
a
s
a
g
r
ea
t
s
o
u
r
ce
f
o
r
a
cq
u
ir
in
g
d
ata
to
d
ig
in
to
m
e
n
tal
h
ea
l
th
p
r
o
b
lem
s
.
T
h
u
s
t
h
e
tex
t
u
al
in
f
o
r
m
a
tio
n
p
o
s
ted
o
n
T
w
itter
is
b
en
e
ficial
f
o
r
s
en
ti
m
e
n
t a
n
a
l
y
s
is
.
T
h
e
s
en
ti
m
e
n
ts
ex
p
r
es
s
ed
in
th
e
t
w
ee
ts
g
i
v
es
a
n
id
ea
o
f
t
h
e
d
ee
p
er
e
m
o
tio
n
s
o
f
t
h
e
u
s
er
s
.
T
h
u
s
t
h
e
f
ee
li
n
g
s
w
h
ic
h
h
av
e
s
o
m
e
n
eg
at
iv
e
m
ea
n
i
n
g
e
x
p
r
ess
ed
in
th
e
t
w
ee
ts
m
a
y
in
d
icate
a
n
e
g
ati
v
e
e
m
o
tio
n
.
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.
9
,
No
.
4
,
A
u
g
u
s
t 2
0
1
9
:
3
2
4
7
-
3
2
5
5
3248
Sen
ti
m
e
n
t
an
al
y
s
is
o
f
T
w
itter
d
ata
is
th
e
ex
tr
ac
tio
n
o
f
e
m
o
tio
n
s
an
d
o
p
in
io
n
s
f
r
o
m
th
e
t
w
ee
t
s
p
o
s
ted
b
y
th
e
u
s
er
s
.
I
t
h
as
ac
h
ie
v
ed
m
u
ch
n
o
tice
in
th
e
r
ec
en
t
y
ea
r
s
d
u
e
to
its
s
ig
n
i
fican
ce
in
v
ar
io
u
s
ap
p
licatio
n
s
as
it
an
al
y
ze
s
s
u
c
h
e
m
o
tio
n
s
an
d
o
p
in
io
n
s
a
n
al
y
ticall
y
a
n
d
o
f
f
er
s
a
r
o
b
u
s
t
tec
h
n
o
lo
g
y
to
a
n
u
m
b
er
o
f
p
r
o
b
lem
d
o
m
ai
n
s
r
an
g
i
n
g
f
r
o
m
b
u
s
in
e
s
s
in
te
llig
e
n
ce
an
d
f
a
k
e
n
e
ws
d
etec
tio
n
,
to
an
al
y
zin
g
a
u
s
er
s
e
m
o
tio
n
al
s
tate,
d
ep
r
ess
io
n
o
r
s
tr
ess
.
T
h
e
t
w
ee
ts
h
a
v
e
s
p
ec
i
fi
c
k
e
y
w
o
r
d
s
an
d
s
en
te
n
ce
s
,
w
h
ich
ar
e
an
al
y
ze
d
to
id
en
tify
t
h
e
u
s
er
s
w
h
o
ar
e
at
h
i
g
h
r
i
s
k
o
f
h
a
v
i
n
g
d
ep
r
ess
io
n
.
T
h
e
y
h
a
v
e
a
ce
r
ta
in
k
i
n
d
o
f
attit
u
d
e
o
n
s
o
cial
m
ed
ia,
an
d
t
h
is
attit
u
d
e
ca
n
b
e
an
al
y
ze
d
b
y
s
en
t
i
m
e
n
t
an
al
y
s
is
,
i
f
t
h
e
u
s
er
s
s
e
n
ti
m
e
n
t
in
te
n
s
it
y
s
ta
y
s
a
t
lo
w
le
v
el
s
it
ca
n
d
ep
ict
th
at
t
h
e
u
s
er
h
as
s
o
m
e
d
eg
r
ee
o
f
m
e
n
tal
p
r
o
b
lem
,
in
o
t
h
er
w
o
r
d
s
,
th
e
u
s
er
h
a
s
d
ep
r
ess
io
n
.
I
n
th
is
m
atter
,
s
en
ti
m
e
n
t
an
al
y
s
is
is
v
er
y
p
o
w
er
f
u
l
es
p
ec
iall
y
w
h
en
t
h
e
u
s
er
s
ar
e
d
iag
n
o
s
ed
as
to
h
a
v
e
ce
r
tai
n
lev
el
o
f
d
ep
r
ess
io
n
.
T
w
it
ter
is
u
s
ed
a
s
a
s
o
cial
m
e
d
ia
to
o
l
f
o
r
ex
tr
ac
tio
n
o
f
d
ata
in
t
h
i
s
r
esear
c
h
,
as
t
h
e
d
ata
i
s
av
ai
lab
le
f
o
r
p
u
b
lic
an
d
th
er
e
is
a
ch
ar
ac
ter
li
m
it
o
n
th
e
t
w
ee
ts
,
w
h
ich
allo
w
s
t
h
e
u
s
er
s
to
w
r
i
te
o
n
l
y
ap
p
r
o
p
r
iate
w
o
r
d
s
in
a
b
r
ief
m
an
n
er
.
T
h
e
d
ata
h
a
s
b
ee
n
e
x
tr
ac
ted
u
s
i
n
g
th
e
t
w
itter
A
P
I
p
r
o
v
id
ed
to
t
w
itter
d
ev
e
lo
p
er
ac
co
u
n
t
s
.
P
y
th
o
n
h
as
b
ee
n
u
s
ed
to
p
ar
s
e
j
s
o
n
d
ata
ex
tr
ac
ted
f
r
o
m
t
w
i
tter
,
m
er
g
e
s
elec
ted
d
ata
an
d
p
r
o
v
id
e
a
f
o
r
m
atted
d
ata
as
a
csv
file.
R
h
a
s
b
ee
n
u
s
ed
f
o
r
b
ase
e
m
o
t
io
n
a
n
al
y
s
i
s
,
s
e
n
ti
m
en
t
ca
lc
u
latio
n
a
n
d
d
ep
r
ess
i
o
n
s
co
r
e
ca
lc
u
latio
n
.
T
h
e
d
ata
h
as b
ee
n
v
is
u
alize
d
u
s
in
g
g
g
p
lo
t in
R
w
h
ich
p
r
o
v
id
ed
a
b
etter
u
n
d
er
s
tan
d
in
g
o
f
t
h
e
fin
al
d
ata.
R
ee
ce
et
al.
[
1
]
d
ev
elo
p
ed
co
m
p
u
tat
io
n
al
m
o
d
els
to
p
r
ed
ict
th
e
d
ev
elo
p
m
en
t
o
f
d
ep
r
ess
io
n
i
n
P
o
s
t
-
T
r
au
m
atic
Stre
s
s
D
is
o
r
d
er
in
T
w
it
ter
u
s
er
s
.
T
h
e
au
t
h
o
r
s
co
llected
T
w
itter
d
ata
an
d
d
etails
o
f
d
ep
r
ess
io
n
h
i
s
to
r
y
f
r
o
m
2
0
4
in
d
i
v
id
u
a
ls
(
1
0
5
d
ep
r
ess
ed
an
d
9
9
h
ea
lt
h
y
)
an
d
e
x
tr
ac
ted
p
r
ed
ictiv
e
f
ea
t
u
r
es
m
ea
s
u
r
i
n
g
af
f
ec
t,lin
g
u
is
tic
s
t
y
le
a
n
d
t
h
e
co
n
tex
t
i
n
o
r
d
er
to
p
r
ed
ict
th
e
t
w
ee
ts
(
N=
2
7
9
,
9
5
1
)
.
T
h
en
t
h
e
y
u
s
ed
s
u
p
er
v
i
s
ed
lear
n
in
g
al
g
o
r
ith
m
s
w
it
h
all
t
h
ese
f
ea
t
u
r
es
to
b
u
ild
m
o
d
els.
E
m
er
g
ed
m
o
d
el
s
f
a
v
o
r
ab
l
y
d
if
f
er
en
tia
ted
b
et
w
ee
n
u
s
er
s
w
h
o
h
ad
p
o
s
ted
h
ea
lth
y
co
n
ten
t
a
n
d
t
h
e
u
s
er
s
w
h
o
h
a
d
co
n
ten
t,
w
h
ic
h
d
ep
icted
d
ep
r
ess
io
n
.
T
h
e
m
o
d
els
g
av
e
r
e
s
u
lts
e
v
e
n
w
h
e
n
t
h
e
a
n
al
y
s
i
s
w
as
co
n
fin
ed
to
t
h
e
t
w
ee
t
s
p
o
s
ted
e
v
en
b
e
f
o
r
e
th
e
fi
r
s
t
d
ep
r
ess
io
n
w
as
d
iag
n
o
s
ed
.
T
h
e
y
r
ep
licated
th
e
p
r
ed
ictiv
e
r
esu
lts
w
it
h
an
in
d
ep
en
d
en
t
s
a
m
p
le
o
f
u
s
er
s
d
iag
n
o
s
ed
w
it
h
P
T
SD.
T
h
e
m
et
h
o
d
s
u
s
ed
b
y
t
h
e
au
t
h
o
r
s
s
u
g
g
est
a
d
ata
-
d
r
i
v
en
p
r
ed
ictiv
e
ap
p
r
o
ac
h
f
o
r
e
ar
ly
d
e
tectio
n
o
f
d
ep
r
ess
io
n
.
Sin
g
h
et
al.
[
2
]
p
r
o
p
o
s
ed
an
ap
p
r
o
ac
h
f
o
r
an
al
y
zi
n
g
th
e
s
e
n
ti
m
e
n
ts
f
r
o
m
th
e
co
m
m
en
t
s
p
o
s
ted
o
n
s
o
cial
m
ed
ia
u
s
i
n
g
a
L
e
x
ico
n
b
ased
ap
p
r
o
ac
h
.
T
h
e
p
r
o
p
o
s
ed
a
p
p
r
o
ac
h
f
o
cu
s
ed
m
ai
n
l
y
o
n
s
u
b
j
ec
tiv
e
d
ata
ac
q
u
ir
ed
f
r
o
m
Face
b
o
o
k
.
T
h
e
au
t
h
o
r
s
’
p
r
i
m
a
r
y
f
o
cu
s
w
as
o
n
clas
s
i
f
y
i
n
g
t
h
e
co
m
m
en
ts
a
s
p
o
s
it
iv
e,
n
e
g
at
iv
e
o
r
n
eu
tr
al
w
h
ic
h
g
av
e
a
co
r
r
ec
t
m
ea
s
u
r
e
o
f
s
ta
tis
tics
o
f
li
k
es
a
n
d
d
is
li
k
es
wh
ich
ass
o
ciate
d
w
i
th
t
h
e
p
o
s
ts
.
T
h
e
p
r
o
p
o
s
ed
w
o
r
k
also
h
elp
s
i
n
s
ec
u
r
in
g
th
e
So
cial
Me
d
ia
s
ites
s
u
ch
a
s
Face
b
o
o
k
to
a
ce
r
tain
ex
te
n
t.
Sin
g
h
an
d
W
an
g
[
3
]
f
o
cu
s
o
n
p
r
ed
ictin
g
d
ep
r
ess
io
n
f
r
o
m
t
h
e
t
w
ee
t
s
o
f
a
T
w
itter
u
s
er
.
T
h
ey
cr
ea
ted
th
eir
o
w
n
d
ataset
b
y
e
x
tr
ac
ti
n
g
t
w
ee
ts
f
r
o
m
d
i
f
f
er
e
n
t
T
w
itte
r
p
ag
es
an
d
th
e
n
lab
eled
th
o
s
e
t
w
ee
t
s
w
i
t
h
th
e
h
elp
o
f
th
e
p
o
lar
it
y
s
co
r
e
o
b
tain
e
d
f
r
o
m
a
p
y
t
h
o
n
p
ac
k
a
g
e
T
ex
tb
lo
b
.
T
h
en
th
e
co
n
s
tr
u
cted
m
a
n
y
d
ee
p
lear
n
in
g
m
o
d
el
s
n
a
m
el
y
R
NN,
C
NN
a
n
d
GR
U,
w
h
ich
w
er
e
u
s
ed
to
m
ak
e
p
r
ed
ictio
n
s
o
n
th
e
d
atas
et
,
f
o
r
all
th
e
m
o
d
els
th
e
y
e
x
a
m
i
n
ed
th
e
i
m
p
ac
t
s
o
f
th
e
ch
ar
a
cter
-
b
ased
v
s
.
w
o
r
d
-
b
ased
m
o
d
els
an
d
also
t
h
e
p
r
etr
ain
ed
e
m
b
ed
d
in
g
s
v
s
.
lear
n
ed
e
m
b
ed
d
in
g
s
.
