T
E
L
KO
M
NIK
A
, V
ol
.
17
,
No.
4,
A
ug
us
t
20
1
9,
p
p.2
08
7
~
2
09
7
IS
S
N: 1
69
3
-
6
93
0
,
accr
ed
ited
F
irst
Gr
ad
e b
y K
em
en
r
istekdikti,
Decr
ee
No: 2
1/E/
K
P
T
/20
18
DOI:
10.12928/TE
LK
OM
N
IK
A
.v
1
7
i
4
.
12619
◼
20
87
Rec
ei
v
ed
M
arc
h
6
, 2
01
8
; R
ev
i
s
ed
Ma
r
c
h 1
7
, 2
0
1
9
;
A
c
c
ep
ted
A
pr
i
l
1
0
,
20
1
9
Depressi
on
a
nd
anxiet
y
de
tect
i
on
t
hro
ug
h
th
e Cl
ose
d
-
L
oo
p m
e
th
od
u
sin
g
D
A
S
S
-
21
S
eti
y
o
Bu
d
i
ya
n
t
o
*
,
Har
r
y
Cand
r
a
S
iho
mb
ing
, Fa
jar
Raha
y
u
I
. M
.
D
ep
a
r
t
m
e
n
t
o
f
E
l
ec
t
r
ic
al
E
n
g
i
n
ee
r
i
n
g
,
F
a
c
ul
t
y
o
f
E
n
gi
n
e
er
i
n
g,
U
n
iv
er
s
i
t
a
s
M
er
c
u
B
u
a
n
a
,
J
a
k
a
rta
1
1
6
5
0
,
I
n
do
n
es
i
a
*C
o
rre
s
p
o
n
d
i
n
g
a
u
th
o
r,
e
-
m
a
i
l
:
s
b
u
diy
a
n
t
o
@
m
e
r
c
u
b
u
a
na
.
a
c
.
i
d
Ab
strac
t
Th
e
c
h
a
n
g
e
o
f
i
n
fo
rm
a
t
i
o
n
a
n
d
c
o
m
m
u
n
i
c
a
ti
o
n
te
c
h
n
o
l
o
g
y
h
a
s
b
ro
u
g
h
t
m
a
n
y
c
h
a
n
g
e
s
i
n
d
a
i
l
y
l
i
fe
.
Th
e
wa
y
h
u
m
a
n
s
i
n
t
e
ra
c
ti
n
g
i
s
c
h
a
n
g
i
n
g
.
It
i
s
p
o
s
s
i
b
l
e
t
o
e
x
p
re
s
s
e
a
c
h
fo
rm
o
f
c
o
m
m
u
n
i
c
a
ti
o
n
d
i
re
c
tl
y
a
n
d
i
n
s
ta
n
t
l
y
.
So
c
i
a
l
m
e
d
i
a
h
a
s
c
o
n
tr
i
b
u
te
d
d
a
t
a
i
n
s
i
z
e
,
d
i
v
e
rs
i
ty
a
n
d
c
a
p
a
c
i
t
y
a
n
d
q
u
a
l
i
ty
.
B
a
s
e
d
o
n
i
t
,
th
e
i
d
e
a
wa
s
t
o
s
e
e
a
n
d
m
e
a
s
u
re
th
e
t
e
n
d
e
n
c
y
o
f
d
e
p
r
e
s
s
i
o
n
a
n
d
a
n
x
i
e
t
y
t
h
ro
u
g
h
s
o
c
i
a
l
m
e
d
i
a
u
s
i
n
g
th
e
Clo
s
e
d
-
L
o
o
p
m
e
t
h
o
d
u
s
i
n
g
Fa
c
e
b
o
o
k
t
e
x
t
m
i
n
i
n
g
p
o
s
ts
.
Th
ro
u
g
h
th
e
s
t
a
g
e
s
o
f
p
re
-
p
ro
c
e
s
s
i
n
g
i
n
c
l
u
d
i
n
g
te
x
t
e
x
tra
c
ti
o
n
u
s
i
n
g
th
e
Naï
v
e
Ba
y
e
s
m
a
c
h
i
n
e
l
e
a
rn
i
n
g
m
o
d
e
l
fo
r
te
x
t
c
l
a
s
s
i
fi
c
a
ti
o
n
,
t
h
e
e
a
rl
y
s
i
g
n
s
o
f
d
e
p
re
s
s
i
o
n
a
n
d
a
n
x
i
e
t
y
a
re
m
e
a
s
u
r
e
d
u
s
i
n
g
DASS
-
2
1
p
a
ra
m
e
t
e
r.
I
n
to
t
a
l
,
2
2
,9
3
4
F
a
c
e
b
o
o
k
p
o
s
t
s
were
c
o
n
tri
b
u
te
d
a
s
tra
i
n
i
n
g
a
n
d
l
e
a
rn
i
n
g
d
a
ta
c
o
l
l
e
c
te
d
fr
o
m
J
u
l
y
2
0
1
7
u
n
ti
l
J
u
l
y
2
0
1
8
.
As
a
re
s
u
l
t
s
,
a
n
a
l
y
s
i
s
a
n
d
m
a
p
p
i
n
g
o
f
s
o
c
i
a
l
d
e
m
o
g
ra
p
h
i
c
s
o
f
u
s
e
rs
th
a
t
a
re
u
s
u
a
l
l
y
a
s
a
tri
g
g
e
r
o
f
d
e
p
re
s
s
i
o
n
,
a
n
d
a
n
x
i
e
ty
,
s
u
c
h
a
s
g
ri
e
f
,
i
l
l
n
e
s
s
,
h
o
u
s
e
h
o
l
d
a
f
fa
i
r
s
,
c
h
i
l
d
re
n
e
d
u
c
a
ti
o
n
a
n
d
o
t
h
e
r
s
a
re
a
v
a
i
l
a
b
l
e
.
Key
w
ords
:
Cl
o
s
e
d
-
L
o
o
p
,
DAS
S
-
2
1
,
d
e
p
re
s
s
i
o
n
a
n
d
a
n
x
i
e
ty
,
m
a
c
h
i
n
e
l
e
a
rn
i
n
g
,
N
a
ï
v
e
B
a
y
e
s
Copy
righ
t
©
2
0
1
9
Uni
v
e
rsi
t
a
s
Ahm
a
d
D
a
hl
a
n.
All
rig
ht
s
r
e
s
e
rve
d
.
1.
Int
r
o
d
u
ctio
n
S
oc
i
a
l
m
ed
i
a
as
m
an
i
f
es
ted
i
n
ev
er
y
d
a
y
l
i
f
e
a
l
l
o
w
s
p
e
op
l
e
t
o
s
ha
r
e
t
ho
u
gh
ts
an
d
s
ho
w
s
em
oti
on
s
tha
t
c
ha
r
a
c
ter
i
z
e
de
pres
s
i
on
an
d
an
x
i
et
y
.
F
ee
l
i
ng
s
of
w
ort
hl
e
s
s
ne
s
s
,
gu
i
l
t,
he
l
pl
es
s
ne
s
s
,
s
el
f
-
ha
tr
e
d
an
d
ot
he
r
as
pe
c
ts
.
S
oc
i
a
l
m
ed
i
a
ha
s
th
e
po
ten
t
i
a
l
as
a
too
l
f
or
m
ea
s
urin
g
an
d
m
on
i
tori
n
g
m
en
tal
he
al
th
de
pres
s
i
on
a
nd
an
x
i
et
y
.
S
oc
i
al
m
ed
i
a
c
an
he
l
p
de
tec
t
m
ea
s
ure
an
d
c
ap
ture
t
he
s
oc
i
a
l
c
on
tex
t
o
f
s
uff
erer
s
of
de
pres
s
i
on
an
d
an
x
i
et
y
i
n
t
he
po
p
ul
ati
on
[
1]
.
Cha
r
ac
teri
s
ti
c
s
of
B
i
g
D
ata
ar
e
da
ta
c
o
nte
n
t
q
ua
nt
i
t
y
(
V
ol
um
e),
da
ta
de
ns
i
t
y
(
V
e
l
oc
i
t
y
)
,
d
ata
f
orm
at
(
V
arie
t
y
)
,
qu
al
i
t
y
of
da
t
a
(
V
erac
i
t
y
)
.
B
i
g
da
t
a
c
an
a
l
s
o
b
e
r
ef
err
ed
as
da
t
a
tha
t
te
l
l
s
i
ts
ac
tu
al
i
nf
or
m
ati
on
t
ha
t
c
an
b
e
us
e
d
w
h
en
i
t
n
ee
d
ed
[2]
.
A
bi
g
da
t
a
an
a
l
y
s
i
s
c
on
du
c
te
d
to
r
a
nk
i
ng
,
f
i
nd
i
ng
an
d
i
de
nt
i
f
y
i
ng
m
ea
ni
n
gf
ul
i
nf
orm
ati
on
f
r
o
m
l
arge
un
s
tr
uc
tured
da
ta
b
y
a
na
l
y
z
i
ng
r
e
l
at
ed
de
t
ai
l
s
ba
s
e
d
o
n
s
eq
ue
nc
es
of
tex
tua
l
m
eta
-
da
t
a
proc
es
s
i
n
g
,
i
de
nti
f
i
c
at
i
on
,
an
d t
i
m
e s
erie
s
proc
es
s
i
ng
[2
]
.