A
s
a
r
esu
lt,
th
e
y
f
o
u
n
d
th
at
t
h
e
m
o
d
el
s
,
w
h
ic
h
p
er
f
o
r
m
ed
th
e
b
est,
w
er
e
t
h
e
w
o
r
d
-
b
ased
GR
U,
w
h
ic
h
h
ad
9
8
p
er
ce
n
t a
cc
u
r
ac
y
,
an
d
th
e
w
o
r
d
-
b
ased
C
NN,
w
h
ich
h
ad
9
7
p
er
c
en
t a
cc
u
r
ac
y
.
Ak
a
y
et
al.
[
4
]
p
r
o
p
o
s
ed
a
th
r
ee
-
s
tep
m
e
th
o
d
w
h
er
ein
th
e
w
e
ig
h
ted
n
et
w
o
r
k
m
o
d
el
w
a
s
u
s
ed
to
r
ep
r
esen
t
th
e
ac
t
iv
i
tes
o
f
th
e
u
s
er
,
t
h
e
n
et
w
o
r
k
cl
u
s
ter
i
n
g
m
o
d
el
a
n
d
t
h
e
m
o
d
u
le
an
al
y
s
is
m
o
d
el
w
er
e
u
s
ed
to
ch
ar
ac
ter
ize
t
h
e
u
s
er
s
in
ter
ac
tio
n
s
o
v
er
t
h
e
w
eb
a
n
d
to
ex
tr
ac
t
f
u
r
t
h
er
i
n
f
o
r
m
atio
n
f
r
o
m
th
e
u
s
er
s
p
o
s
t
s
.
A
d
d
in
g
to
it
th
e
to
p
o
lo
g
ical
p
r
o
p
er
ties
o
f
th
e
n
et
w
o
r
k
e
m
u
late
th
e
u
s
er
s
ac
ti
v
it
ies
s
u
c
h
p
o
s
ts
to
p
ic
an
d
its
ti
m
i
n
g
,
w
h
ile
t
h
e
w
ei
g
h
ted
ed
g
es e
m
u
late
th
e
s
e
m
a
n
tic
co
n
t
en
t o
f
t
h
e
p
o
s
t a
n
d
th
e
s
i
m
ilar
i
ties
b
et
w
ee
n
t
h
e
m
.
I
s
h
tiaq
[
5
]
i
n
h
is
w
o
r
k
f
o
cu
s
ed
o
n
t
h
e
P
ar
ts
o
f
Sp
ee
c
h
(
P
OS)
tag
g
in
g
i
n
w
h
ich
th
e
p
ar
ts
o
f
s
p
ee
ch
w
er
e
r
an
k
ed
i
n
ac
co
r
d
an
ce
to
th
e
ir
s
en
ti
m
e
n
t
d
escr
ib
i
n
g
in
flu
e
n
c
e.
Sen
ti
m
e
n
t
I
n
flu
e
n
ce
r
s
w
er
e
d
ev
is
ed
f
o
r
th
e
p
ar
ts
o
f
s
p
ee
ch
an
d
w
e
r
e
r
a
n
k
ed
ac
co
r
d
in
g
to
h
o
w
th
e
y
i
n
flu
e
n
ce
th
e
d
ete
ctio
n
o
f
a
n
y
k
in
d
o
f
s
en
ti
m
en
t.
T
h
e
r
esu
l
ts
o
f
th
is
w
o
r
k
s
h
o
w
ed
th
a
t
i
f
t
h
e
P
OS
ar
e
r
an
k
ed
ap
p
r
o
p
r
iatel
y
t
h
e
n
g
o
o
d
r
esu
lts
co
u
ld
b
e
o
b
tain
ed
.
T
h
e
au
th
o
r
m
ai
n
l
y
f
o
c
u
s
ed
o
n
s
e
n
ti
m
e
n
t
ex
tr
ac
tio
n
i
n
t
h
e
f
o
r
m
o
f
p
o
s
it
iv
e
an
d
n
eg
a
tiv
e
t
w
ee
ts
u
s
in
g
a
r
u
le
b
ased
s
co
r
in
g
m
ec
h
a
n
i
s
m
w
h
er
ei
n
th
e
o
b
j
ec
tiv
e
w
as
o
n
r
an
k
in
g
t
h
e
s
e
n
ti
m
e
n
t
i
n
flu
en
ce
r
s
.
Fo
r
t
h
is
r
ea
s
o
n
,
n
o
u
n
s
,
v
er
b
s
,
ad
v
er
b
s
an
d
ad
j
ec
tiv
es
w
er
e
co
n
s
id
er
ed
as
th
e
m
ai
n
s
e
n
ti
m
en
t
in
flu
e
n
ce
r
s
.
A
ll
t
h
e
ab
o
v
e
in
flu
e
n
ce
r
s
w
er
e
ass
i
g
n
ed
s
o
m
e
s
co
r
es
an
d
r
an
k
ed
a
f
ter
a
th
o
r
o
u
g
h
u
n
d
er
s
tan
d
i
n
g
o
f
all
th
e
co
n
ce
p
t
s
.
T
h
e
r
esu
lts
o
n
th
e
p
r
o
p
o
s
ed
m
o
d
el
w
er
e
ap
p
lied
o
n
ST
SGo
ld
d
ataset
a
n
d
t
h
e
n
a
co
n
f
u
s
io
n
m
atr
i
x
w
a
s
cr
e
ated
f
o
r
th
r
ee
clas
s
es,
n
a
m
e
l
y
p
o
s
iti
v
e,
n
e
g
ati
v
e
an
d
n
eu
tr
al.
M
o
s
t
o
f
t
h
e
t
w
ee
ts
w
e
r
e
co
r
r
ec
tly
class
i
fied
b
y
t
h
e
p
r
o
p
o
s
ed
m
o
d
el.
A
ls
o
th
e
f
u
n
ctio
n
a
lit
y
o
f
t
h
e
g
i
v
e
n
m
o
d
el
w
a
s
m
ea
s
u
r
ed
f
r
o
m
p
r
ec
is
io
n
an
d
r
ec
all,
w
h
ich
w
a
s
ca
lcu
lated
f
r
o
m
t
h
e
co
n
f
u
s
io
n
m
atr
i
x
.
Nad
ee
m
et
al.
[
6
]
ex
a
m
i
n
ed
t
h
e
ab
ilit
y
o
f
s
o
cial
m
ed
ia
f
o
r
p
r
ed
ictio
n
o
f
Ma
j
o
r
Dep
r
ess
iv
e
Di
s
o
r
d
er
(
MD
D)
in
th
e
o
n
li
n
e
u
s
er
s
,
e
v
en
b
ef
o
r
e
it
b
eg
i
n
s
.
T
h
e
y
u
s
ed
a
cr
o
w
d
s
o
u
r
ce
d
m
et
h
o
d
to
co
m
p
ile
a
l
is
t
o
f
t
w
itter
u
s
er
s
w
h
o
h
a
v
e
a
ch
a
n
ce
to
b
ein
g
d
iag
n
o
s
ed
w
it
h
d
ep
r
ess
io
n
.
A
ls
o
u
s
ed
t
h
e
b
ag
o
f
wo
r
d
s
ap
p
r
o
ac
h
o
n
th
e
tw
ee
t
s
co
llected
f
r
o
m
a
w
h
o
l
e
y
ea
r
,
t
h
en
le
v
er
ag
ed
v
ar
io
u
s
s
tati
s
tical
clas
s
i
fi
er
s
to
g
iv
e
ce
r
tain
esti
m
atio
n
s
to
th
e
r
is
k
o
f
d
ep
r
ess
io
n
.
Used
D
ec
is
io
n
T
r
ee
s
,
a
L
in
ea
r
Vec
to
r
C
lass
i
fi
er
an
d
t
h
e
Nav
e
B
a
y
e
s
A
l
g
o
r
ith
m
.
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:
2
0
8
8
-
8708
Dete
ctin
g
th
e
ma
g
n
itu
d
e
o
f
d
e
p
r
ess
io
n
in
Tw
itte
r
u
s
er
s
u
s
in
g
s
en
timen
t a
n
a
lysi
s
(
Jin
i J
o
jo
S
tep
h
en
)
3249
Dev
itt
et
al.
[
7
]
p
r
o
v
id
es
a
b
asic
u
n
d
er
s
ta
n
d
i
n
g
o
f
s
e
n
ti
m
en
t
p
o
lar
it
y
id
en
ti
ficatio
n
.
T
h
ey
u
s
e
a
co
h
esio
n
-
b
ased
te
x
t
r
ep
r
esen
t
atio
n
m
e
th
o
d
u
s
ed
to
co
m
p
ar
e
n
e
w
s
s
to
r
ies
an
d
g
r
o
u
p
th
e
tex
ts
b
ased
o
n
p
o
lar
it
y
.
Her
ep
o
lar
ity
d
ir
ec
tio
n
a
n
d
in
ten
s
it
y
i
s
u
s
ed
as
an
ev
al
u
atio
n
m
etr
ic
r
elativ
e
to
t
h
e
h
u
m
a
n
d
ec
is
io
n
s
.
A
r
ef
er
e
n
ce
to
th
e
w
o
r
k
d
o
n
e
b
y
P
an
g
an
d
Vis
v
an
a
th
a
n
w
a
s
m
e
n
tio
n
ed
w
h
er
ein
t
h
e
y
w
o
r
k
ed
o
n
id
en
t
if
y
in
g
p
o
lar
it
y
b
ased
o
n
th
e
ab
s
en
ce
o
f
o
r
p
r
ee
n
s
o
f
p
ar
ticu
lar
tex
ts
.
T
h
eir
w
o
r
k
also
r
elies
o
n
p
o
lar
ity
m
ea
s
u
r
e
m
e
n
t
b
ased
o
n
th
e
lex
ico
n
o
f
p
r
etag
g
ed
p
o
s
itiv
e
an
d
n
eg
ati
v
e
ter
m
s
w
h
ich
wer
e
u
s
ed
as
r
elativ
e
p
o
s
itiv
e
an
d
n
eg
a
tiv
e
e
m
o
tio
n
d
escr
ip
to
r
.
T
h
e
in
te
n
s
it
y
w
as
m
ea
s
u
r
ed
b
ased
o
n
av
er
a
g
e
h
u
m
a
n
r
atin
g
s
f
o
r
a
s
p
ec
i
fi
c
te
x
t
an
d
a
s
s
u
c
h
t
h
i
s
w
a
s
n
o
t
al
w
a
y
s
a
li
n
ea
r
r
elatio
n
s
h
i
p
b
et
w
ee
n
a
v
er
ag
e
r
a
n
k
i
n
g
s
ca
le
an
d
t
h
e
r
ea
l
i
n
te
n
s
it
y
d
is
p
l
a
y
ed
th
r
o
u
g
h
t
h
e
te
x
t.
A
l
s
o
,
th
e
p
r
o
b
le
m
o
f
o
v
er
-
r
el
ian
ce
o
n
t
h
e
h
an
d
-
co
d
ed
lex
i
co
n
h
ad
its
co
n
s
a
s
t
h
e
y
w
o
u
l
d
b
e
in
co
n
s
i
s
ten
t
an
d
p
r
o
n
e
to
er
r
o
r
s
.
So
th
e
u
s
e
o
f
m
u
ltip
le
lex
ico
n
s
f
r
o
m
d
if
f
er
en
t
u
n
iq
u
e
s
o
u
r
ce
s
w
as
s
u
g
g
e
s
ted
s
o
t
h
at
to
g
et
h
er
u
s
i
n
g
m
u
ltip
le
le
x
ico
n
s
w
o
u
ld
in
cr
ea
s
e
th
e
b
ase
p
o
lar
it
y
v
al
u
es a
n
d
a
b
etter
m
atc
h
w
it
h
h
u
m
an
n
o
tio
n
s
.
Klen
n
er
e
.
al.
[
8
]
,
u
s
ed
an
Af
f
ec
t
L
e
x
ico
n
t
h
at
p
r
o
v
id
ed
t
h
e
p
r
io
r
p
o
lar
ity
o
f
th
e
w
o
r
d
s
.
T
h
en
a
ch
u
n
k
er
w
a
s
u
s
ed
to
d
eter
m
i
n
e
w
o
r
d
s
t
h
at
w
er
e
r
elev
an
t
to
th
e
u
s
e
i
n
co
m
p
o
s
itio
n
al
p
h
r
ase
lev
el
p
o
lar
it
y
d
eter
m
in
at
io
n
.
Her
e
n
o
t
all
t
h
e
w
o
r
d
s
i
n
th
e
s
e
n
te
n
ce
wer
e
u
s
ed
a
n
d
o
n
l
y
s
p
ec
i
fi
c
p
h
r
ases
w
er
e
u
s
ed
to
d
eter
m
in
e
th
e
fin
al
p
o
lar
it
y
.
T
h
e
m
ain
p
r
o
b
lem
id
en
ti
f
y
in
g
t
h
e
w
o
r
d
s
w
as
r
e
g
ar
d
in
g
n
eu
tr
al
w
o
r
d
s
an
d
t
h
eir
co
m
p
o
s
i
tio
n
s
.
T
h
e
co
m
p
o
s
ed
p
h
r
ase
co
u
ld
cr
ea
te
a
p
o
s
itiv
e
o
r
a
n
eg
ati
v
e
ter
m
,
w
h
ic
h
co
u
ld
b
e
o
v
er
lo
o
k
ed
b
y
th
e
m
et
h
o
d
.
T
h
e
s
e
n
ti
m
en
t
a
n
al
y
s
i
s
u
s
in
g
le
x
ico
n
s
e
n
ti
m
e
n
t
co
m
p
o
s
itio
n
p
r
o
v
id
ed
a
b
ette
r
w
a
y
to
u
n
d
er
s
ta
n
d
th
e
p
o
lar
it
y
an
d
s
e
n
ti
m
e
n
t e
v
a
lu
atio
n
g
i
v
en
p
r
io
r
p
o
lar
ity
.
Neu
m
a
n
e
t
al.
[
9
]
,
p
r
o
v
id
es
a
m
et
h
o
d
to
s
cr
ee
n
d
ep
r
ess
io
n
-
r
elate
d
w
o
r
d
s
p
r
o
ac
tiv
e
m
etap
h
o
r
ical
s
cr
ee
n
i
n
g
.
T
h
is
m
et
h
o
d
ex
tr
a
cts
m
etap
h
o
r
ical
r
ela
tio
n
s
i
n
w
h
ic
h
d
ep
r
ess
io
n
o
r
r
elev
a
n
t
s
u
b
s
et
s
o
f
t
h
i
s
ter
m
i
s
u
s
ed
an
d
ex
tr
ac
t
s
th
e
co
n
ce
p
t
u
al
d
o
m
ai
n
s
r
elati
n
g
to
it.
A
lex
ico
n
w
as
g
e
n
er
ated
u
s
i
n
g
t
h
ese
r
esu
lt
s
,
w
h
ic
h
w
as
u
s
ed
to
au
to
m
at
icall
y
e
v
al
u
at
e
th
e
lev
el
o
f
d
ep
r
ess
io
n
in
te
x
ts
o
r
w
h
et
h
er
th
e
w
h
o
le
te
x
t
d
ea
lt
w
it
h
d
ep
r
ess
io
n
o
r
n
o
t.
A
l
th
o
u
g
h
t
h
i
s
w
as
a
u
n
iq
u
e
w
a
y
,
t
h
e
d
o
m
ai
n
le
v
el
an
al
y
s
is
w
o
u
ld
p
r
o
v
e
co
s
t
l
y
a
n
d
th
e
ap
t
m
ea
s
u
r
e
o
f
d
ep
r
ess
io
n
m
a
y
n
o
t
b
e
ac
h
iev
ed
.
T
h
e
lev
el
o
f
d
ep
r
ess
io
n
w
a
s
also
n
o
t
ac
h
ie
v
ed
u
s
i
n
g
t
h
is
m
eth
o
d
as
it
w
a
s
b
ased
o
n
th
e
f
r
eq
u
e
n
c
y
o
f
w
o
r
d
s
in
th
e
te
x
t
s
,
w
h
ic
h
co
u
ld
at
ti
m
e
s
p
r
o
v
id
e
in
co
n
s
is
te
n
t r
es
u
lts
.
I
r
elan
d
an
d
Me
h
l
[
1
0
]
in
2
0
1
4
,
t
h
e
id
ea
th
at
d
ep
r
ess
ed
p
eo
p
le
ar
e
in
a
s
tate
o
f
m
o
r
e
s
el
f
-
r
efl
ec
t
io
n
a
n
d
ten
d
to
f
o
cu
s
o
n
th
e
m
s
el
v
es a
n
d
tal
k
ab
o
u
t
th
e
m
s
elv
e
s
f
r
eq
u
en
t
l
y
ev
e
n
d
u
r
in
g
a
co
n
v
er
s
a
tio
n
h
as b
ee
n
f
o
u
n
d
b
y
o
th
er
au
t
h
o
r
s
.
Usi
n
g
t
h
is
m
et
h
o
d
s
in
g
u
lar
fi
r
s
t
p
er
s
o
n
p
r
o
n
o
u
n
s
w
er
e
ev
al
u
ated
i
n
te
x
t
t
r
an
s
cr
ip
ts
a
n
d
it
w
as
f
o
u
n
d
th
at
th
er
e
w
a
s
i
n
d
ee
d
a
co
r
r
elatio
n
b
et
w
ee
n
m
o
r
e
f
r
eq
u
en
t
u
s
e
o
f
fi
r
s
t
o
f
s
in
g
u
lar
fi
r
s
t
-
p
er
s
o
n
p
r
o
n
o
u
n
s
w
h
e
n
p
eo
p
le
ar
e
d
ep
r
ess
ed
.
T
h
e
m
ain
a
n
al
y
s
i
s
to
n
o
te
w
as
t
h
at
th
i
s
ef
f
ec
t
w
as
co
m
m
o
n
a
m
o
n
g
all
d
em
o
g
r
ap
h
ics
i
n
clu
d
i
n
g
a
g
e
an
d
g
e
n
d
er
.
B
u
t
th
e
u
s
e
o
f
s
i
n
g
u
lar
fi
r
s
t
p
er
s
o
n
p
r
o
n
o
u
n
s
co
u
ld
o
n
l
y
tel
l
to
a
n
ex
ten
t
t
h
at
t
h
e
p
er
s
o
n
w
as
f
e
elin
g
d
ep
r
ess
ed
,
i.
e.
t
h
e
s
e
n
te
n
ce
w
o
u
ld
b
e
a
n
e
g
ati
v
e
p
o
la
r
it
y
s
e
n
te
n
ce
,
b
u
t
t
h
e
lev
el
o
r
in
te
n
s
it
y
o
f
t
h
e
p
o
lar
ity
w
as
n
o
t d
is
cu
s
s
ed
.
B
er
en
g
u
er
es
a
n
d
C
astro
[
1
1
]
in
th
eir
p
ap
er
h
av
e
in
tr
o
d
u
ce
d
an
au
th
o
r
s
en
t
i
m
e
n
t
b
en
c
h
m
a
r
k
o
f
e
m
o
j
i
an
d
h
a
v
e
co
m
p
ar
ed
it
w
it
h
a
w
r
iter
s
e
n
ti
m
e
n
t
b
en
c
h
m
ar
k
.
T
h
ey
f
o
u
n
d
th
a
t
r
ea
d
er
s
an
d
w
r
iter
s
s
ee
m
to
b
r
o
ad
ly
ag
r
ee
o
n
t
h
e
s
e
n
ti
m
e
n
t
o
f
e
m
o
j
i
(
8
4
p
er
ce
n
t)
ev
en
t
h
o
u
g
h
t
h
e
r
ea
d
er
’
s
s
o
u
r
ce
o
f
co
m
m
en
t
s
w
er
e
t
w
ee
ts
a
n
d
t
h
e
w
r
iter
’
s
s
o
u
r
ce
o
f
co
m
m
en
t
s
w
a
s
an
an
o
n
y
m
o
u
s
w
o
r
k
-
h
ap
p
in
ess
m
o
n
i
to
r
in
g
ap
p
w
h
er
e
co
m
m
e
n
t
s
r
ef
er
ed
t
o
w
o
r
k
s
u
g
g
esti
o
n
s
.
T
h
e
lar
g
est
d
is
ag
r
ee
m
e
n
t
b
et
w
ee
n
r
ea
d
er
s
an
d
w
r
i
ter
s
o
cc
u
r
r
ed
f
o
r
n
eg
ativ
e
e
m
o
j
i
(
s
ad
f
ac
e
an
d
p
o
u
tin
g
f
ac
e
)
.
Fo
r
th
i
s
g
r
o
u
p
o
f
e
m
o
j
i,
th
e
au
th
o
r
s
r
ep
o
r
t
f
ee
lin
g
2
6
p
er
ce
n
t
w
o
r
s
e
th
a
n
w
h
a
t
r
ea
d
er
s
p
er
ce
iv
e
in
ter
m
s
o
f
s
ta
n
d
ar
d
d
ev
iatio
n
.
E
m
o
j
i u
s
e
w
as
n
o
t f
o
u
n
d
to
b
e
co
r
r
elate
d
w
i
th
a
u
t
h
o
r
m
o
o
d
in
es
s
.
I
t
w
a
s
f
o
u
n
d
to
b
e
co
r
r
elate
d
w
it
h
m
o
r
e
h
ap
p
in
ess
w
it
h
in
u
s
er
s
a
n
d
b
et
w
ee
n
u
s
er
s
.
T
h
eir
r
esear
ch
s
ee
m
s
to
i
m
p
r
o
v
e
th
e
ac
cu
r
ac
y
o
f
s
e
n
ti
m
e
n
t e
s
ti
m
atio
n
o
f
au
t
h
o
r
s
an
d
w
r
iter
s
o
f
w
h
e
n
e
m
o
j
is
ar
e
u
s
ed
.
T
h
e
E
v
o
lu
tio
n
o
f
Sen
ti
m
e
n
t
An
al
y
s
i
s
[
1
2
]
,
i
n
th
is
ar
ticle,
th
e
a
u
t
h
o
r
s
p
r
ese
n
ted
a
co
m
p
u
ter
-
a
s
s
i
s
ted
liter
atu
r
e
r
ev
ie
w
,
u
s
i
n
g
au
to
m
ated
tex
t
cl
u
s
ter
in
g
w
i
th
m
an
u
al
q
u
a
litati
v
e
a
n
al
y
s
i
s
,
an
d
a
b
ib
lio
m
etr
ic
s
t
u
d
y
o
f
s
en
ti
m
e
n
t
a
n
al
y
s
i
s
o
f
6
,
9
9
6
p
ap
er
s
.
T
h
e
y
i
n
v
e
s
ti
g
ated
t
h
e
h
is
to
r
y
o
f
s
e
n
ti
m
en
t
an
al
y
s
is
a
n
d
ev
al
u
ated
t
h
e
i
m
p
ac
t o
f
s
e
n
ti
m
e
n
t a
n
al
y
s
i
s
a
n
d
its
tr
en
d
s
th
r
o
u
g
h
a
ci
tatio
n
an
d
b
ib
lio
m
etr
ic
s
t
u
d
y
,
d
eli
m
ited
th
e
co
m
m
u
n
itie
s
o
f
s
e
n
ti
m
e
n
t
a
n
al
y
s
i
s
b
y
fin
d
in
g
t
h
e
m
o
s
t
p
o
p
u
lar
p
u
b
licat
io
n
v
en
u
e,
d
is
co
v
er
ed
w
h
ic
h
r
esear
ch
to
p
ics
h
a
v
e
b
ee
n
in
v
est
ig
ated
i
n
s
e
n
t
i
m
e
n
t
an
al
y
s
i
s
,
an
d
r
ev
ie
w
ed
th
e
m
o
s
t
cited
o
r
ig
i
n
al
w
o
r
k
s
a
n
d
liter
atu
r
e
r
ev
ie
w
s
i
n
s
en
ti
m
e
n
t a
n
al
y
s
is
.
To
E
d
w
ar
d
s
an
d
Ho
ltz
m
a
n
[
1
3
]
th
e
au
t
h
o
r
s
h
av
e
cle
ar
i
m
p
licatio
n
s
f
o
r
th
eo
r
y
,
id
en
ti
fi
ca
tio
n
,
ass
es
s
m
en
t,
a
n
d
tr
ea
t
m
en
t.
I
n
ter
m
s
o
f
t
h
eo
r
y
,
t
h
e
n
o
tio
n
t
h
at
s
e
lf
-
f
o
cu
s
es
ar
e
ce
n
tr
al
to
d
ep
r
ess
io
n
r
ec
eiv
e
s
s
o
m
e
m
o
d
es
t
s
u
p
p
o
r
t.