T
he
DA
S
S
-
21
s
c
a
l
e
i
s
a
m
ea
s
urem
e
nt
s
c
al
e
th
at
i
s
us
ed
to
f
ac
i
l
i
tat
e
grou
pi
ng
an
d
c
at
eg
or
i
z
i
n
g
s
oc
i
a
l
m
ed
i
a
tex
ts
i
nto
a
be
s
t
m
atc
h
ed
d
ua
l
f
ac
tor
m
od
el
tha
t
s
ho
w
s
t
he
g
en
eral
n
eg
a
ti
v
e
ef
f
ec
ts
of
s
p
ec
i
f
i
c
f
ac
tors
o
f
Depres
s
i
o
n,
A
nx
i
et
y
,
a
nd
S
tr
es
s
i
n
ps
y
c
ho
l
o
gi
c
a
l
d
i
s
order
s
[3]
.
C
l
os
ed
-
L
oo
p
s
y
s
t
em
i
s
a
c
on
tr
ol
s
y
s
t
e
m
tha
t
us
e
s
f
ee
db
ac
k
w
hi
c
h
pa
r
t
l
y
c
om
es
f
r
o
m
the
ou
tp
ut
s
i
g
na
l
t
ha
t
i
s
f
ed
ba
c
k
as
an
i
n
pu
t
to
m
i
ni
m
i
z
e
err
ors
an
d
to
i
m
prov
e
ac
c
urac
y
on
t
he
s
y
s
t
em
[4]
.
S
oc
i
a
l
m
ed
i
a
c
an
be
us
ed
to
s
e
e
the
c
on
di
t
i
o
n
of
i
ts
us
ers
thro
u
gh
an
a
l
y
s
i
s
of
t
ex
ts
us
i
ng
t
he
N
aï
v
e
B
a
y
es
c
l
as
s
i
f
i
c
at
i
on
al
go
r
i
t
hm
as
the
m
os
t
wi
d
el
y
us
ed
[
5]
a
nd
f
as
t
c
l
as
s
i
f
i
c
at
i
on
of
Naï
v
e
B
a
y
es
wor
k
s
be
tte
r
a
nd
r
eq
u
i
r
es
o
nl
y
l
es
s
tr
ai
n
i
n
g
da
t
a
to
pr
e
di
c
t
c
l
as
s
es
f
r
o
m
a
c
ol
l
e
c
ti
on
of
da
t
a
tes
t
w
he
n
i
nd
ep
e
nd
e
nc
e
as
s
u
m
pti
on
s
a
pp
l
y
[6]
.
T
he
i
de
a
i
s
to
m
ea
s
ure
de
pres
s
i
o
n
an
d
an
x
i
et
y
th
r
ou
gh
t
ex
t
m
i
ni
ng
of
F
ac
eb
oo
k
,
Cl
os
ed
-
Lo
o
p
m
eth
od
us
ed
as
a
l
ea
r
n
i
ng
proc
es
s
an
d
Naïv
e
B
a
y
es
m
ac
hi
ne
as
tr
ai
n
i
ng
m
od
el
f
or tex
t c
l
as
s
i
f
i
c
ati
on
tha
t ra
i
s
es
s
ev
er
al
qu
es
t
i
on
s
as
f
ol
l
o
w
s
:
-
T
he
i
ni
t
i
a
l
s
i
g
ns
(
W
ha
t)
th
at
c
au
s
e d
e
pres
s
i
on
or a
nx
i
et
y
oc
c
ur i
n s
oc
i
a
l
m
ed
i
a
us
e
r
s
?
-
Caus
es
(
W
h
y
)
of
de
pres
s
i
o
n o
r
an
x
i
et
y
c
an
oc
c
ur to s
o
c
i
al
m
ed
i
a
us
ers
?
-
Ide
nt
i
f
i
c
ati
on
(
W
ho
)
of
de
pres
s
i
on
or
an
x
i
et
y
f
r
om
s
oc
i
al
m
ed
i
a
us
ers
?
-
Does
(
W
he
n) dep
r
es
s
i
o
n o
r
an
x
i
e
t
y
c
a
n o
c
c
ur to s
oc
i
a
l
m
ed
i
a u
s
ers
?
-
W
h
ere de
pres
s
i
on
or anx
i
et
y
oc
c
urs
?
Evaluation Warning : The document was created with Spire.PDF for Python.
◼
IS
S
N: 16
93
-
6
93
0
T
E
L
KO
M
NIK
A
V
ol
.
17
,
No
.
4
,
A
ug
us
t
20
19
:
20
87
-
20
97
2088
-
Ho
w
d
ep
r
es
s
i
o
n o
r
a
nx
i
et
y
oc
c
urs
, d
oe
s
i
t
af
f
ec
t s
oc
i
al
m
ed
i
a u
s
ers
?
T
he
ap
proac
h
b
y
[5]
,
m
ak
i
ng
a
de
c
i
s
i
on
s
u
pp
ort
s
y
s
t
em
to
c
ol
l
ec
t
s
i
gn
a
l
s
tha
t
p
r
od
uc
e
i
m
po
r
tan
t
p
att
erns
th
at
l
ea
d
to
c
h
i
l
d
a
bu
s
e
thro
ug
h
s
tr
uc
tured
an
d
un
s
tr
uc
tured
d
ata
i
n
f
r
ee
t
ex
t
us
i
ng
th
e
Ran
do
m
F
ores
t
Mo
de
l
m
ac
hi
ne
l
e
arni
ng
m
od
e
l
an
d
S
up
po
r
t
V
ec
tor
M
ac
hi
n
e
throu
gh
tex
t
c
l
as
s
i
f
i
c
at
i
on
a
l
g
orit
h
m
s
.
In
th
ei
r
r
es
ea
r
c
h
[6]
,
c
ho
os
e
a
s
m
art
s
y
s
t
e
m
ap
proac
h,
a
data
-
b
as
ed
de
c
i
s
i
on
m
od
el
.
I
nte
l
l
i
ge
nt
s
y
s
tem
s
an
d
m
ac
hi
ne
l
ea
r
n
i
n
g
m
od
el
s
thro
ug
h
ne
w
m
eth
od
ol
o
gi
es
i
n
i
nte
l
l
i
ge
nt
s
y
s
tem
s
i
n
r
ea
l
-
w
orl
d
b
us
i
ne
s
s
-
to
-
bu
s
i
n
es
s
(
B
2
B
)
s
al
es
f
orec
as
ti
ng
.
A
grou
p
of
s
al
es
ex
pe
r
ts
c
ol
l
ec
t
B
2
B
s
al
es
c
as
e
r
ec
ords
w
i
th
k
no
wn
r
es
ul
ts
t
o
s
up
po
r
t
t
he
tas
k
of
predi
c
ti
n
g
n
e
w
s
al
es
op
po
r
tun
i
ti
es
,
a
l
l
o
w
c
og
n
i
ti
v
e
ev
a
l
u
ati
on
s
of
m
od
el
s
b
y
u
s
ers
ba
s
ed
on
ne
w
i
ns
i
g
hts
.
In
[7
]
ex
pl
ai
n
ed
,
de
pres
s
i
on
i
s
a
ge
ne
r
a
l
m
en
tal
di
s
ord
er
tha
t
aris
e
s
w
i
t
h
f
ee
l
i
ng
s
of
de
pres
s
i
o
n,
l
os
s
of
i
nte
r
es
t
or
p
l
ea
s
ur
e,
d
ec
r
ea
s
e
d
en
erg
y
,
f
ee
l
i
n
gs
of
gu
i
l
t
or
i
nf
erio
r
i
t
y
,
di
s
turbe
d
s
l
ee
p
or
a
pp
e
ti
t
e
di
s
order
s
,
an
d
po
or
c
on
c
en
tr
ati
o
n.
W
ha
t's
m
ore,
de
pre
s
s
i
on
i
s
of
ten
ac
c
o
m
pa
ni
e
d
b
y
a
nx
i
et
y
s
y
m
p
tom
s
.
T
he
s
e
probl
em
s
c
an
be
c
om
e
c
hroni
c
or
r
ec
urr
en
t
a
nd
c
au
s
e
s
ub
s
ta
nti
al
da
m
ag
e
a
nd
the
ab
i
l
i
t
y
of
i
nd
i
v
i
du
al
s
to
c
arr
y
o
ut
the
i
r
da
i
l
y
r
ol
es
an
d res
p
on
s
i
bi
l
i
t
i
es
.
In
the
w
ors
t
c
on
d
i
t
i
on
s
,
d
ep
r
es
s
i
on
c
an
c
au
s
e
s
om
eo
ne
to
c
om
m
i
t s
ui
c
i
de
.
T
he
r
e
are
an
es
ti
m
ate
d
78
8
,00
0
s
ui
c
i
de
de
at
hs
wor
l
d
wi
de
.
S
ui
c
i
d
e
i
s
the
s
ec
on
d
l
ea
di
ng
c
au
s
e
of
de
at
h
am
on
g
c
hi
l
dre
n
ag
ed
15
-
2
9
y
e
ars
gl
o
ba
l
l
y
wi
t
h
a
g
l
o
ba
l
a
ge
s
ta
nd
ard
s
u
i
c
i
d
e
r
ate
of
10
.7
pe
r
10
0,
00
0
po
pu
l
at
i
on
.
T
hi
s
t
r
ag
ed
y
ha
s
l
on
g
-
term
eff
ec
ts
on
pe
o
pl
e
who
are
l
ef
t
be
hi
nd
an
d
greatl
y
af
f
ec
ts
f
a
m
i
l
i
es
,
c
om
m
un
i
ti
es
an
d
c
o
un
tr
i
es
(
W
HO
,
20
15
)
.
Me
an
whi
l
e
[8
]
,
i
n
th
ei
r
r
es
ea
r
c
h
us
i
ng
t
he
P
att
er
n
Rec
og
n
i
ti
on
A
l
g
orit
hm
on
B
i
g
Dat
a
s
oc
i
a
l
m
ed
i
a,
on
l
i
n
e
tr
an
s
ac
ti
on
s
,
ne
t
w
ork
s
en
s
ors
or
m
ob
i
l
e
de
v
i
c
es
.
T
hi
s
ap
proa
c
h
i
s
us
ed
i
n
t
he
a
pp
l
i
c
at
i
on
of
the
Com
pu
ter
V
i
s
i
on
f
i
e
l
d
an
d
i
m
ag
e a
n
al
y
s
i
s
w
i
th
l
arge
-
s
c
al
e c
ha
r
ac
teri
s
ti
c
s
.
Depres
s
i
o
n
i
s
on
e
of
the
m
o
s
t
de
v
as
tat
i
n
g
ps
y
c
h
i
atr
i
c
di
s
order
s
,
th
e
m
ai
n
c
au
s
e
of
di
s
ab
i
l
i
t
y
i
n
p
eo
p
l
e
i
n
t
ee
ns
an
d
prod
uc
ti
v
e
a
ge
s
.
T
r
ag
i
c
al
l
y
,
7
6%
of
pe
op
l
e
wi
th
m
od
erate
de
pres
s
i
o
n
an
d
6
1%
of
p
eo
p
l
e
wi
th
m
aj
or
de
pres
s
i
on
ne
v
er
ge
t
he
l
p
o
n
ti
m
e
[9]
.
T
he
n
[
10
]
ad
de
d,
m
en
tal
em
oti
on
al
di
s
order
s
are
t
he
s
am
e
term
as
ps
y
c
h
ol
og
i
c
al
di
s
tr
es
s
.
T
hi
s
c
on
di
t
i
on
i
s
a
c
on
di
ti
on
th
at
i
n
di
c
a
t
es
a
pe
r
s
on
i
s
e
x
p
erie
nc
i
ng
ps
y
c
h
ol
o
gi
c
a
l
c
ha
n
ge
s
tha
t
c
an
b
e
ex
pe
r
i
e
nc
ed
b
y
e
v
er
y
on
e
i
n
c
ertai
n
c
i
r
c
um
s
tan
c
es
bu
t
c
an
r
ec
o
v
er
as
be
f
ore.
T
he
prev
al
en
c
e
of
s
ev
ere
m
en
ta
l
d
i
s
order
s
i
n
th
e
In
do
n
es
i
a
n
p
op
u
l
at
i
on
i
s
1.7
pe
r
m
i
l
e.
M
os
t
s
ev
ere
m
en
ta
l
di
s
order
s
i
n DI
Y
o
g
y
ak
arta,
A
c
eh
,
S
o
uth
S
u
l
a
wes
i
,
B
a
l
i
an
d
Cent
r
a
l
J
a
v
a.
A
c
c
ordi
n
g
to
[1
1],
wor
r
y
a
nd
an
x
i
et
y
are
t
wo
di
f
f
erent
c
on
c
ep
ts
th
at
oc
c
ur
i
n
v
ari
ou
s
pa
r
ts
of
t
he
hu
m
an
bra
i
n.
A
nx
i
o
us
c
an
oc
c
ur
wi
t
ho
u
t
wor
r
y
,
an
d
wor
r
y
wi
t
ho
u
t
a
nx
i
et
y
,
bu
t
b
oth
ten
d
to
b
e
i
ns
ep
arabl
e
c
o
nd
i
t
i
o
ns
.
an
x
i
ou
s
or
i
gi
na
t
i
n
g
f
r
o
m
the
m
i
nd
,
oc
c
ur
i
n
the
m
i
nd
,
a
nd
i
n
v
ol
v
e
the
bra
i
n
t
hi
nk
i
ng
of
the
pref
r
on
ta
l
c
ortex
,
i
n
terac
ti
n
g
wi
th
t
he
l
i
m
bi
c
s
y
s
t
em
,
w
h
i
c
h
c
on
tr
ol
s
em
ot
i
on
s
an
d
b
as
i
c
hu
m
an
i
ns
ti
nc
ts
.
A
nx
i
et
y
i
s
al
wa
y
s
p
ortr
a
y
ed
ph
y
s
i
c
a
l
l
y
,
as
s
y
m
pto
m
s
,
ac
ti
on
s
,
a
nd
be
ha
v
i
ors
of
the
bo
d
y
tha
t
t
r
i
gg
er
brai
n
p
arts
to
t
urn
o
n
the
c
i
r
c
ui
t
of
f
ea
r
.
A
nx
i
et
y
c
an
ha
v
e
u
nc
on
s
c
i
ou
s
tr
ai
ts
as
a
i
n
di
c
at
i
on
s
of
c
au
s
e
an
d
wi
l
l
ap
pe
ar
as
s
y
m
pto
m
s
,
s
uc
h
as
ab
do
m
i
na
l
pa
i
n,
he
ad
ac
h
e,
or
s
ho
r
tne
s
s
of
bre
ath
[11
]
.
U
s
i
n
g
b
atc
h
proc
es
s
-
orie
nte
d
H
ad
o
op
a
nd
Ma
pR
ed
uc
e
o
n
B
i
g
Dat
a
f
or
de
c
i
s
i
on
m
a
k
ers
w
ho
ad
op
t
a
na
l
y
s
i
s
to
ac
hi
ev
e
ef
f
i
c
i
en
t
d
ec
i
s
i
o
ns
i
n
ac
c
orda
nc
e
wi
th
t
he
ap
p
l
i
c
at
i
on
do
m
ai
n.
T
he
ad
op
ti
o
n
of
a
m
e
c
ha
ni
s
m
b
y
th
e
Q
ue
r
y
Cont
r
o
l
l
er
(
Q
C)
tha
t
i
s
a
bl
e
to
m
an
ag
e
th
e
r
es
u
l
ts
c
arr
i
ed
ou
t
on
a
nu
m
be
r
of
proc
es
s
or
s
ea
c
h
r
es
po
ns
i
bl
e
f
or
ea
c
h
ex
i
s
ti
n
g
c
l
us
ter
[1
2]
.
B
as
ed
o
n
th
e
c
on
di
t
i
o
ns
[13
]
,
d
es
c
r
i
be
s
r
es
ea
r
c
h
on
th
e
i
m
po
r
ta
nc
e
of
op
e
n
d
i
g
i
ta
l
c
o
l
l
a
bo
r
ati
on
as
a
s
oc
i
ote
c
hn
i
c
al
s
y
s
t
em
tha
t
l
oo
s
e
l
y
b
i
n
ds
i
nd
i
v
i
d
ua
l
s
when
f
ac
i
ng
c
h
al
l
en
ge
s
i
n
an
a
l
y
z
i
ng
d
ata
wi
th
n
e
w
d
ata
s
ets
th
at
r
ea
c
h
di
f
f
erent
c
on
tex
ts
us
i
ng
n
e
w
c
om
pu
tat
i
on
a
l
m
od
el
s
an
d
an
a
l
y
t
i
c
al
te
c
hn
i
q
ue
s
.
T
he
n
[14]
,
c
o
nd
uc
t
r
es
e
a
r
c
h
r
el
ate
d
to
bi
g
da
ta
a
na
l
y
s
i
s
,
c
l
ou
d
c
om
pu
ti
n
g,
s
oc
i
al
ne
t
w
ork
i
ng
a
nd
m
ac
hi
ne
l
ea
r
ni
ng
o
n
c
om
pu
ter
v
i
s
i
o
n
f
ac
e
r
ec
og
ni
t
i
o
n
an
d
c
l
o
ud
c
om
pu
ti
ng
E
x
tr
em
e
Le
arni
ng
Ma
c
h
i
ne
s
tec
hn
i
qu
es
to
pe
r
f
or
m
ne
w
c
l
ou
d
-
ba
s
e
d
F
ac
e
T
ag
gi
ng
r
ec
o
gn
i
ti
o
n
on
s
oc
i
a
l
m
ed
i
a
an
d
da
t
ab
as
e
en
g
i
n
es
f
ac
e
r
ec
og
ni
t
i
on
i
s
i
n
the
c
l
ou
d
(
n
on
-
l
oc
a
l
)
an
d
o
pe
r
at
es
on
a
l
arge
-
s
c
al
e
i
m
ag
e
da
ta
ba
s
e
(
B
i
g
D
ata
)
.
T
h
e
us
er
i
n
terf
ac
e
c
om
m
un
i
c
ate
s
w
i
th
a
c
l
ou
d
-
b
as
ed
w
e
b
A
P
I
c
on
t
ai
n
i
ng
f
ac
e
r
ec
og
n
i
ti
on
m
a
c
hi
ne
s
an
d
f
ac
e
da
tab
as
e
s
c
on
s
i
s
ti
ng
of
f
ac
e d
ete
c
ti
on
,
ex
tr
ac
ti
o
n,
m
atc
hi
ng
an
d
s
o o
n
.
Res
ea
r
c
h
b
y
[1
5]
,
prop
os
e
r
eg
r
es
s
i
on
m
eth
od
s
thro
ug
h
E
x
te
nd
e
d
Ma
r
k
ov
Ch
ai
n
on
predi
c
t
i
on
s
of
th
e
arr
i
v
al
of
r
ai
n
us
i
n
g
oth
er
m
ac
hi
ne
l
e
arni
n
g
al
g
orit
hm
s
t
o
pred
i
c
t
r
ai
nf
al
l
ba
s
e
d
on
pre
di
c
ti
v
e
ac
c
urac
y
a
nd
wi
th
m
i
ni
m
al
c
orr
el
at
i
on
s
tha
t
ex
i
s
t
i
n
a
l
l
c
l
i
m
ate
s
.