I
n
ter
m
s
o
f
id
en
ti
ficatio
n
a
n
d
ass
e
s
s
m
en
t,
th
e
y
co
n
cl
u
d
e
th
at
i
n
d
e
ed
fi
r
s
t
p
er
s
o
n
s
in
g
u
lar
p
r
o
n
o
u
n
s
ar
e
a
m
o
d
est
lin
g
u
is
tic
m
ar
k
er
o
f
d
ep
r
ess
io
n
.
I
n
ter
m
s
o
f
tr
ea
t
m
en
t,
th
e
ir
m
eta
-
an
a
l
y
s
is
p
r
o
v
id
es
co
n
fi
d
en
ce
in
t
h
e
esti
m
ate
o
f
th
e
ef
f
ec
t
s
ize,
s
u
c
h
th
at
c
u
tti
n
g
-
ed
g
e
r
esear
ch
o
n
lin
g
u
is
tic
s
tr
ateg
ies
to
co
p
e
w
it
h
d
ep
r
ess
io
n
ar
e
m
o
r
e
in
f
o
r
m
e
d
(
Kr
o
s
s
&
Ay
d
u
k
,
2
0
0
8
,
2
0
1
1
;
Kr
o
s
s
et
al.
,
2
0
1
4
;
Z
i
m
m
er
m
an
n
et
al.
,
2
0
1
6
)
.
T
h
eir
r
esear
ch
co
n
tr
ib
u
t
es to
d
ep
r
ess
io
n
f
o
r
b
ein
g
b
etter
u
n
d
er
s
to
o
d
,
id
en
tifi
ed
,
ass
e
s
s
ed
,
a
n
d
tr
ea
ted
.
R
o
s
a
et
al.
[
1
4
]
f
o
u
n
d
th
at
s
en
ti
m
e
n
t
an
al
y
s
i
s
ca
n
h
elp
m
o
n
ito
r
a
p
er
s
o
n
’
s
m
o
o
d
.
P
eo
p
le
w
it
h
s
y
m
p
to
m
s
o
f
d
ep
r
ess
io
n
h
a
v
e
s
i
m
ilar
b
eh
av
io
r
th
at
ca
n
b
e
ex
p
r
ess
ed
in
th
e
p
h
r
ases
p
o
s
t
ed
in
s
o
cial
n
et
w
o
r
k
s
.
T
h
u
s
t
h
i
s
u
s
e
f
u
l
i
n
f
o
r
m
atio
n
h
elp
s
d
eter
m
i
n
e
th
e
u
s
er
s
w
h
o
h
av
e
p
o
ten
tial
p
s
y
ch
o
lo
g
ical
d
i
s
t
u
r
b
s
s
u
c
h
a
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.
9
,
No
.
4
,
A
u
g
u
s
t 2
0
1
9
:
3
2
4
7
-
3
2
5
5
3250
d
ep
r
ess
io
n
.
A
ls
o
,
a
u
t
h
o
r
ized
p
er
s
o
n
s
,
r
elati
v
e
s
,
an
d
m
e
d
ical
s
ta
f
f
ca
n
h
av
e
ac
ce
s
s
to
th
is
in
f
o
r
m
at
io
n
.
T
h
e
p
r
o
p
o
s
ed
s
o
lu
ti
o
n
in
th
ei
r
r
esear
ch
atte
n
d
s
all
th
e
s
e
c
o
n
s
id
er
atio
n
s
.
I
t
s
tate
s
t
h
at
a
r
ec
o
m
m
e
n
d
er
s
y
s
te
m
b
ased
o
n
th
e
p
er
s
o
n
’
s
m
o
o
d
ca
n
b
e
i
m
p
le
m
e
n
ted
to
i
m
p
r
o
v
e
th
e
e
m
o
tio
n
al
s
tate
o
f
t
h
e
u
s
er
s
id
en
ti
fi
ed
w
ith
d
ep
r
ess
io
n
s
y
m
p
to
m
s
.
Z
u
cc
o
et
al
.
[
1
5
]
p
r
esen
ted
a
p
r
eli
m
in
a
r
y
d
esi
g
n
o
f
a
n
i
n
teg
r
ated
m
u
lt
i
m
o
d
al
s
y
s
te
m
b
a
s
e
d
o
n
S
A
an
d
AC
m
eth
o
d
o
lo
g
ies
f
o
r
d
ep
r
ess
io
n
co
n
d
itio
n
s
m
o
n
ito
r
i
n
g
.
S
p
ec
icall
y
,
th
e
p
ap
er
d
escr
ib
ed
th
e
m
a
in
s
tep
s
o
f
S
A
an
d
A
C
an
al
y
s
is
p
ip
eli
n
es
a
n
d
d
is
c
u
s
s
ed
th
e
m
ai
n
c
h
alle
n
g
e
s
i
n
t
h
e
d
es
ig
n
a
n
d
i
m
p
l
e
m
en
t
atio
n
o
f
s
u
c
h
a
s
y
s
te
m
.
Fu
t
u
r
e
w
o
r
k
s
w
i
ll p
r
esen
t t
h
e
n
a
l s
y
s
te
m
an
d
t
h
e
r
es
u
lts
te
s
ti
n
g
a
n
d
v
alid
atio
n
.
Gr
atch
et
al.
[
1
6
]
,
c
o
n
d
u
cte
d
s
ev
er
al
clin
ical
in
ter
v
ie
w
s
d
esig
n
ed
to
s
u
p
p
o
r
t
th
e
p
s
y
ch
o
lo
g
ical
co
n
d
itio
n
.
T
h
ese
in
ter
v
ie
w
s
wer
e
co
n
d
u
cted
b
y
h
u
m
a
n
s
a
s
w
ell
as
b
y
an
a
g
en
t
n
a
m
ed
E
ll
ie.
T
h
is
d
ata
h
as
b
ee
n
tr
an
s
cr
ib
ed
an
d
is
b
ein
g
u
s
ed
in
th
i
s
r
esear
ch
.
T
h
e
tr
an
s
cr
ib
ed
d
ata
h
as
p
r
o
v
id
ed
a
lis
t
o
f
w
o
r
d
s
w
ith
t
h
e
ter
m
f
r
eq
u
en
c
y
w
h
ich
tell
s
u
s
w
h
ic
h
w
o
r
d
s
t
h
e
u
s
er
s
u
s
ed
m
o
r
e.
T
h
e
y
al
s
o
u
s
ed
m
u
ltip
le
c
lin
i
ca
l
m
e
th
o
d
s
lik
e
t
h
e
u
s
e
o
f
s
e
n
s
o
r
s
,
r
e
s
p
ir
atio
n
o
f
th
e
p
atie
n
ts
an
d
E
lectr
o
C
ar
d
io
Gr
am
to
d
eter
m
i
n
e
t
h
e
e
m
o
tio
n
al
s
tate
o
f
t
h
e
p
er
s
o
n
.
A
d
d
itio
n
all
y
,
th
e
a
u
to
m
ated
ag
e
n
ts
w
er
e
ab
le
to
g
en
er
ate
lo
g
s
o
f
t
h
e
u
s
er
’
s
s
p
ee
ch
an
d
p
r
o
v
id
e
r
ea
l
-
ti
m
e
r
ec
o
g
n
itio
n
o
f
th
e
u
s
er
’
s
v
o
ice
p
atter
n
an
d
th
e
u
s
e
o
f
r
ep
etitiv
e
w
o
r
d
s
.
I
t
w
as
f
o
u
n
d
th
at
th
e
p
eo
p
le
d
is
p
la
y
ed
e
m
o
tio
n
s
m
o
r
e
in
te
n
s
el
y
w
h
e
n
i
n
ter
ac
ti
n
g
w
it
h
a
co
m
p
u
ter
co
m
p
ar
ed
to
a
h
u
m
a
n
.
T
h
is
tr
an
s
cr
ip
t
g
en
er
ated
t
h
r
o
u
g
h
t
h
ese
in
ter
v
ie
w
s
w
ill
b
e
u
s
ed
in
th
e
c
u
r
r
en
t
r
ese
ar
ch
.
A
lt
h
o
u
g
h
th
is
h
as
b
ee
n
u
s
ed
an
d
in
v
e
s
ti
g
ated
in
t
h
e
p
ast,
u
s
i
n
g
a
n
e
w
m
et
h
o
d
to
id
en
tify
t
h
e
w
o
r
d
s
it
w
o
u
ld
b
e
p
o
s
s
ib
le
to
av
o
id
th
e
m
aj
o
r
h
in
d
r
a
n
ce
s
t
h
at
d
o
es n
o
t a
llo
w
f
o
r
th
e
m
ea
s
u
r
e
m
e
n
t o
f
t
h
e
e
m
o
tio
n
al
i
n
te
n
s
i
t
y
o
f
t
h
e
u
s
er
.
Sali
m
a
th
et
al.
[
1
7
]
p
r
o
p
o
s
ed
a
m
et
h
o
d
f
o
r
s
e
n
ti
m
e
n
t
an
al
y
s
i
s
o
f
t
h
e
co
n
v
er
s
ati
o
n
w
it
h
1
8
9
p
ar
ticip
an
ts
.
T
h
e
d
ataset
co
n
s
i
s
ted
o
f
v
o
ice
r
ec
o
r
d
in
g
s
,
f
ac
ia
l
ex
p
r
ess
io
n
s
,
an
d
t
h
e
tex
t.
W
h
at
t
h
e
y
d
id
w
as
t
h
at
th
e
y
m
ai
n
l
y
f
o
cu
s
ed
o
n
class
i
f
y
in
g
t
h
e
co
n
v
er
s
a
tio
n
s
b
elo
n
g
in
g
to
p
atie
n
t
s
as
p
o
s
itiv
e,
n
eg
ativ
e
o
r
n
eu
tr
al,
th
u
s
p
r
o
v
id
in
g
t
h
e
ac
tu
a
l stati
s
tics
o
f
lik
e
s
an
d
d
i
s
li
k
es r
elate
d
to
a
d
is
cu
s
s
io
n
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
I
n
a
lar
g
e
p
o
r
tio
n
o
f
t
h
e
r
esear
ch
,
w
h
ich
h
a
s
b
ee
n
d
o
n
e
s
o
f
a
r
,
f
o
r
Dep
r
ess
io
n
,
o
n
e
r
e
g
u
lar
th
i
n
g
a
m
o
n
g
all,
w
a
s
t
h
at
t
h
e
r
esear
c
h
er
s
u
tili
ze
d
th
e
i
n
f
o
r
m
atio
n
f
r
o
m
c
o
n
s
tr
ain
ed
s
o
u
r
ce
s
,
f
o
r
ex
a
m
p
le,
o
n
lin
e
g
at
h
er
i
n
g
s
an
d
d
id
n
o
t
u
t
ilize
e
v
er
y
w
o
r
d
w
h
ic
h
w
as
g
i
v
e
n
i
n
th
e
co
n
te
n
t.
T
h
is
b
r
o
u
g
h
t a
b
o
u
t
h
al
f
lea
r
n
in
g
a
n
d
le
s
s
p
r
ec
is
e
p
r
esen
ce
o
f
s
o
m
e
s
o
r
t
o
f
d
ep
r
ess
io
n
in
t
h
e
p
atie
n
t
s
.
T
o
d
ef
ea
t
th
i
s
it
i
s
r
eq
u
ir
ed
t
h
at
ap
p
r
o
p
r
iate
co
n
ten
t
m
i
n
i
n
g
s
tr
ateg
ie
s
o
u
g
h
t
to
b
e
u
tili
ze
d
an
d
s
u
ch
m
et
h
o
d
o
lo
g
ies
o
u
g
h
t
to
b
e
u
tili
ze
d
w
h
ic
h
ca
n
d
i
s
s
ec
t
fin
is
h
w
o
r
d
s
in
s
en
te
n
ce
s
a
n
d
s
cr
ee
n
t
h
e
p
r
esen
ce
o
f
d
ep
r
ess
io
n
i
n
th
o
s
e.
T
h
e
r
esear
ch
p
r
o
b
lem
th
at
w
i
l
l
b
e
in
v
esti
g
ated
as
p
ar
t
o
f
th
is
r
esear
ch
is
“
Do
e
s
th
er
e
ex
is
t
a
m
et
h
o
d
t
o
ev
alu
a
te
t
h
e
m
ag
n
it
u
d
e
o
f
d
ep
r
ess
io
n
in
a
p
er
s
o
n
b
as
ed
o
n
th
e
e
m
o
tio
n
al
i
n
te
g
r
i
t
y
o
f
t
h
eir
t
w
ee
t
s
”.