Res
e
arc
h
ap
pro
ac
h
b
y
[1
6]
,
s
ho
w
s
a
s
um
m
a
r
y
of
the
pro
po
s
ed
s
y
s
t
em
arc
hi
tec
ture.
Int
erac
ti
v
e
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
M
NIK
A
IS
S
N: 1
69
3
-
6
93
0
◼
Depres
s
i
o
n a
n
d a
nx
i
ety
d
et
ec
ti
on
th
r
ou
gh
the
C
l
os
e
d
-
L
oo
p
me
t
ho
d u
s
i
ng
… (
S
et
i
y
o B
ud
i
y
an
t
o
)
2089
ex
pl
orat
i
o
n
of
l
arg
e
-
s
c
al
e
m
ul
ti
-
m
od
al
da
t
a
f
l
o
w
c
on
s
i
s
ts
of
r
ep
e
ate
d
p
aral
l
e
l
as
s
i
gn
m
en
ts
of
Ma
pR
ed
uc
e
to
f
i
n
d p
a
tte
r
n
s
th
at
of
ten
ap
pe
ar.
In
h
i
s
r
es
ea
r
c
h
a
pp
r
o
ac
h
[
17
]
,
us
e
l
ea
r
n
i
ng
a
l
go
r
i
thm
s
f
or
S
ha
l
l
o
w
an
d
De
ep
E
x
tr
e
m
e
Le
arn
i
ng
Ma
c
hi
ne
s
to
ex
pl
o
i
t
th
e
l
at
es
t
c
utt
i
n
g
-
ed
ge
da
t
a
tec
hn
ol
og
y
,
l
e
arn
i
ng
a
l
g
orit
hm
s
,
an
d
da
t
a
-
ba
s
ed
T
r
an
s
i
en
t
Del
a
y
P
r
e
di
c
ti
on
S
y
s
t
em
(
T
DP
S
)
s
tat
i
s
ti
c
s
t
oo
l
s
f
or
l
arg
e
-
s
c
al
e
r
ai
l
wa
y
ne
t
w
ork
s
.
W
hi
l
e
[1
8]
,
m
en
ti
o
ns
the
s
oc
i
a
l
m
ed
i
a
as
a
pri
v
a
te
m
ed
i
a
ha
s
em
erged
as
a
m
ed
i
u
m
to
c
o
m
m
un
i
c
ate
o
pi
n
i
on
s
,
produc
ts
an
d
s
erv
i
c
es
or
ev
en
po
l
i
t
i
c
al
an
d
p
ub
l
i
c
ev
en
ts
as
r
i
c
h
r
es
ou
r
c
es
f
or
s
en
ti
m
en
t
a
na
l
y
s
i
s
a
nd
t
ex
t
m
i
ni
n
g,
m
ac
hi
ne
l
ea
r
n
i
ng
,
s
tat
i
s
ti
c
a
l
an
d
c
o
m
pu
tat
i
on
a
l
l
i
n
gu
i
s
ti
c
s
.
T
hroug
h
op
en
s
o
urc
e
R
ap
p
l
i
c
at
i
on
s
,
c
l
as
s
i
f
i
c
ati
on
,
da
ta
m
i
ni
ng
tec
hn
i
qu
es
s
uc
h
as
grou
pi
ng
to
f
i
nd
as
s
oc
i
ati
on
s
an
d
pa
tt
erns
i
n
tex
t
a
nd
i
n
ex
pl
or
i
ng
a
nd
di
s
c
ov
erin
g n
e
w i
nf
or
m
ati
o
n a
n
d rel
ati
on
s
h
i
ps
i
n t
ex
tu
al
s
ou
r
c
es
o
n T
w
i
tte
r
d
ata
.
T
he
ap
proac
h
b
y
[
19
]
,
us
i
ng
Co
gn
i
ti
v
e
B
i
as
es
the
or
y
i
n
l
o
ok
i
ng
an
an
x
i
e
t
y
c
o
nd
i
t
i
o
ns
an
d t
he
l
i
m
i
ts
of
bi
as
as
s
oc
i
ate
d
wi
t
h t
hr
ea
ts
i
n a
nx
i
e
t
y
,
c
on
c
l
u
di
n
g t
ha
t t
he
bi
as
ha
s
c
o
m
pa
r
ab
l
e
m
ag
ni
tud
e
i
n
v
ari
ou
s
t
y
pe
s
of
an
x
i
ou
s
p
op
u
l
at
i
o
ns
.
T
hree
ex
pe
r
i
m
en
tal
pa
r
ad
i
g
m
s
ha
v
e
be
en
us
ed
t
o
s
tud
y
pa
tt
erns
r
el
a
t
ed
to
b
i
as
af
f
ec
ti
ng
a
nx
i
e
t
y
:
em
oti
on
a
l
s
tr
oo
p
,
d
ot
pro
b
e,
an
d
s
pa
ti
a
l
em
oti
on
al
c
u
i
ng
.
T
hi
s
s
ol
uti
on
of
f
ers
a
f
i
nd
i
ng
s
f
r
o
m
ex
i
s
ti
n
g
m
eta
-
an
al
y
z
es
.
M
ac
hi
n
e
l
e
arni
ng
an
d
tex
t
an
al
y
ti
c
s
ha
v
e
pro
v
en
i
nc
r
ea
s
i
n
gl
y
us
ef
ul
i
n
a
nu
m
be
r
of
he
al
t
h
r
el
a
ted
a
pp
l
i
c
ati
on
s
i
n
an
a
l
y
z
i
ng
of
on
l
i
ne
da
t
a
f
or
di
s
ea
s
e
ep
i
d
em
i
c
s
as
a
war
ni
n
g
s
i
g
ns
of
a
v
arie
t
y
of
m
en
tal
he
al
t
h
i
s
s
ue
s
s
uc
h
as
an
x
i
et
y
,
an
orex
i
a
an
d
de
pres
s
i
on
.
P
ers
on
a
l
bl
og
s
are
c
ol
l
e
c
ted
f
r
o
m
the
T
u
m
bl
r
A
P
I, a
nd
l
a
be
l
ed
t
h
em
ba
s
ed
on
whet
h
er th
e
y
ex
hi
b
i
te
d
[2
0]
.
S
em
an
ti
c
HMC
pro
po
s
ed
b
y
[2
1]
i
s
a
hi
erar
c
hi
c
a
l
m
ul
ti
-
l
ab
e
l
c
l
as
s
i
f
i
c
ati
on
u
s
ed
to
au
tom
ati
c
al
l
y
c
l
as
s
i
f
y
u
ns
tr
uc
tured
tex
t
do
c
um
en
ts
a
c
c
ordi
ng
t
o
a
n
on
tol
og
y
to
de
s
c
r
i
be
t
he
c
l
as
s
i
f
i
c
ati
on
m
od
el
th
at
f
oc
us
on
an
al
y
z
i
ng
th
e
da
t
a
i
n
B
i
g
Data
s
ou
r
c
es
.
In
h
i
s
r
es
ea
r
c
h
[22]
,
di
s
c
us
s
i
ng
d
ep
r
es
s
i
o
n
whi
c
h
i
s
a
s
erio
us
c
ha
l
l
en
ge
i
n
pe
r
s
on
a
l
an
d
p
ub
l
i
c
he
al
t
h.
T
he
propos
ed
m
eth
od
ol
o
g
y
us
es
c
r
o
w
ds
o
urc
i
ng
to
c
ol
l
ec
t
a
r
ep
orted
s
et
of
T
w
i
tte
r
us
ers
an
d
d
i
ag
no
s
e
d
w
i
t
h
c
l
i
n
i
c
al
de
pres
s
i
on
,
b
as
ed
o
n
a
s
ta
nd
ar
d
ps
y
c
h
om
etri
c
i
ns
tr
um
en
t
to
es
tab
l
i
s
h
a
s
tat
i
s
t
i
c
al
c
l
as
s
i
f
i
c
ati
on
th
at
prov
i
d
es
an
es
t
i
m
ate
of
the
r
i
s
k
of
de
pres
s
i
on
,
i
m
pl
em
en
ted
s
e
v
era
l
s
te
ps
to
m
ea
s
ure i
nd
i
v
i
du
a
l
s
oc
i
al
m
ed
i
a b
eh
av
i
or f
or one
y
e
a
r
be
f
ore the
on
s
et
of
de
pre
s
s
i
on
r
ep
orted.
R
es
ea
r
c
h
ai
m
s
b
y
[23
]
i
s
t
o
c
l
as
s
i
f
y
au
tho
r
s
of
t
w
ee
t
s
b
y
c
om
pa
r
i
ng
m
ac
hi
ne
l
ea
r
ni
ng
m
eth
od
s
l
i
k
e
l
og
i
s
ti
c
r
eg
r
e
s
s
i
on
an
d
n
ai
v
e
B
a
y
es
.
T
he
Na
ïv
e
B
a
y
es
c
l
as
s
i
f
i
c
a
ti
on
es
ti
m
ate
s
P
(
C)
an
d
P
(
X
|
C)
of
the
d
o
c
u
m
en
t
(
X
)
an
d
c
l
as
s
(
C)
,
the
th
e
r
el
ati
v
e
f
r
eq
ue
nc
y
of
ea
c
h
target
c
l
as
s
i
n
t
he
tr
ai
ni
n
g
d
ata
c
al
c
ul
ate
d
us
i
ng
the
i
n
d
ep
en
de
nc
e
as
s
um
pti
on
t
h
at
th
e
at
tr
i
b
ute
de
pe
nd
s
on
th
e
c
on
d
i
ti
o
ns
de
term
i
ne
d
b
y
t
arget
c
l
as
s
v
al
u
e.
T
he
ac
t
of
au
the
nti
c
at
i
n
g
i
nf
orm
ati
on
en
c
o
un
ter
ed
on
s
oc
i
a
l
m
ed
i
a
be
c
om
es
v
er
y
c
om
pl
e
x
.
T
he
pro
c
es
s
es
of
thi
s
ap
p
l
i
c
at
i
on
are
f
etc
hi
n
g
of
t
weet
s
,
pre
-
proc
es
s
i
n
g,
f
ea
t
ure
ex
tr
ac
ti
on
,
an
d
de
v
el
op
i
ng
a
m
ac
hi
ne
l
ea
r
n
i
n
g m
od
el
f
or c
l
as
s
i
f
i
c
ati
o
n
.
Com
pu
ter
ne
t
w
ork
tec
hn
ol
og
y
as
a
m
ed
i
um
o
f
c
o
mm
un
i
c
ati
on
be
t
w
ee
n
de
v
i
c
es
ha
s
m
ad
e
s
i
gn
i
f
i
c
an
t
progr
es
s
i
n
t
erm
s
of
c
o
m
m
un
i
c
ati
on
m
ed
i
a.
It
i
s
on
e
of
the
f
a
s
tes
t
gro
w
i
ng
i
nte
r
n
et
ap
p
l
i
c
a
ti
o
ns
no
w
[
24
].
Data
tr
af
f
i
c
ha
s
i
nc
r
ea
s
ed
b
y
1
31
%
s
i
nc
e
20
1
1
h
as
en
c
ou
r
ag
e
d
s
o
m
e
m
ob
i
l
e
op
era
tors
i
n
E
urop
e
t
o
i
n
v
es
t
i
n
m
ac
hi
ne
-
to
-
m
ac
hi
ne
c
om
m
un
i
c
ati
on
s
[25
]
a
nd
protoc
ol
r
ou
t
i
n
g c
an
i
m
prov
e t
he
pe
r
f
orm
an
c
e o
f
th
e n
et
w
ork
, c
an
i
m
prov
e t
r
ou
g
h
pu
t a
nd
r
ed
uc
e
ha
nd
ov
er
d
el
a
y
[2
6].
T
he
t
ec
hn
o
l
og
i
es
tha
t
u
nd
er
l
i
e
t
he
ef
f
ec
ti
v
en
es
s
of
3G
-
W
i
F
i
of
f
l
oa
d
i
ng
are
i
n
c
on
s
ta
nt
de
v
e
l
op
m
en
t.
A
n
i
m
po
r
tan
t
s
uc
h
tec
h
no
l
og
y
are
the
C
og
n
i
ti
v
e
Rad
i
os
,
whi
c
h
w
or
k
b
y
i
nt
el
l
i
g
en
t
l
y
ad
j
us
t
i
ng
bo
t
h s
i
gn
al
s
tr
e
ng
t
h a
n
d res
ou
r
c
e u
s
e
[27
]
.
2.
Re
se
a
r
ch M
eth
o
d
T
he
pu
r
po
s
e
of
thi
s
s
tud
y
i
s
to
ov
erlo
ok
of
op
po
r
tu
ni
t
i
es
i
n
b
i
g
da
ta
an
d
m
ac
hi
ne
l
ea
r
n
i
n
g
thro
ug
h
Naï
v
e
B
a
y
e
s
tex
t
c
l
as
s
i
f
i
c
ati
on
us
i
n
g
te
x
t
m
i
ni
n
g
s
oc
i
al
m
ed
i
a,
to
d
ete
c
t
an
d
an
a
l
y
s
e
de
pr
es
s
i
on
an
d
an
x
i
et
y
throu
gh
t
he
Cl
os
e
d
-
Lo
op
m
eth
od
a
nd
D
A
S
S
-
2
1.
2.1
. Init
i
atio
n
and
Iden
t
if
ic
atio
n
of
Rev
iew
C
om
bi
na
ti
on
of
k
e
y
wor
ds
as
wel
l
as
i
n
l
o
w
erc
as
e
l
et
ters
wi
th
ou
t
q
uo
t
ati
on
m
ark
s
an
d
ea
c
h
w
or
d
s
ep
ara
ted
b
y
a
s
pa
c
e
t
ha
t
r
e
pres
en
t
the
o
bj
ec
ti
v
es
of
the
r
es
ea
r
c
h,
na
m
el
y
"
B
i
g
Da
ta
"
,
"
Ma
c
h
i
ne
L
ea
r
ni
n
g"
,
"
T
ex
t
Mi
n
i
ng
"
,
"
Depr
es
s
i
on
"
an
d
"
A
nx
i
e
t
y
"
an
d
"
Cl
os
ed
-
Lo
op
"
.
Num
be
r
of
c
o
m
bi
na
ti
o
ns
of
k
e
y
wor
ds
us
e
d
i
n
I
E
E
E
x
pl
or
e
Di
gi
t
al
Li
brar
y
j
o
urnal
s
ea
r
c
he
s
pro
du
c
e
d 6
groups
of
k
e
y
w
ords
6,
1
5,
2
0,1
5
, 6
an
d
1
c
om
bi
na
ti
o
ns
.
Evaluation Warning : The document was created with Spire.PDF for Python.
◼
IS
S
N: 16
93
-
6
93
0
T
E
L
KO
M
NIK
A
V
ol
.
17
,
No
.
4
,
A
ug
us
t
20
19
:
20
87
-
20
97
2090
3.
Re
sult
s
a
n
d
A
n
al
y
s
is
A
n
um
be
r
of
12
8
pu
b
l
i
c
ati
o
ns
f
r
o
m
the
I
E
E
E
X
pl
ore
o
bt
ai
n
ed
as
m
ai
n
d
ata
b
as
e,
th
e
ne
x
t
ph
as
e
was
to
s
tr
i
p t
he
r
es
ul
ts
b
y
us
i
n
g t
h
e s
ta
ge
s
of
r
e
v
i
e
w
i
ng
t
he
l
i
teratur
e
a
bs
tr
ac
t, s
ug
ge
s
t
i
ng
de
v
el
op
m
en
t
a
nd
c
on
c
l
us
i
on
s
an
d
al
s
o
r
ev
i
e
wi
n
g
the
e
nti
r
e
c
o
nte
n
ts
of
the
l
i
terat
ure.
T
he
r
es
ea
r
c
h
f
r
a
m
ew
ork
w
as
de
v
e
l
o
pe
d
t
o
group
an
d
c
ate
go
r
i
z
e
s
oc
i
al
m
ed
i
a
tex
ts
i
nto
s
pe
c
i
f
i
c
f
ac
tors
o
f
de
pres
s
i
on
,
a
nx
i
et
y
,
s
tr
es
s
(
DA
S
)
.
S
oc
i
al
m
ed
i
a
tex
ts
are
c
ol
l
ec
te
d
ac
c
ordi
ng
t
o
i
de
nti
t
y
,
n
am
e,
ge
nd
er,
ag
e
an
d
ge
og
r
a
ph
i
c
i
nf
or
m
ati
on
.
C
he
c
k
c
on
di
ti
on
f
un
c
ti
o
n
tha
t
f
ou
nd
i
n
DA
S
S
-
21
b
ee
n
a
pp
l
i
e
d
t
o
ha
v
e
a
pr
ob
a
bi
l
i
t
y
v
al
u
e
a
nd
a
c
on
di
ti
o
n
m
ar
k
er.
Lo
op
i
ng
i
s
c
arr
i
ed
ou
t u
nti
l
ex
i
s
ti
n
g t
e
x
ts
h
av
e
be
e
n c
he
c
k
ed
as
s
ho
w
n
i
n
Fig
ure
1
a
nd
T
ab
l
e 1
.
F
i
gu
r
e
1
.
T
he
r
es
ea
r
c
h m
eth
od
propos
e
d
i
n t
he
s
tu
d
y
T
ab
l
e 1
.
T
he
r
es
e
arc
h a
l
go
r
i
thm
propo
s
ed
i
n t
he
s
tu
d
y
P
s
e
u
d
o
C
o
d
e
I
nput
:
S
oc
i
a
l
Med
i
a
T
e
x
t
s
$
t
e
k
s
=
$
c
o
n
n
-
>d
a
t
a
b
a
s
e
(
)
;
//read media social texts
if
(
$
t
e
k
s
!
=
0
)
t
h
e
n
{
//database
not empty
w
h
il
e
(
$
r
e
s
u
lt
s
=>
a
r
r
a
y
(
$
t
e
k
s
)
)
{
//convert as array
$
s
t
r
ing
=
c
lea
n
e
r
(
$
r
e
s
u
lt
s
)
;
//
Text Cleansing
f
o
r
(
$
i=0
;
$
i
<
2
1
;
$
i++)
{
//looping parameter DASS
-
21
$
c
las
s
i
f
ier
-
>le
a
r
n
(
$
d
a
s
s
2
1
_
id[
$
i]
,
T
y
p
e
(
$
i))
;
//Texts in Bahasa Indonesia
$
c
las
s
i
f
ier
-
>le
a
r
n
(
$
d
a
s
s
2
1
_
e
n
g
[
$
i
]
,
Ty
p
e
(
$
i))
;
//Texts in english
}
//end for
$
s
t
a
t
u
s
=
$
c
las
s
i
f
ier
-
>g
u
e
s
s
(
$
s
t
r
in
g
)
;
//save status
}
//end while
}
//end if
e
ls
e
{
error
(
”
R
e
a
d
ing
d
a
t
a
Failed
”
)
;
}
$
s
t
a
t
u
s
=
a
r
r
a
y
(
”
D
E
P
R
E
S
S
I
ON
/
A
N
X
I
E
TY
”
,
”
P
r
o
b
a
b
il
it
y
V
a
lue
”
)
Out
put:
S
t
a
t
us
a
nd
P
ro
babi
l
i
t
y
v
a
l
ue
3.1
. D
ata
S
o
u
r
ce
s
D
ata
c
ol
l
ec
te
d
f
r
o
m
74
9
F
ac
eb
oo
k
ac
c
ou
nts
,
an
ac
c
ou
nt
c
l
e
an
s
i
ng
proc
es
s
do
ne
b
y
s
el
ec
ti
ng
s
oc
i
al
m
ed
i
a
ac
c
o
un
ts
f
r
o
m
a
pe
r
s
on
na
m
e,
as
i
n
to
ta
l
the
r
e
i
s
6
54
p
ers
on
a
l
ac
c
ou
n
ts
r
es
ul
ted
.