T
o
an
s
w
er
t
h
is
q
u
esti
o
n
,
d
if
f
e
r
en
t
e
m
o
tio
n
s
w
i
ll
b
e
ev
al
u
ate
d
an
d
a
w
ei
g
h
ted
s
co
r
e
w
ill
b
e
ca
lcu
lated
f
o
r
ea
ch
t
w
ee
t
w
h
ic
h
w
i
ll
b
e
a
v
er
ag
ed
o
u
t
f
o
r
a
s
i
n
g
le
d
a
y
,
th
er
eb
y
g
e
n
er
atin
g
th
e
fin
al
s
co
r
e
o
r
m
a
g
n
it
u
d
e.
A
ls
o
th
e
co
r
r
elatio
n
b
et
w
ee
n
th
e
t
w
it
ter
t
w
ee
ts
an
d
th
e
m
ag
n
it
u
d
e
w
ill
b
e
ex
p
lo
r
e
d
to
u
n
d
er
s
tan
d
d
ep
r
ess
io
n
i
n
a
b
etter
f
ash
io
n
.
T
h
e
p
r
im
ar
y
g
o
al
o
f
th
i
s
p
ap
er
is
to
p
r
o
v
id
e
a
s
y
s
te
m
w
h
ich
ca
n
ch
ec
k
f
o
r
d
ep
r
ess
io
n
in
t
w
itter
u
s
er
s
b
ased
o
n
th
eir
t
w
ee
ts
f
o
r
th
e
p
ast
f
e
w
m
o
n
t
h
s
.
I
n
t
h
is
s
ec
t
io
n
w
e
w
ill
d
is
c
u
s
s
h
o
w
th
e
d
ata
h
as
b
ee
n
p
r
o
d
u
ce
d
an
d
h
o
w
th
e
d
ep
r
ess
io
n
lev
el
s
ar
e
m
ea
s
u
r
ed
f
o
r
th
e
u
s
er
s
.
Fig
u
r
e
1
.
Me
th
o
d
o
lo
g
y
o
v
er
v
i
e
w
2
.
1
.
B
uil
din
g
c
o
rpus
I
n
o
r
d
er
to
an
s
w
er
t
h
e
r
esear
ch
q
u
e
s
tio
n
s
w
e
n
ee
d
ed
to
f
e
tch
t
h
e
d
ata
f
o
r
s
p
ec
i
fi
c
u
s
er
s
w
h
o
ca
n
b
e
id
en
ti
fi
ed
as
d
ep
r
ess
ed
,
s
o
a
f
e
w
k
e
y
w
o
r
d
s
w
er
e
u
s
ed
to
f
et
ch
a
li
s
t
o
f
u
s
er
s
w
h
o
h
ad
u
s
e
d
tag
s
s
u
ch
a
s
#
ab
u
s
e,
#
an
x
iet
y
,
#
ad
d
ict,
#
ad
d
ictio
n
,
an
d
#
b
u
ll
y
i
n
g
.
Usi
n
g
th
e
s
e
t
ag
s
a
li
s
t
o
f
u
s
er
s
w
as
c
u
r
ate
d
an
d
th
e
t
w
it
ter
A
P
I
w
a
s
u
s
ed
to
f
etc
h
t
h
e
d
ata
f
r
o
m
t
h
e
s
i
te.
A
r
estrictio
n
o
f
3
2
0
0
t
w
ee
ts
in
cl
u
d
i
n
g
r
et
w
ee
ts
,
v
id
eo
s
etc
h
as
b
ee
n
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:
2
0
8
8
-
8708
Dete
ctin
g
th
e
ma
g
n
itu
d
e
o
f
d
e
p
r
ess
io
n
in
Tw
itte
r
u
s
er
s
u
s
in
g
s
en
timen
t a
n
a
lysi
s
(
Jin
i J
o
jo
S
tep
h
en
)
3251
p
lace
d
o
n
b
y
t
w
it
ter
.
T
h
e
t
w
i
tter
d
ata
h
as
b
ee
n
co
m
p
iled
f
o
r
5
2
u
s
er
s
w
it
h
ea
ch
u
s
er
d
ata
av
er
ag
i
n
g
ar
o
u
n
d
2
0
0
0
t
w
ee
ts
.
T
h
e
d
ata
h
as
b
ee
n
f
u
r
t
h
er
s
eg
r
e
g
ated
p
er
d
ay
s
o
t
h
at
th
e
v
ar
iatio
n
s
f
o
r
d
e
p
r
ess
io
n
ca
n
b
e
u
n
d
er
s
to
o
d
.
2
.
2
.
Da
t
a
pre
-
pro
c
ess
ing
T
h
e
d
ata
ex
tr
ac
ted
w
h
ic
h
w
a
s
r
a
w
d
ata
in
j
s
o
n
f
o
r
m
at
an
d
was
i
n
co
m
p
atib
le
f
o
r
u
s
e
w
i
th
o
u
r
p
r
o
g
r
a
m
,
s
o
d
ata
p
r
ep
r
o
ce
s
s
in
g
w
a
s
i
m
p
le
m
e
n
ted
in
t
h
r
ee
s
ta
g
es.
Fil
e
C
o
n
v
er
s
io
n
:
T
h
e
j
s
o
n
d
ata
in
u
tf
-
8
e
n
co
d
in
g
w
a
s
fi
r
s
t
c
o
n
v
er
ted
to
ASC
I
I
,
s
o
as
to
r
e
m
o
v
e
all
Un
ico
d
e
s
p
ec
ial
s
y
m
b
o
ls
w
h
ic
h
w
o
u
ld
b
e
o
f
n
o
u
s
e
f
o
r
th
e
p
u
r
p
o
s
e
o
f
d
ep
r
ess
io
n
a
n
al
y
s
i
s
.
T
h
is
d
ata
w
a
s
th
e
n
p
ar
s
ed
an
d
o
n
l
y
t
h
e
k
e
y
s
w
i
th
v
alu
e
t
w
ee
t
-
tex
t,
t
w
ee
t
-
d
ate
,
u
s
er
,
t
w
ee
t
-
t
y
p
e,
lo
ca
tio
n
w
er
e
s
elec
ted
.
T
h
e
p
ar
s
ed
d
ata
w
as t
h
en
s
av
e
d
in
th
e
f
o
r
m
o
f
a
co
m
m
a
s
ep
a
r
ated
fi
le
(
cs
v
)
f
o
r
ea
s
y
a
n
al
y
s
is
o
f
t
h
e
d
ata.
Data
C
lean
i
n
g
:
T
h
e
fin
al
d
ata
f
r
o
m
th
e
last
s
tep
co
n
tain
e
d
d
ata
in
A
SC
I
I
en
co
d
in
g
w
i
th
a
lo
t
o
f
tex
t
in
g
ib
b
er
is
h
as
th
e
U
n
ico
d
e
co
n
v
er
ted
s
p
ec
ial
s
y
m
b
o
ls
in
t
h
e
t
w
ee
t
w
er
e
co
n
v
er
ted
to
ASC
I
I
.
D
i
f
f
er
en
t
s
y
m
b
o
ls
lik
e
e
x
cla
m
atio
n
m
a
r
k
s
,
p
u
n
ct
u
atio
n
s
,
d
ig
it
s
,
s
p
ec
ial
ch
ar
ac
ter
s
etc
w
er
e
r
e
m
o
v
ed
.
A
f
ter
th
ese
v
alu
e
s
w
er
e
r
e
m
o
v
ed
it
w
a
s
v
is
ib
le
t
h
at
s
o
m
e
t
w
ee
t
s
p
r
o
d
u
ce
d
n
u
ll
v
a
lu
e
s
,
w
h
ic
h
w
er
e
o
m
itted
.
Als
o
th
e
tex
t
f
o
r
m
atti
n
g
w
as a
ls
o
r
e
m
o
v
ed
d
u
r
in
g
t
h
is
s
tep
a
n
d
all
w
o
r
d
s
w
er
e
co
n
v
er
ted
to
s
m
all
ca
s
e
letter
s
.
Sto
p
W
o
r
d
R
em
o
v
al
:
T
h
e
T
M
lib
r
ar
y
w
a
s
u
s
ed
f
o
r
th
i
s
p
u
r
p
o
s
e.
T
M
lib
r
a
r
y
p
r
o
v
id
es
a
d
ic
tio
n
ar
y
w
i
th
s
to
p
w
o
r
d
s
,
w
h
ic
h
ar
e
m
o
s
t
f
r
eq
u
e
n
tl
y
u
s
ed
w
o
r
d
s
.
As
th
e
d
eleti
o
n
o
f
all
s
to
p
w
o
r
d
s
w
o
u
ld
r
en
d
er
th
e
d
ep
r
ess
io
n
an
al
y
s
is
u
s
eles
s
,
a
j
o
in
w
as
p
er
f
o
r
m
ed
o
n
t
h
e
s
to
p
w
o
r
d
d
ictio
n
ar
y
a
n
d
a
lis
t
o
f
p
o
s
iti
v
e
w
o
r
d
s
c
u
r
ated
b
y
Min
q
in
g
H
u
an
d
B
i
n
g
L
i
u
(
in
s
er
t
citatio
n
h
ttp
://
www
.
c
s
.
u
ic.
ed
u
/li
u
b
/FB
S/s
e
n
ti
m
en
tan
al
y
s
is
.
h
t
m
l
).
Usi
n
g
t
h
e
j
o
in
r
e
m
o
v
ed
o
n
l
y
t
h
e
p
o
s
iti
v
e
s
to
p
w
o
r
d
s
an
d
r
et
ain
ed
th
e
o
t
h
er
s
w
h
ic
h
co
u
ld
b
e
f
u
r
t
h
e
r
u
s
ed
f
o
r
d
ep
r
ess
io
n
an
al
y
s
i
s
.
2
.
3
.
Depre
s
s
io
n
m
a
g
nitu
de
c
a
lcula
t
io
n
B
ase
e
m
o
tio
n
ca
lcu
la
tio
n
:
U
s
i
n
g
t
h
e
s
y
u
z
h
et
p
ac
k
a
g
e,
b
ase
e
m
o
tio
n
s
w
er
e
ca
lc
u
lated
f
o
r
ea
ch
t
w
ee
t
an
d
a
lis
t
o
f
eig
h
t
e
m
o
tio
n
s
w
er
e
r
ea
lized
.
T
h
e
em
o
tio
n
s
ca
lc
u
lated
in
cl
u
d
ed
an
g
er
,
an
ticip
atio
n
,
d
is
g
u
s
t,
f
ea
r
,
j
o
y
,
s
ad
n
es
s
,
s
u
r
p
r
is
e
an
d
tr
u
s
t.
T
h
e
r
esu
ltin
g
lis
t
o
f
t
h
ese
e
m
o
tio
n
s
s
h
o
w
ed
h
o
w
th
e
s
e
e
m
o
tio
n
s
h
ad
b
ee
n
r
ep
r
esen
ted
in
t
h
e
t
w
ee
t.
A
ls
o
t
h
e
b
asic
s
e
n
ti
m
e
n
t
o
f
t
h
e
t
wee
t
w
a
s
also
an
al
y
ze
d
,
w
h
e
th
e
r
it
w
as
a
p
o
s
iti
v
e
t
w
ee
t o
r
a
n
e
g
ati
v
e
o
n
e.
Sen
ti
m
e
n
t
s
co
r
e
ev
a
lu
at
io
n
:
T
h
e
t
w
ee
ts
w
er
e
to
k
e
n
ized
as
b
ig
r
a
m
s
a
n
d
tr
ig
r
a
m
s
to
f
u
r
th
er
an
al
y
ze
t
h
e
s
en
ti
m
e
n
t
s
co
r
es
f
o
r
t
h
e
t
w
ee
t
s
.
T
h
r
ee
d
if
f
er
e
n
t
le
x
ico
n
s
w
e
r
e
u
s
ed
f
o
r
s
en
ti
m
en
t
an
al
y
s
is
f
o
r
th
e
to
k
e
n
ized
w
o
r
d
s
n
a
m
el
y
,
A
FIN
N,
B
I
N
G
an
d
NR
C
.
A
ll
t
h
r
ee
p
r
o
v
id
e
a
d
if
f
er
en
t
m
a
g
n
it
u
d
e
o
f
s
en
ti
m
e
n
t
s
co
r
e.