R
an
d
om
s
el
ec
ti
o
n
us
i
ng
S
l
o
v
i
n
m
i
ni
m
al
s
a
m
pl
e
f
or
m
ul
a
i
s
ap
p
l
i
ed
wi
th
a
m
argi
n
of
err
or
of
5%
or
0.0
5
.
T
he
r
e
i
s
24
8
ac
c
o
un
ts
ha
s
b
ee
n
s
el
ec
ted
wi
t
h
10
9
w
om
en
an
d
1
39
m
en
i
n d
eta
i
l
s
.
3.2. D
epre
ss
ion
and
A
n
xi
ety
Behav
ior
S
oc
i
a
l
m
ed
i
a
t
ex
t
c
l
as
s
i
f
i
c
ati
o
n
ba
s
ed
o
n
a
d
ata
s
e
t
r
ep
r
es
en
t
ed
on
B
ah
as
a
Ind
on
es
i
a
an
d
E
ng
l
i
s
h
throu
gh
a
m
ac
hi
n
e
l
ea
r
n
i
n
g
proc
es
s
us
i
n
g
th
e
Naï
v
e
B
a
y
es
a
l
go
r
i
th
m
as
a
tr
ai
ni
ng
proc
es
s
and
pa
r
am
ete
r
s
i
n
DA
S
S
-
21
as
a
l
e
arni
ng
pro
c
es
s
.
B
as
ed
on
t
he
ab
o
v
e
proc
c
es
s
,
16
5
F
ac
eb
oo
k
ac
c
ou
nts
w
i
th
a
ten
de
nc
y
to
de
pres
s
i
on
an
d
an
x
i
et
y
r
es
u
l
te
d
th
at
wer
e
i
n
the
r
an
ge
of
y
ea
r
s
20
0
9
-
20
1
8
as
s
ho
wn
i
n
F
i
g
ure
2
(
a)
a
nd
(
b).
A
m
ap
of
d
ep
r
es
s
i
o
n
a
nd
an
x
i
et
y
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
M
NIK
A
IS
S
N: 1
69
3
-
6
93
0
◼
Depres
s
i
o
n a
n
d a
nx
i
ety
d
et
ec
ti
on
th
r
ou
gh
the
C
l
os
e
d
-
L
oo
p
me
t
ho
d u
s
i
ng
… (
S
et
i
y
o B
ud
i
y
an
t
o
)
2091
tr
en
ds
d
i
s
tr
i
bu
ti
o
n
f
r
o
m
F
ac
eb
oo
k
s
ho
wn
i
n
F
i
g
ure
3
(
a)
an
d
a
de
t
ai
l
ed
m
ap
of
Ind
on
es
i
a
f
r
om
ea
c
h c
on
di
t
i
on
an
d s
prea
di
ng
of
de
pres
s
i
on
an
d
an
x
i
e
t
y
s
ho
wn
i
n
F
i
gu
r
e
3
(
b).
(
a)
(
b)
F
i
gu
r
e
2
.
(
a) D
ep
r
es
s
i
o
n a
n
d A
nx
i
ou
s
p
os
ts
pe
r
us
er,
(
b) Num
be
r
of
c
l
ea
ne
d
po
s
t
s
i
n t
h
e ran
ge
of
y
ea
r
s
20
18
-
20
09
f
r
om
to
tal
=
2
2.9
34
p
os
ts
(
a)
(
b)
F
i
gu
r
e
3
.
(
a) T
he
te
nd
e
nc
y
of
th
e
de
pres
s
i
on
an
d
an
x
i
ou
s
c
i
t
y
grou
ps
,
(
b)
ge
og
r
ap
h
i
c
al
m
ap
of
th
e
di
s
tr
i
b
uti
on
of
de
pres
s
i
o
n (
bl
u
e) anx
i
ou
s
(
y
e
l
l
o
w
)
a
nd
s
tr
es
s
(
pu
r
pl
e)
Evaluation Warning : The document was created with Spire.PDF for Python.
◼
IS
S
N: 16
93
-
6
93
0
T
E
L
KO
M
NIK
A
V
ol
.
17
,
No
.
4
,
A
ug
us
t
20
19
:
20
87
-
20
97
2092
3.2
.1
. Init
ial
S
ign
s
(
W
h
at)
t
h
at
Cause D
epre
ss
ion
o
r
A
n
xie
t
y
?
In
T
ab
l
e
2,
th
e
to
p
50
l
i
s
ts
s
ho
w
t
he
c
au
s
es
of
de
pr
es
s
i
on
an
d
an
x
i
et
y
as
ex
p
r
es
s
ed
throug
h
t
he
po
s
ts
of
F
ac
eb
oo
k
.
T
he
s
e
l
ec
ti
on
of
tex
t
i
s
de
t
erm
i
ne
d
ba
s
e
d
on
the
h
i
gh
es
t
l
ev
el
of
proba
bi
l
i
t
y
of
de
pres
s
i
on
an
d a
nx
i
et
y
f
r
o
m
ea
c
h p
os
t t
e
x
t.
T
ab
l
e 2
. T
he
P
r
ob
a
bi
l
i
t
y
of
T
ex
t S
ho
w
i
ng
E
arl
y
S
i
gn
s
of
Depres
s
i
on
a
nd
A
nx
i
et
y
D
e
p
r
e
s
s
ion
A
n
x
iet
y
N
o
.
U
s
e
r
s
P
r
o
b
.
N
o
.
U
s
e
r
s
P
r
o
b
.
N
o
.
U
s
e
r
s
P
r
o
b
.
N
o
.
U
s
e
r
s
P
r
o
b
.
1
8
9
.
8
9
26
9
7
.
3
9
1
78
9
.
1
1
26
154
6
.
2
8
2
46
9
.
8
5
27
13
7
.
3
5
2
48
9
.
0
6
27
74
6
.
0
2
3
37
9
.
7
9
28
5
7
.
2
4
3
222
8
.
8
7
28
80
5
.
8
3
4
78
9
.
7
3
29
12
7
.
1
5
4
135
8
.
7
5
29
26
5
.
6
3
5
72
9
.
6
7
30
70
7
.
0
3
5
17
8
.
5
9
30
43
5
.
5
6
19
9
.
6
6
31
31
6
.
8
3
6
65
8
.
5
5
31
34
5
.
4
8
7
6
9
.
6
4
32
22
6
.
8
7
32
8
.
4
4
32
18
5
.
3
8
34
9
.
5
9
33
43
6
.
7
6
8
46
8
.
3
2
33
16
5
.
2
7
9
24
9
.
5
4
34
10
6
.
7
6
9
4
8
.
3
34
218
5
.
1
5
10
49
9
.
5
2
35
74
6
.
6
4
10
206
8
35
2
5
.
0
9
11
80
9
.
5
1
36
56
6
.
6
11
57
7
.
9
7
36
166
5
.
0
7
12
32
9
.
4
8
37
4
6
.
2
4
12
83
7
.
8
5
37
94
5
.
0
4
13
83
9
.
2
2
38
21
6
.
2
3
13
24
7
.
8
2
38
61
5
.
0
3
14
28
9
.
1
1
39
65
6
.
2
14
136
7
.
6
4
39
131
4
.
9
15
25
8
.
9
1
40
48
5
.
8
7
15
31
7
.
5
9
40
41
4
.
8
7
16
53
8
.
8
9
41
1
5
.
8
5
16
49
7
.
5
3
41
8
4
.
8
17
55
8
.
8
9
42
51
5
.
7
17
147
7
.
3
7
42
230
4
.
7
6
18
15
8
.
6
9
43
26
5
.
3
8
18
192
7
.
3
3
43
1
4
.
7
2
19
16
8
.
6
8
44
69
5
.
3
4
19
37
7
.
2
3
44
35
4
.
7
1
20
17
8
.
5
2
45
89
5
.
2
3
20
185
7
.
0
8
45
55
4
.
5
7
21
39
8
.
4
46
84
5
.
2
21
246
7
.
0
6
46
6
4
.
5
6
22
91
7
.
9
8
47
18
5
.
1
1
22
39
7
47
10
4
.
5
2
23
57
7
.
6
7
48
61
4
.
8
8
23
150
6
.
5
7
48
219
4
.
5
1
24
52
7
.
6
6
49
33
4
.
7
1
24
91
6
.
4
4
49
25
2
7
.
5
6
50
66
4
.
6
8
25
72
6
.
3
4
50
3.2
.2
.
Caus
es
(
W
h
y
)
of
De
p
r
es
s
ion
o
r
A
n
x
iet
y
ca
n
O
cc
u
r
to
S
o
cia
l M
edia Us
er
s
?