As
t
h
e
t
w
ee
t
s
h
av
e
b
ee
n
cr
ea
t
ed
as
ch
u
n
k
s
b
ased
o
n
t
h
e
d
at
e,
s
o
ea
ch
d
a
y
r
ep
r
esen
ts
a
b
u
n
ch
o
f
t
w
ee
ts
a
n
d
it
v
ar
ies
co
n
s
id
er
ab
l
y
b
ased
o
n
u
s
er
.
E
ac
h
lex
ico
n
p
r
o
v
id
es
th
e
fin
al
s
e
n
ti
m
e
n
t
s
co
r
e
in
v
a
r
y
in
g
m
ag
n
it
u
d
es
w
h
ic
h
w
ill
b
e
d
if
fi
c
u
lt
to
an
a
l
y
ze
,
s
o
th
e
v
a
lu
e
s
w
er
e
n
o
r
m
alize
d
ar
o
u
n
d
-
1
to
+1
an
d
th
en
a
v
er
ag
ed
to
ca
lcu
late
a
fin
al
s
e
n
ti
m
e
n
t sco
r
e
f
o
r
a
b
u
n
ch
o
f
t
w
ee
ts
f
o
r
a
s
p
ec
ifi
c
u
s
er
.
Fig
u
r
e
2
.
B
ase
em
o
tio
n
v
al
u
es
Fig
u
r
e
3
.
Fin
al
s
e
n
ti
m
e
n
t sco
r
e
ev
alu
at
io
n
W
eig
h
ted
Av
er
a
g
e
Sco
r
e
a
n
d
Fin
al
Dep
r
ess
io
n
Ma
g
n
it
u
d
e:
C
er
tai
n
w
ei
g
h
ts
w
er
e
o
b
tain
ed
f
o
r
ea
c
h
e
m
o
tio
n
u
s
ed
i
n
t
h
e
ev
a
lu
at
io
n
s
.
T
h
e
p
r
o
v
id
ed
w
ei
g
h
ts
w
e
r
e
2
4
.
2
8
,
5
.
7
1
,
1
5
.
0
0
,
9
.
2
8
,
0
.
7
1
,
3
9
.
2
8
,
3
.
5
7
,
2
.
1
4
f
o
r
an
g
er
,
an
ticip
atio
n
,
d
is
g
u
s
t,
f
ea
r
,
j
o
y
,
s
ad
n
es
s
,
s
u
r
p
r
is
e
an
d
tr
u
s
t
r
esp
ec
tiv
el
y
.
T
h
ese
w
e
ig
h
ts
w
er
e
ca
lcu
lated
as
p
er
t
h
e
u
s
e
o
f
o
n
l
y
eig
h
t
e
m
o
tio
n
s
,
an
d
i
f
t
h
e
n
u
m
b
er
o
f
e
m
o
tio
n
s
i
n
cr
ea
s
ed
th
e
w
ei
g
h
ts
al
s
o
d
if
f
er
ed
.
I
t
w
as i
n
f
er
r
ed
f
r
o
m
t
h
e
p
r
ev
io
u
s
d
is
c
u
s
s
io
n
t
h
at
d
e
p
r
ess
io
n
is
a
s
tate
o
f
t
h
e
m
in
d
an
d
a
m
i
x
t
u
r
e
o
f
d
if
f
er
e
n
t e
m
o
tio
n
s
,
s
o
it
w
o
u
l
d
b
e
r
ig
h
t to
s
a
y
t
h
at
le
v
el
s
o
f
d
ep
r
ess
io
n
ca
n
b
e
a
n
al
y
ze
d
f
r
o
m
th
e
m
i
x
t
u
r
e
o
f
all
th
e
v
a
lu
e
s
f
r
o
m
al
l
th
e
e
m
o
tio
n
s
.
A
w
e
ig
h
ted
s
u
m
o
f
th
e
p
r
o
d
u
ct
o
f
fin
al
s
en
ti
m
e
n
t
v
al
u
e
w
it
h
t
h
e
e
m
o
tio
n
v
a
lu
e
s
w
as
ca
lcu
late
d
.
T
h
e
o
u
tp
u
t
v
al
u
e
g
en
er
ated
h
ad
a
v
er
y
h
i
g
h
r
an
g
e
w
h
ich
w
as
n
o
r
m
alize
d
b
et
w
ee
n
-
4
to
+4
f
o
r
b
etter
v
i
s
u
aliza
tio
n
o
f
t
h
e
d
ata.
T
h
is
o
u
tp
u
t
v
al
u
e
p
r
o
v
id
ed
u
s
a
lev
el
o
f
d
ep
r
ess
io
n
i
n
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.
9
,
No
.
4
,
A
u
g
u
s
t 2
0
1
9
:
3
2
4
7
-
3
2
5
5
3252
th
e
d
a
y
to
d
a
y
t
w
ee
ts
f
o
r
t
h
e
u
s
er
,
b
u
t
t
h
i
s
d
id
n
o
t
p
r
o
v
e
t
h
at
a
u
s
er
h
ad
b
ee
n
d
ep
r
ess
ed
d
u
r
in
g
t
h
at
ti
m
e.
Dep
r
ess
io
n
a
s
a
s
ta
te
ca
n
h
a
v
e
lo
n
g
ter
m
e
f
f
ec
ts
a
n
d
s
o
th
e
v
al
u
es
as
s
u
c
h
ca
n
n
o
t
b
e
t
ak
en
to
r
ep
r
esen
t
d
ep
r
ess
io
n
in
a
u
s
er
.
T
h
e
v
al
u
es
ca
n
h
o
w
e
v
er
co
r
r
elate
to
th
e
f
ac
t
t
h
at
t
h
er
e
is
a
c
h
an
ce
th
at
t
h
e
u
s
er
is
d
ep
r
ess
ed
o
r
n
o
t
d
ep
r
ess
ed
d
u
r
in
g
th
e
p
er
io
d
.
T
o
u
s
e
th
e
m
ag
n
it
u
d
es
g
en
er
ated
in
a
p
r
o
p
er
m
an
n
er
,
th
e
d
ata
n
ee
d
ed
to
b
e
v
is
u
a
lized
an
d
as
ea
ch
v
al
u
e
r
ep
r
esen
ted
a
d
ay
o
f
t
w
ee
t
s
,
a
lis
t
o
f
all
th
e
v
al
u
es
w
er
e
f
o
u
n
d
w
h
er
ei
n
th
e
m
a
g
n
i
tu
d
e
r
e
m
ain
ed
n
eg
at
iv
e
f
o
r
a
co
n
s
i
d
e
r
ab
le
p
e
r
io
d
o
f
ti
m
e.
Fig
u
r
e
4
.
Sen
ti
m
e
n
t
s
co
r
e
ev
al
u
atio
n
Fig
u
r
e
5
.
Fin
al
d
ep
r
ess
io
n
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
W
e
tak
e
t
h
e
ca
s
e
o
f
a
u
s
er
”
AADo
w
d
”.
Fro
m
h
is
t
w
ee
ts
,
i
t
w
a
s
clea
r
l
y
v
is
ib
le
t
h
at
t
h
er
e
h
ad
b
ee
n
m
u
ltip
le
i
n
s
ta
n
ce
s
w
h
er
ei
n
n
e
g
ati
v
e
m
a
g
n
it
u
d
e
h
ad
b
ee
n
r
e
co
r
d
ed
f
o
r
a
co
n
s
id
er
ab
le
p
e
r
io
d
.
Fro
m
t
h
e
fig
u
r
e,
it
is
v
i
s
ib
le
t
h
at
th
e
u
s
er
h
ad
b
ee
n
d
ep
r
ess
ed
f
r
o
m
3
2
n
d
d
a
y
to
th
e
4
4
th
d
a
y
as
t
h
e
y
s
h
o
w
a
lo
n
g
s
eq
u
e
n
ce
o
f
n
eg
at
iv
e
m
a
g
n
itu
d
es.
W
h
en
t
h
e
d
ata
f
r
o
m
t
h
e
t
w
ee
t
s
w
er
e
ch
ec
k
ed
it
w
a
s
clea
r
th
at
t
h
e
u
s
er
w
as
i
n
f
ac
t
i
n
d
ep
r
ess
io
n
as
th
e
u
s
er
all
th
r
o
u
g
h
t
h
ese
d
a
y
s
w
a
s
co
n
ti
n
u
o
u
s
l
y
p
o
s
ti
n
g
t
w
ee
ts
r
eg
ar
d
in
g
t
h
e
lo
s
s
o
f
li
v
es
d
u
r
i
n
g
w
ar
,
t
h
e
ill
e
f
f
ec
ts
o
f
w
ar
o
n
t
h
e
u
s
er
s
f
a
m
i
l
y
,
th
e
i
n
ab
ilit
y
o
f
t
h
e
g
o
v
er
n
m
en
t
to
s
u
p
p
o
r
t
s
u
ch
f
a
m
i
lies
,
p
o
liti
ca
l
co
r
r
u
p
tio
n
”
etc.
Du
r
i
n
g
t
h
is
p
er
io
d
it
w
as
v
i
s
ib
le
t
h
at
t
h
e
u
s
er
w
a
s
tr
a
n
s
fix
ed
at
a
s
i
n
g
le
lo
ca
tio
n
f
o
r
a
lo
n
g
p
er
io
d
o
f
ti
m
e,
w
h
ic
h
co
u
ld
b
e
ass
u
m
ed
as
a
h
o
u
s
e
o
r
a
h
o
s
p
ital.
T
h
e
tim
i
n
g
o
f
t
w
ee
ts
i
n
co
m
p
ar
is
o
n
to
t
w
ee
ts
f
r
o
m
o
th
er
p
er
io
d
s
w
a
s
d
if
f
er
en
t
an
d
th
e
t
w
ee
t
s
in
th
is
p
er
io
d
w
er
e
co
n
s
i
s
te
n
t
an
d
d
u
r
in
g
s
p
ec
ifi
c
h
o
u
r
s
o
f
th
e
d
ay
.
Si
m
ilar
l
y
,
t
h
e
d
ata
al
s
o
co
r
r
elate
d
f
o
r
th
e
p
er
io
d
b
et
w
ee
n
7
0
th
d
a
y
to
8
4
th
d
a
y
a
n
d
th
e
u
s
er
h
ad
eit
h
er
t
w
ee
ted
m
a
n
y
n
e
g
ati
v
e
t
w
ee
t
s
o
r
r
et
w
ee
ted
n
e
g
ati
v
e
t
w
ee
ts
b
y
o
t
h
er
s
.
A
g
r
ap
h
h
as
b
ee
n
p
r
o
v
id
ed
w
h
ich
s
h
o
w
s
th
e
e
n
g
ag
e
m
e
n
t
o
f
t
h
i
s
u
s
er
o
n
T
w
i
tter
d
u
r
i
n
g
d
i
f
f
er
e
n
t
h
o
u
r
s
o
f
t
h
e
d
a
y
as
w
ell
as
o
n
d
if
f
er
en
t
d
a
y
s
.
B
u
t
f
o
r
all
t
h
e
o
t
h
er
p
o
s
ts
th
e
en
g
ag
e
m
e
n
t
p
atter
n
w
a
s
v
e
r
y
d
if
f
er
e
n
t
f
r
o
m
th
e
o
n
e
s
h
o
w
i
n
g
t
h
e
e
n
g
ag
e
m
e
n
t
p
atter
n
d
u
r
i
n
g
t
h
e
d
ep
r
ess
io
n
in
ter
v
a
l.
T
h
is
p
r
o
v
id
es
u
s
w
i
t
h
m
o
r
e
ev
id
en
ce
t
h
at
th
e
u
s
er
w
a
s
,
i
n
f
ac
t,
s
u
f
f
er
in
g
f
r
o
m
s
o
m
e
s
o
r
t
o
f
d
ep
r
ess
io
n
an
d
it
co
u
ld
clea
r
l
y
b
e
co
r
r
elate
d
w
it
h
t
h
e
d
ata
a
t
d
if
f
er
en
t
p
o
in
ts
o
f
ti
m
e
w
it
h
th
e
t
w
ee
t
s
.
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:
2
0
8
8
-
8708
Dete
ctin
g
th
e
ma
g
n
itu
d
e
o
f
d
e
p
r
ess
io
n
in
Tw
itte
r
u
s
er
s
u
s
in
g
s
en
timen
t a
n
a
lysi
s
(
Jin
i J
o
jo
S
tep
h
en
)
3253
Fig
u
r
e
6
.
Dep
r
ess
io
n
lev
e
l
m
a
g
n
i
tu
d
e
o
v
er
v
ie
w
(
a)
(
b
)
Fig
u
r
e
6
.
Dep
r
ess
io
n
lev
e
l
m
a
g
n
i
tu
d
e
o
v
er
v
ie
w
(
a)
Ho
u
r
-
W
i
s
e
E
n
g
ag
e
m
e
n
ts
,
(
b)
Da
y
-
W
is
e
E
n
g
a
g
e
m
en
t
s
(
a)
(
b
)
Fig
u
r
e
7
.
E
n
g
a
g
e
m
e
n
t
s
d
u
r
in
g
d
ep
r
ess
io
n
p
er
io
d
,
(
a)
Ho
u
r
-
W
is
e
E
n
g
a
g
e
m
en
ts
,
(
b
)
Da
y
-
W
is
e
E
n
g
a
g
e
m
en
ts
4.
CO
NCLU
SI
O
N
T
h
e
p
r
im
ar
y
ai
m
o
f
t
h
i
s
r
ese
ar
ch
w
a
s
to
id
en
ti
f
y
a
m
ea
n
s
to
ca
lcu
late
th
e
le
v
el
o
f
d
ep
r
ess
io
n
i
n
a
t
w
i
tter
u
s
er
b
ased
o
n
th
eir
t
wee
ts
.
T
o
ev
alu
ate
th
e
s
co
r
e
o
r
th
e
m
a
g
n
i
tu
d
e
g
e
n
er
ated
b
y
th
e
alg
o
r
it
h
m
,
it
w
a
s
i
m
p
o
r
tan
t
to
co
r
r
elate
th
e
d
ata
w
it
h
t
h
e
t
w
ee
ts
a
n
d
fin
d
o
u
t
m
an
u
all
y
w
h
eth
er
t
h
e
s
co
r
es
r
ep
r
esen
ted
w
er
e
co
r
r
ec
t
an
d
th
at
t
h
e
y
p
r
o
v
id
e
a
f
ac
t
u
al
u
n
d
er
s
ta
n
d
i
n
g
o
f
d
ep
r
ess
io
n
in
th
e
u
s
er
.
I
t
is
clea
r
l
y
ev
id
en
t
f
r
o
m
th
e
o
u
t
co
m
e
th
a
t
t
h
e
p
h
a
s
es
id
e
n
ti
fi
e
d
b
y
t
h
e
al
g
o
r
it
h
m
d
o
es
in
d
ee
d
co
r
r
elate
w
it
h
t
h
e
u
s
e
r
’
s
t
wee
ts
an
d
s
o
it
ca
n
b
e
clea
r
l
y
s
aid
th
at
t
h
e
u
s
er
w
a
s
d
ep
r
ess
ed
d
u
r
in
g
th
at
ti
m
e
p
er
io
d
.
I
t
w
as
also
f
o
u
n
d
t
h
at
w
h
e
n
th
e
u
s
er
w
a
s
in
d
ep
r
ess
io
n
,
th
e
y
w
er
e
t
w
ee
ti
n
g
d
u
r
i
n
g
s
p
ec
i
fi
c
h
o
u
r
s
o
f
t
h
e
d
a
y
a
n
d
d
u
r
in
g
s
p
ec
i
fi
c
d
a
y
s
o
f
t
h
e
w
ee
k
,
w
h
ic
h
w
a
s
ab
n
o
r
m
al
a
s
f
o
r
all
t
h
e
o
t
h
er
t
w
ee
ts
i
t
w
as
r
ec
o
r
d
ed
to
b
e
a
d
if
f
er
en
t
ti
m
e
o
f
t
h
e
d
a
y
an
d
d
if
f
er
en
t
d
a
y
s
o
f
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.
9
,
No
.
4
,
A
u
g
u
s
t 2
0
1
9
:
3
2
4
7
-
3
2
5
5
3254
th
e
w
ee
k
.
A
f
u
r
t
h
er
h
elp
o
f
a
p
s
y
c
h
o
lo
g
is
t
w
as
s
o
u
g
h
t
o
u
t
an
d
it
w
a
s
clea
r
l
y
e
v
id
en
t
f
r
o
m
t
h
eir
r
esp
o
n
s
e
t
h
at
th
e
d
ep
r
ess
io
n
le
v
els
d
o
co
r
r
elate
w
it
h
t
h
e
t
w
ee
ts
a
n
d
th
at
th
er
e
ex
is
t
s
s
o
m
e
s
en
s
e
o
f
d
ep
r
ess
io
n
in
t
h
e
u
s
er
d
u
r
in
g
th
at
p
er
io
d
.
T
h
e
r
esear
ch
q
u
esti
o
n
f
o
r
th
i
s
p
ap
er
w
a
s
also
an
s
w
er
ed
as
to
w
h
et
h
er
th
er
e
ex
is
t
s
a
m
ea
n
s
to
ev
alu
a
te
d
ep
r
ess
io
n
o
n
t
h
e
b
as
is
th
e
e
m
o
tio
n
al
i
n
te
g
r
it
y
o
f
a
p
er
s
o
n
ca
n
b
e
f
o
r
m
u
lated
,
w
h
i
ch
ca
n
b
e
co
r
r
elate
d
w
it
h
t
h
e
d
ata
an
d
s
t
u
d
ied
.
T
h
e
li
m
iti
n
g
f
ac
to
r
f
o
r
s
u
c
h
s
y
s
te
m
s
ar
e
m
an
u
al
i
n
ter
v
e
n
tio
n
an
d
cli
n
ical
as
s
ess
m
e
n
t
s
.
I
t
is
i
m
p
o
r
tan
t
th
at
t
h
e
d
ata
i.
e.
,
th
e
t
w
ee
ts
co
r
r
elate
w
it
h
th
e
fin
a
l
d
ep
r
ess
io
n
s
co
r
es
ca
lc
u
lated
a
n
d
th
a
t
a
co
m
p
lete
m
ed
ical
ev
alu
a
tio
n
w
o
u
ld
b
e
a
p
r
ef
er
r
ed
m
et
h
o
d
f
o
r
u
n
d
er
s
ta
n
d
in
g
t
h
e
m
e
n
tal
h
ea
lt
h
o
f
th
e
p
atien
t.
So
i
n
ter
m
s
o
f
u
s
a
g
e,
t
h
is
al
g
o
r
ith
m
ca
n
b
e
u
s
ed
as a
n
aid
e
f
o
r
m
ed
ical
o
b
s
er
v
er
s
to
u
n
d
er
s
ta
n
d
p
atien
t
s
u
n
d
er
g
o
in
g
d
ep
r
ess
io
n
th
er
ap
y
at
r
eh
ab
ce
n
tr
es.
I
t
ca
n
aid
e
m
ed
ical
p
r
o
f
ess
io
n
als
t
o
u
n
d
er
s
tan
d
a
p
er
s
o
n
’
s
b
eh
a
v
io
r
b
ased
o
n
th
eir
o
n
lin
e
ac
ti
v
it
y
.
I
n
ter
m
s
o
f
f
u
tu
r
e
w
o
r
k
t
h
e
c
u
r
r
en
t
s
y
s
te
m
ca
n
b
e
u
p
g
r
ad
e
d
to
ch
ec
k
all
s
o
cial
m
ed
ia
ac
tiv
it
y
f
o
r
t
h
e
u
s
er
an
d
a
s
s
es
s
t
h
eir
m
e
n
tal
h
ea
lth
b
ased
o
n
t
h
eir
ac
ti
v
itie
s
o
n
d
if
f
er
en
t
p
lat
f
o
r
m
s
.
A
ls
o
t
h
e
i
m
p
le
m
en
ta
tio
n
ca
n
b
e
u
s
ed
to
ch
ec
k
th
e
o
n
li
n
e
a
ctiv
it
y
f
o
r
a
p
er
s
o
n
i
n
a
clo
s
e
d
en
v
ir
o
n
m
en
t
s
u
c
h
as
a
r
e
h
a
b
clin
ic
an
d
w
h
er
e
th
e
u
s
er
b
e
h
av
io
r
ca
n
b
e
m
o
n
ito
r
ed
f
u
ll
ti
m
e.
S
u
ch
ac
ti
v
itie
s
c
an
s
cr
ap
e
k
e
y
w
o
r
d
s
f
r
o
m
th
e
u
s
er
’
s
o
n
li
n
e
ac
t
iv
i
t
y
an
d
en
ab
le
m
ed
ical
p
r
o
f
es
s
io
n
als to
ass
es
s
th
e
s
tate
o
f
t
h
e
p
atien
t i
n
a
b
e
tter
w
a
y
.
A
l
s
o
th
e
m
a
n
u
al
i
n
ter
v
en
t
io
n
f
o
r
v
al
id
atin
g
t
h
e
t
w
ee
ts
c
an
b
e
m
ad
e
au
to
n
o
m
o
u
s
an
d
a
m
ac
h
i
n
e
lear
n
in
g
m
o
d
el
ca
n
b
e
d
e
v
el
o
p
ed
w
h
ic
h
ca
n
h
elp
in
co
r
r
o
b
o
r
atin
g
t
h
e
e
x
is
te
n
ce
o
f
a
n
y
s
ig
n
s
o
f
d
ep
r
ess
io
n
b
ased
o
n
t
h
e
m
ag
n
it
u
d
e
ca
lc
u
lated
.
T
h
is
ca
n
h
elp
i
n
m
a
k
i
n
g
t
h
e
s
y
s
te
m
co
m
p
letel
y
a
u
t
o
n
o
m
o
u
s
a
n
d
h
elp
in
ea
s
y
i
m
p
le
m
e
n
tatio
n
i
n
s
p
ec
i
fi
c
en
v
ir
o
n
m
e
n
ts
s
u
ch
as
h
o
s
p
itals
,
r
eh
ab
ilit
a
ti
o
n
cl
in
ic
s
,
o
f
fi
ce
s
.
T
h
is
al
g
o
r
ith
m
ca
n
also
b
e
i
m
p
le
m
e
n
ted
in
a
m
ac
h
i
n
e
lear
n
i
n
g
m
o
d
el
an
d
th
e
m
ac
h
i
n
e
ca
n
b
e
m
a
d
e
to
u
n
d
er
s
t
an
d
th
e
ca
teg
o
r
izatio
n
o
f
t
w
ee
ts
a
n
d
p
r
o
p
er
ev
alu
atio
n
b
ased
o
n
m
a
g
n
i
tu
d
e.
S
u
c
h
lear
n
i
n
g
ca
n
h
e
lp
u
s
u
n
d
er
s
ta
n
d
if
a
p
ar
ticu
lar
u
s
er
i
n
r
ea
l
-
ti
m
e
i
s
cu
r
r
en
tl
y
in
d
ep
r
ess
io
n
o
r
h
as
b
ee
n
in
t
h
e
d
ep
r
ess
io
n
f
o
r
a
p
er
io
d
o
f
ti
m
e
an
d
f
u
r
t
h
er
n
ec
e
s
s
ar
y
s
tep
s
ca
n
b
e
u
n
d
er
ta
k
en
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
e
au
th
o
r
w
o
u
ld
li
k
e
to
th
an
k
m
e
n
to
r
an
d
g
u
id
e,
P
r
o
f
.
Dr
.
P
r
a
b
u
P
,
f
o
r
h
is
co
n
s
t
an
t
s
u
p
p
o
r
t
th
r
o
u
g
h
o
u
t
t
h
e
li
f
ec
y
cle
o
f
t
h
is
r
esear
ch
.
T
h
e
u
n
i
v
er
s
i
t
y
h
a
s
also
p
la
y
ed
a
m
aj
o
r
r
o
le
in
p
r
o
v
id
in
g
s
u
p
p
o
r
t
in
ter
m
s
o
f
e
x
tr
ac
tin
g
t
h
e
d
ata
a
n
d
u
n
d
er
s
ta
n
d
in
g
t
h
e
p
r
o
b
le
m
d
o
m
ai
n
.
T
h
e
p
ap
er
w
o
u
ld
n
o
t
h
av
e
b
ee
n
co
m
p
leted
w
it
h
o
u
t
t
h
e
co
n
tr
ib
u
tio
n
o
f
all
t
h
e
o
t
h
er
f
ac
u
lt
ies
o
f
C
h
r
is
t
(
Dee
m
ed
to
b
e
U
n
i
v
er
s
it
y
)
,
f
o
r
b
o
t
h
r
esear
c
h
an
d
r
ev
ie
w
.
RE
F
E
R
E
NC
E
S
[1
]
S
teff
i
V
e
ien
tl
e
n
a
,
P
ra
b
u
P
,
“
P
re
v
a
len
c
e
o
f
H
y
p
e
rten
sio
n
a
n
d
De
term
in
a
ti
o
n
o
f
it
s
Risk
F
a
c
to
rs.