B
as
ed
o
n
the
us
er’s
tex
t
po
s
t
i
n
F
ac
eb
o
ok
,
da
ta
c
l
ea
n
i
ng
s
uc
h
as
pu
nc
tu
ati
on
,
n
u
m
be
r
s
an
d
r
ea
d
ab
l
e
c
ha
r
ac
ters
t
h
at
5
,65
1
wor
ds
ar
e
ob
ta
i
n
e
d,
s
o
th
at
s
e
v
era
l
k
e
y
wor
ds
c
an
be
s
ho
wn
as
c
au
s
es
of
de
pr
es
s
i
on
an
d
an
x
i
et
y
as
s
ho
w
n
i
n
T
ab
l
e
3
w
i
t
h
at
l
e
as
t
w
or
ds
10
ti
m
es
ap
pe
aranc
e
.
T
ab
l
e 3
.
T
hi
n
gs
th
a
t
Ca
us
e
Dep
r
es
s
i
o
n
a
nd
A
nx
i
et
y
N
o
.
W
o
r
d
S
u
m
N
o
.
W
o
r
d
S
u
m
N
o
.
W
o
r
d
S
u
m
N
o
.
W
o
r
d
S
u
m
1
Tuh
a
n
62
16
K
e
lua
r
g
a
19
31
N
e
p
h
e
w
14
46
B
e
laja
r
11
2
A
n
a
k
52
17
Foto
19
32
J
a
k
a
r
t
a
13
47
A
ll
a
h
11
3
S
e
la
m
a
t
49
18
Ti
m
e
18
33
B
r
o
t
h
e
r
13
48
Fil
m
11
4
H
idu
p
49
19
Y
e
a
r
18
34
N
a
t
a
l
13
49
A
ir
11
5
Or
a
n
g
45
20
M
a
n
u
s
ia
18
35
Tea
m
13
50
P
e
r
a
s
a
a
n
11
6
Go
d
37
21
H
a
t
i
17
36
A
c
a
r
a
13
51
W
o
r
k
11
7
Fa
m
il
y
35
22
H
o
m
e
17
37
M
a
m
a
13
52
H
a
s
il
11
8
Go
ld
32
23
S
a
lah
16
38
W
o
r
ld
12
53
B
a
li
10
9
Tan
g
a
n
31
24
H
e
a
r
t
16
39
K
u
a
t
12
54
M
o
m
10
10
D
a
y
30
25
S
e
m
o
g
a
16
40
B
e
lov
e
d
12
55
Ter
i
m
a
k
a
s
ih
10
11
Tak
u
t
27
26
K
a
s
ih
15
41
S
is
t
e
r
12
56
S
c
h
o
o
l
10
12
Te
m
a
n
25
27
J
a
lan
15
42
M
o
r
n
ing
12
57
S
e
k
o
lah
10
13
L
if
e
22
28
C
h
r
is
t
m
a
s
15
43
H
o
li
d
a
y
12
58
Y
e
s
u
s
10
14
B
les
s
20
29
E
n
joy
14
44
D
o
a
12
59
Lagu
10
15
S
e
h
a
t
19
30
Fr
ien
d
14
45
W
o
men
12
60
P
e
a
c
e
10
3.2
.3
.
Iden
t
if
ica
t
ion
(
W
h
o
)
of
Depre
ss
ion
o
r
A
n
xie
t
y
f
r
o
m
S
o
c
ial
M
edia Use
r
s
?
B
ase
d
on
i
n
f
or
m
a
t
i
on
o
f
Fa
ceb
oo
k
use
r
,
sho
w
n
de
m
o
g
r
a
ph
i
c
da
t
a
ba
s
ed
on
g
en
de
r
i
n
T
ab
l
e
4,
e
m
pl
oy
m
en
t
s
t
atus
i
n
T
ab
l
e
5
.
Me
n
ha
v
e
a
hi
g
he
r
te
nd
e
nc
y
(
53
.
0%)
to
ex
pe
r
i
e
nc
e
de
pres
s
i
on
an
d
an
x
i
et
y
t
ha
n
w
om
en
(
4
6.4
%)
an
d
G
r
ou
ps
of
us
ers
wi
th
ha
s
a
J
o
b
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
M
NIK
A
IS
S
N: 1
69
3
-
6
93
0
◼
Depres
s
i
o
n a
n
d a
nx
i
ety
d
et
ec
ti
on
th
r
ou
gh
the
C
l
os
e
d
-
L
oo
p
me
t
ho
d u
s
i
ng
… (
S
et
i
y
o B
ud
i
y
an
t
o
)
2093
s
tat
us
ha
v
e
a
hi
g
he
r
te
nd
e
nc
y
to
ex
p
erie
nc
e
de
pres
s
i
on
an
d
an
x
i
et
y
tha
n
ot
he
r
g
r
ou
ps
of
us
ers
.
T
he
ag
e
grou
p
41
-
5
0
y
e
ar
s
ha
s
a
hi
g
he
r
ten
de
nc
y
to
ex
pe
r
i
e
nc
e
de
pr
es
s
i
on
a
n
d
an
x
i
e
t
y
t
ha
n
the
ag
e
gro
up
un
de
r
30
y
e
ars
an
d
a
bo
v
e
51
y
e
ars
a
s
s
ho
w
n
i
n
F
i
gu
r
e
s
3
(
a)
a
nd
3
(
b).
Us
er
groups
wi
th
Un
i
v
ers
i
t
y
ed
uc
ati
o
n o
r
eq
u
i
v
al
en
t
ha
v
e
a
hi
g
he
r
te
nd
en
c
y
to
ex
pe
r
i
e
nc
e d
e
pres
s
i
on
an
d
an
x
i
et
y
.
T
he
gro
up
of
us
ers
wi
th
M
arr
i
ed
s
tat
us
al
s
o
ha
s
a
h
i
gh
er
te
nd
e
nc
y
t
o
ex
p
erie
nc
e
de
pres
s
i
o
n
an
d
an
x
i
et
y
.
W
he
r
e
s
i
n
gl
e
s
t
atu
s
ten
ds
to
be
de
pres
s
ed
an
d
an
x
i
ou
s
whi
c
h
i
s
q
ui
t
e
hi
g
h a
s
s
ho
wn i
n Fi
gu
r
e
4 a
nd
Fi
gu
r
e
5.
T
ab
l
e 4
.
Us
ers
b
y
S
ex
G
r
o
up
W
o
men
M
e
n
Total
77
88
165
4
6
.
4
%
5
3
.
0
%
1
0
0
.
0
%
T
ab
l
e 5
.
Us
ers
A
c
c
ordi
n
g
t
o
J
ob
S
tat
us
E
m
p
loy
e
e
Ot
h
e
r
s
Total
160
5
165
9
7
.
0
%
3
.
0
%
1
0
0
.
0
%
(
a)
(
b)
F
i
gu
r
e
3
.
(
a) Us
ers
b
y
a
ge
group,
(
b) us
ers
ac
c
ordi
n
g t
o b
i
r
t
h d
a
te
i
nf
orm
ati
on
; n
=
16
5.
Evaluation Warning : The document was created with Spire.PDF for Python.
◼
IS
S
N: 16
93
-
6
93
0
T
E
L
KO
M
NIK
A
V
ol
.
17
,
No
.
4
,
A
ug
us
t
20
19
:
20
87
-
20
97
2094
F
i
gu
r
e
4.
T
en
de
nc
y
of
de
pr
es
s
i
on
a
nd
an
x
i
e
t
y
i
n
ed
uc
ati
o
n b
ac
k
ground
F
i
gu
r
e
5
.
T
en
de
nc
y
of
de
pr
es
s
i
on
a
nd
an
x
i
e
t
y
i
n m
arr
i
ed
s
tat
us
3.2
.4
.
Do
es
(
w
h
en)
Depres
sion
o
r
A
n
xie
t
y
ca
n
O
c
c
u
r
to
S
o
ci
al
M
edia Use
r
s
?
Mo
r
e
d
eta
i
l
e
d
d
es
c
r
i
pti
o
n
o
f
the
nu
m
be
r
of
de
pres
s
ed
an
d
a
nx
i
o
us
ten
de
nc
i
es
of
us
ers
i
s
ba
s
ed
on
the
a
v
erag
e
nu
m
be
r
pe
r
m
on
th
an
d
th
e
a
v
erag
e
n
um
be
r
pe
r
da
y
i
n
th
e
r
an
ge
2017
-
20
1
8 a
s
i
n Fi
gu
r
e
6
(
a) and
F
i
g
ure 6
(
b).
3.2
.5
.
W
h
er
e
Depr
es
s
ion
o
r
A
n
xie
t
y Occu
r
s?
B
as
ed
o
n
da
t
a
ob
t
ai
n
ed
,
t
h
en
the
i
nf
orm
ati
on
of
the
top
30
c
i
ti
es
was
c
ol
l
ec
t
ed
w
i
th
the
hi
g
he
s
t
n
um
be
r
of
de
pres
s
i
on
an
d
an
x
i
et
y
te
nd
e
nc
i
es
as
i
n
F
i
g
ure
7.
It
was
f
ou
nd
th
at
t
he
bi
g
c
i
ti
es
(
J
ak
arta,
Me
da
n,
B
a
nd
un
g,
S
urab
a
y
a)
s
ho
wed
the
gre
at
es
t
nu
m
be
r
of
de
pres
s
i
on
an
d
an
x
i
et
y
t
en
d
en
c
i
es
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
M
NIK
A
IS
S
N: 1
69
3
-
6
93
0
◼
Depres
s
i
o
n a
n
d a
nx
i
ety
d
et
ec
ti
on
th
r
ou
gh
the
C
l
os
e
d
-
L
oo
p
me
t
ho
d u
s
i
ng
… (
S
et
i
y
o B
ud
i
y
an
t
o
)
2095
(
a)
(
b)
F
i
gu
r
e
6
.