In
Ko
ra
n
g
ra
p
a
d
y
,
Ud
u
p
i
District,
Co
a
sta
l
Ka
rn
a
tak
a
,
In
d
ia
,
”
Asia
n
J
o
u
rn
a
l
Of
Ph
a
rm
a
c
e
u
ti
c
a
l
A
n
d
Cl
in
ica
l
Res
e
a
rc
h
,
v
o
l.
1
1
,
n
o
.
6
,
p
p
.
5
1
7
-
21
,
J
u
n
e
2
0
1
8
.
[2
]
A
n
d
re
w
G
.
Re
e
c
e
,
A
n
d
re
w
J.
R
e
a
g
a
n
,
Ka
th
a
rin
a
L
.
M
.
L
ix
,
P
e
ter
S
h
e
rid
a
n
D
o
d
d
s,
Ch
rist
o
p
h
e
r
M
.
Da
n
f
o
rth
&
El
le
n
J.
L
a
n
g
e
r
”
F
o
re
c
a
stin
g
th
e
o
n
se
t
a
n
d
c
o
u
rse
o
f
m
e
n
tal
il
ln
e
ss
w
it
h
Tw
it
ter
d
a
ta”
in
2
0
1
7
S
c
i
e
n
ti
fi
c
Re
p
o
rts,
p
p
.
1
-
1
1
,
1
1
Oc
to
b
e
r
2
0
1
7
.
[3
]
Da
n
i
Ca
stro
,
“
Em
o
ji
S
e
n
ti
m
e
n
t
P
e
rc
e
p
ti
o
n
b
e
tw
e
e
n
Re
a
d
e
rs
a
n
d
W
rit
e
rs,
Jo
se
Be
re
n
g
u
e
re
s
,”
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Bi
g
Da
t
a
(
BIGDAT
A)
,
p
p
.
4
3
2
1
-
4
3
2
8
,
2
0
1
7
.
[4
]
Ch
iara
Zu
c
c
o
,
Ba
rb
a
ra
Ca
lab
re
se
,
M
a
rio
Ca
n
n
a
taro
CR
Da
ta
A
n
a
l
y
ti
c
s
De
p
a
rt
m
e
n
t
o
f
M
e
d
ica
l
a
n
d
S
u
rg
ica
l
S
c
ien
c
e
s
Un
iv
e
rsit
y
“
M
a
g
n
a
G
rc
i
a
”
V
iale
Eu
ro
p
a
,
8
8
1
0
0
,
Ca
tan
z
a
ro
,
Italy
E
m
a
il
:
c
h
iara
.
z
u
c
c
o
@s
tu
d
e
n
ti
@u
n
icz
.
i
t
,
b
c
a
lab
re
se
@u
n
icz
.
it
,
c
a
n
n
a
taro
@
u
n
icz
.
i;
“
S
e
n
ti
m
e
n
t
A
n
a
l
y
sis
a
n
d
Aff
e
c
ti
v
e
Co
m
p
u
ti
n
g
f
o
r
d
e
p
re
ss
io
n
m
o
n
it
o
rin
g
,
”
IEE
E
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
Bio
i
n
f
o
rm
a
t
ics
a
n
d
Bio
m
e
d
icin
e
(BI
BM
),
p
p
.
1
9
8
8
-
1
9
9
5
,
2
0
1
7
.
[5
]
Ra
jd
e
e
p
S
in
g
h
,
R
o
sh
a
n
Ba
g
la,
Ha
rk
iran
Ka
u
r
,”
Tex
t
A
n
a
l
y
ti
c
s
o
f
W
e
b
P
o
stsC
o
m
m
e
n
ts
Us
in
g
S
e
n
ti
m
e
n
t
A
n
a
l
y
sis
”
2
0
1
5
.
[6
]
Div
e
e
sh
S
in
g
h
a
n
d
A
li
n
e
e
n
W
a
n
g
,
“
De
tec
ti
n
g
De
p
re
ss
io
n
T
h
ro
u
g
h
Tw
e
e
ts”
S
tan
d
f
o
rd
Un
iv
e
rsity
C
A 9
4
3
0
,
;p
p
.
1
-
9.
[7
]
A
lt
u
g
Ak
a
y
,
M
e
m
b
e
r,
IEE
E,
A
n
d
re
i
Dra
g
o
m
ir,
M
e
m
b
e
r,
IEE
E,
a
n
d
Bj
o
rn
-
Er
ik
Erl
a
n
d
ss
o
n
,
S
e
n
i
o
r
M
e
m
b
e
r,
IEE
E
A
s
se
ss
in
g
A
n
ti
d
e
p
re
ss
a
n
ts
Us
in
g
In
telli
g
e
n
t
Da
ta
M
o
n
it
o
rin
g
a
n
d
M
in
i
n
g
o
f
On
li
n
e
F
o
ra
”
in
2
0
1
6
,
I
EE
E
J
o
u
rn
a
l
o
f
Bi
o
me
d
ica
l
a
n
d
He
a
lt
h
In
f
o
rm
a
ti
c
s
,
V
o
l.
2
0
,
N
o
.
4,
p
p
.
9
7
7
-
9
8
6
,
J
u
ly
2
0
1
6
.
[8
]
M
o
in
Na
d
e
e
m
,
M
ik
e
Ho
rn
.
,
G
le
n
Co
p
p
e
rsm
it
h
,
Jo
h
n
s
Ho
p
k
in
s
Un
iv
e
rsit
y
a
n
d
Dr.
S
a
n
d
ip
S
e
n
,
P
h
D,
Un
iv
e
rsity
o
f
T
u
lsa
,
“
Id
e
n
ti
fy
in
g
De
p
re
ss
io
n
o
n
Tw
it
ter,”
p
p
.
1
-
9.
[9
]
A
n
n
De
v
it
t,
Kh
u
rsh
id
A
h
m
a
d
,
“
S
e
n
ti
m
e
n
t
P
o
larity
Id
e
n
ti
fi
c
a
ti
o
n
in
F
in
a
n
c
ial
N
e
w
s:
A
Co
h
e
sio
n
-
b
a
se
d
A
p
p
ro
a
c
h
”
,
p
p
.
1
-
8.
[1
0
]
Ya
ir
Ne
u
m
a
n
,
Yo
h
a
i
Co
h
e
n
,
Da
n
A
ss
a
f
,
G
a
b
b
i
Ke
d
m
a
,
“
P
ro
a
c
ti
v
e
sc
re
e
n
in
g
f
o
r
d
e
p
re
ss
io
n
th
ro
u
g
h
m
e
tap
h
o
rica
l
a
n
d
a
u
to
m
a
ti
c
tex
t
a
n
a
l
y
sis
,
”
Arti
fi
c
ia
l
In
telli
g
e
n
c
e
in
M
e
d
icin
e
,
V
o
l.
5
6
,
No
.
1
,
p
p
.
19
-
2
5
,
2
0
1
2
.
[1
1
]
“
T
h
e
Ev
o
lu
ti
o
n
o
f
S
e
n
ti
m
e
n
t
A
n
a
l
y
sis”
-
A
Re
v
ie
w
o
f
R
e
se
a
r
c
h
T
o
p
ic
s,
V
e
n
u
e
s,
a
n
d
T
o
p
Cit
e
d
P
a
p
e
rs;
De
c
e
m
b
e
r
2
0
1
6
.
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:
2
0
8
8
-
8708
Dete
ctin
g
th
e
ma
g
n
itu
d
e
o
f
d
e
p
r
ess
io
n
in
Tw
itte
r
u
s
er
s
u
s
in
g
s
en
timen
t a
n
a
lysi
s
(
Jin
i J
o
jo
S
tep
h
en
)
3255
[1
2
]
Ho
lt
z
m
a
n
,
Nic
h
o
las
S
.
”
A
m
e
ta
-
a
n
a
ly
sis
o
f
c
o
rre
latio
n
s b
e
tw
e
e
n
d
e
p
re
ss
io
n
a
n
d
fi
rst
p
e
rso
n
u
se
,
”
J
o
u
rn
a
l
o
f
re
se
a
rc
h
in
p
e
rs
o
n
a
l
it
y
,
p
p
.
63
-
6
8
,
2
0
1
6
.
[1
3
]
Re
n
a
ra
L
.
Ro
sa
,
De
m
o
ste
n
e
s,
Z.
Ro
d
rig
u
e
z
,
G
ise
le,
M
.
S
c
h
w
a
rtz,
Ia
v
a
n
a
De
Ca
m
p
o
s
Rib
e
rio
a
n
d
G
ra
c
a
Bre
s
sa
n
,
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
d
ig
it
a
l
S
y
ste
m
s
-
Un
iv
e
rsit
y
o
f
S
a
o
P
u
a
lo
-
Bra
z
il
Un
iv
e
rsity
Estad
u
a
l
P
a
u
lo
s
t
a
Ju
li
o
d
e
M
e
sq
u
it
a
F
i
lh
o
,
Bi
o
sc
ien
c
e
s
In
stit
u
te
o
f
Rio
Clar
o
Bra
z
il
“
Mo
n
it
o
r
in
g
S
y
ste
m
f
o
r
P
o
te
n
ti
a
l
Us
e
rs
w
it
h
De
p
re
ss
io
n
Us
in
g
S
e
n
t
im
e
n
t
A
n
a
l
y
sis
,
”
p
p
.
3
8
1
-
3
8
2
,
2
0
1
6
.
[1
4
]
Ire
lan
d
,
M
.
E.
,
&
M
e
h
l,
M
.
R.
“
Na
tu
ra
l
lan
g
u
a
g
e
u
se
a
s
a
m
a
r
k
e
r
o
f
p
e
rso
n
a
li
ty
.
In
T
.
Ho
lt
g
ra
v
e
s
(Ed
.
)
,”
T
h
e
o
x
f
o
r
d
h
a
n
d
b
o
o
k
o
f
lan
g
u
a
g
e
a
n
d
so
c
ial
p
sy
c
h
o
lo
g
y
,
Ox
f
o
rd
Un
iv
e
rsity
P
re
ss
,
2
0
1
4
.
[1
5
]
Jo
n
a
th
a
n
G
ra
tch
,
Ro
n
A
rtstein
,
G
a
l
e
L
u
c
a
s,
G
io
ta
S
trato
u
e
t
a
l.
,
T
h
e
Distre
ss
A
n
a
l
y
sis
In
terv
ie
w
Co
rp
u
s
o
f
h
u
m
a
n
a
n
d
c
o
m
p
u
ter
in
terv
iew
s
,
”
Pro
c
e
e
d
in
g
s
o
f
t
h
e
Ni
n
th
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
L
a
n
g
u
a
g
e
Res
o
u
rc
e
s
a
n
d
Eva
lu
a
ti
o
n
(
L
RE
C
2
0
1
4
)
,
L
REC,
p
p
.
3
1
2
3
-
3
1
2
8
,
2
0
1
4
.
[1
6
]
M
u
n
a
z
z
a
Ish
ti
a
q
”
S
e
n
ti
m
e
n
t
A
n
a
ly
sis
o
f
Tw
it
ter
Da
ta
Us
in
g
S
e
n
ti
m
e
n
t
In
fl
u
e
n
c
e
rs”
in
2
0
1
4
Co
ll
e
g
e
o
f
E
lec
trica
l
a
n
d
M
e
c
h
a
n
ica
l
En
g
i
n
e
e
rin
g
Na
t
io
n
a
l
Un
ive
rs
i
ty
o
f
S
c
ien
c
e
s
&
T
e
c
h
n
o
l
o
g
y
(
NUS
T
)
,
v
o
l
6
,
n
o
.
1
,
p
p
.
1
7
-
25
,
23
De
c
e
m
b
e
r
2
0
1
4
.
[1
7
]
A
sh
w
a
th
Ku
m
a
r,
Ro
b
in
K
T
h
o
m
a
s
,
S
e
th
u
ra
m
Ra
m
a
li
n
g
a
Re
d
d
y
,
Yu
h
a
o
Qia
o
sa
li
m
a
ta@
tcd
.
ie,
ro
t
h
o
m
a
s@
tcd
.
ie,
ra
m
a
li
n
s@
tcd
.
ie,
q
iao
y
@tc
d
.
ie
Tri
n
it
y
Co
ll
e
g
e
Du
b
li
n
;
“
M
e
tri
c
-
b
a
se
d
m
e
th
o
d
to
d
e
tec
t
th
e
lev
e
l
o
f
d
e
p
re
ss
io
n
b
a
se
d
o
n
T
e
x
t
,
”
p
p
.
1
-
9
,
2
0
1
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.