(
a) N
um
be
r
of
po
s
ts
of
an
x
i
ou
s
an
d
,
(
b)
d
ep
r
es
s
i
on
i
n u
ni
ts
of
da
y
s
p
er
m
on
th
F
i
gu
r
e
7
.
T
r
en
d o
f
de
pres
s
i
o
n (bl
ue
)
a
nd
an
x
i
et
y
(
oran
ge
)
–
C
i
t
y
Evaluation Warning : The document was created with Spire.PDF for Python.
◼
IS
S
N: 16
93
-
6
93
0
T
E
L
KO
M
NIK
A
V
ol
.
17
,
No
.
4
,
A
ug
us
t
20
19
:
20
87
-
20
97
2096
3.2
.6
.
Ho
w
Depres
sion
o
r
A
n
xi
e
t
y
O
c
curs
, do
es
it
A
f
f
ec
t
S
o
cia
l M
edia Use
r
s
?
B
as
ed
o
n
da
t
a
an
a
l
y
s
i
s
,
th
ere
are
no
ex
pres
s
i
o
ns
or
s
tat
em
en
ts
fr
o
m
F
ac
eb
oo
k
us
ers
tha
t
c
an
b
e
att
r
i
bu
te
d
tha
t
i
n
the
pre
v
i
ou
s
po
s
t
tha
t
c
an
s
ho
w
as
t
he
c
au
s
e
of
de
pres
s
i
o
n o
r
a
nx
i
o
us
.
4.
Co
n
clus
ion
T
he
i
n
i
ti
al
s
i
gn
s
of
de
pre
s
s
i
on
a
nd
an
x
i
et
y
ha
s
be
en
s
e
en
throu
gh
F
ac
eb
oo
k
tex
t
an
a
l
y
z
i
ng
.
B
as
e
d
o
n
i
t
w
a
s
f
ou
nd
tha
t
s
tat
em
en
ts
t
hroug
h
s
oc
i
a
l
m
ed
i
a
t
ex
t
ha
s
r
el
a
ti
on
t
o
de
pres
s
i
o
n
a
nd
a
nx
i
et
y
c
an
a
pp
r
oa
c
h
the
c
o
nd
i
ti
on
s
ex
pe
r
i
en
c
ed
b
y
us
ers
.
T
he
s
ou
r
c
e
of
de
pres
s
i
o
n
an
d
an
x
i
et
y
,
s
u
c
h
as
grie
f
,
i
l
l
ne
s
s
es
,
ho
us
eh
o
l
d
af
f
ai
r
s
,
s
c
ho
ol
c
hi
l
dr
en
an
d
oth
ers
.
T
he
proc
es
s
of
de
pres
s
i
o
n
an
d
an
x
i
et
y
c
an
l
as
t
s
h
ort,
m
ed
i
um
or
l
on
g
t
i
m
e
de
pe
nd
i
ng
on
c
on
di
t
i
o
ns
a
nd
s
oc
i
al
d
em
og
r
ap
h
i
c
b
ac
k
ground
of
us
er
s
s
uc
h
as
ge
n
de
r
,
ag
e,
ag
e
of
m
arr
i
ag
e,
ed
uc
at
i
on
an
d
ot
he
r
th
i
n
g
s
.
In
th
e
f
utu
r
e,
us
i
ng
tex
t
f
r
o
m
T
w
i
tte
r
,
Ins
tag
r
am
,
P
ath
an
d
ot
he
r
s
oc
i
al
m
ed
i
a
s
ou
r
c
es
c
an
be
us
ed
to
d
e
v
el
op
a
n
a
na
l
y
s
i
s
of
de
pres
s
i
o
n
an
d
an
x
i
et
y
us
i
ng
i
m
ag
es
or
ph
o
tos
p
os
ted
b
y
us
ers
thro
ug
h
f
ac
e
r
ec
og
n
i
ti
on
m
eth
od
s
us
i
ng
m
ore
c
o
m
pl
ex
al
g
orit
hm
s
an
d a
n
al
y
s
i
s
t
o
ha
v
e b
r
o
ad
er r
es
u
l
ts
.
Ref
er
en
ce
s
[1
]
Cas
a
d
e
i
D,
Se
rra
G
,
T
a
n
i
K.
I
m
p
l
e
m
e
n
ta
ti
o
n
o
f
a
d
i
re
c
t
c
o
n
tro
l
a
l
g
o
r
i
th
m
f
o
r
i
n
d
u
c
ti
o
n
m
o
to
rs
b
a
s
e
d
on
d
i
s
c
r
e
te
s
p
a
c
e
v
e
c
to
r m
o
d
u
l
a
ti
o
n
.
IEEE
Tr
a
n
s
a
c
t
i
o
n
s
o
n
P
o
wer
El
e
c
tro
n
i
c
s
.
2
0
0
0
;
1
5
(4
)
:
7
6
9
-
77
.
[2
]
M
i
a
h
SJ
,
Vu
HQ
,
G
a
m
m
a
c
k
J
,
M
c
G
ra
th
M
.
A
b
i
g
d
a
t
a
a
n
a
l
y
ti
c
s
m
e
th
o
d
f
o
r
to
u
r
i
s
t
b
e
h
a
v
i
o
u
r
a
n
a
l
y
s
i
s
.
In
fo
rm
a
ti
o
n
&
M
a
n
a
g
e
m
e
n
t
.
2
0
1
7
;
5
4
(6
):
7
7
1
-
85
.
[3
]
M
o
o
re
SA,
Dow
d
y
E,
Fu
rl
o
n
g
M
J
.
Us
i
n
g
th
e
De
p
re
s
s
i
o
n
,
An
x
i
e
ty
,
Stre
s
s
Sc
a
l
e
s
–
2
1
w
i
th
US
Ad
o
l
e
s
c
e
n
ts
:
An
Al
te
rn
a
te
M
o
d
e
l
s
An
a
l
y
s
i
s
.
J
o
u
rn
a
l
o
f
P
s
y
c
h
o
e
d
u
c
a
t
i
o
n
a
l
As
s
e
s
s
m
e
n
t
.
2
0
1
7
;
3
5
(
6
)
:
581
-
98
.
[4
]
T
u
to
ri
a
l
E.
Clo
s
e
d
-
l
o
o
p
Sy
s
te
m
s
.
El
e
c
tr
o
n
T
u
to
r
[I
n
te
rn
e
t]
.
2
0
1
4
;
1
.
Av
a
i
l
a
b
l
e
f
ro
m
:
h
tt
p
s
:/
/w
ww
.e
l
e
c
tro
n
i
c
s
-
tu
to
ri
a
l
s
.w
s
/s
y
s
te
m
s
/
c
l
o
s
e
d
-
l
o
o
p
-
s
y
s
t
e
m
.h
t
m
l
.
[
Ac
c
e
s
s
e
d
:
J
u
l
y
7
2
0
1
8
].
[5
]
Am
ri
t
C,
Pa
a
u
w
T
,
Al
y
R,
L
a
v
r
i
c
M
.
Id
e
n
ti
fy
i
n
g
c
h
i
l
d
a
b
u
s
e
th
ro
u
g
h
t
e
x
t
m
i
n
i
n
g
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
.
Ex
p
e
rt
s
y
s
te
m
s
w
i
th
a
p
p
l
i
c
a
ti
o
n
s
.
2
0
1
7
;
8
8
:
4
0
2
-
18
.
[6
]
Bo
h
a
n
e
c
M
,
Bo
rš
tn
a
r
M
K,
Rob
n
i
k
-
Ši
k
o
n
j
a
M
.
E
x
p
l
a
i
n
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
i
n
s
a
l
e
s
p
re
d
i
c
ti
o
n
s
.
Ex
p
e
rt
Sy
s
te
m
s
wi
th
Ap
p
l
i
c
a
ti
o
n
s
.
2
0
1
7
;
7
1
:
4
1
6
-
28
.
[7
]
Y
a
s
a
m
y
M
M
,
v
a
n
O
m
m
e
re
n
M
,
Chi
s
h
o
l
m
D,
Sa
x
e
n
a
S.
Dep
re
s
s
i
o
n
.
A
g
l
o
b
a
l
Pu
b
l
i
c
h
e
a
l
t
h
Con
c
e
r
n
.
W
H
O
De
p
a
rtm
e
n
t
o
f
M
e
n
ta
l
H
e
a
l
th
a
n
d
Su
b
s
ta
n
c
e
A
b
u
s
e
.
W
o
r
l
d
He
a
l
th
Orga
n
i
z
a
ti
o
n
.
2
0
1
2
.
[8
]
Fe
rn
á
n
d
e
z
A,
G
ó
m
e
z
Á,
L
e
c
u
m
b
e
rry
F,
Pa
r
d
o
Á,
Ra
m
íre
z
I
.
Pa
tt
e
rn
r
e
c
o
g
n
i
ti
o
n
i
n
L
a
ti
n
Am
e
ri
c
a
i
n
th
e
“Bi
g
Da
ta
”
e
ra
.
P
a
tt
e
r
n
Re
c
o
g
n
i
ti
o
n
.
2
0
1
5
;
4
8
(4
)
:
1
1
8
5
-
96
.
[9
]
L
e
a
h
y
RL,
Hol
l
a
n
d
S
J
,
M
c
G
i
n
n
L
K.
T
re
a
tm
e
n
t
Pl
a
n
s
a
n
d
In
te
rv
e
n
ti
o
n
s
fo
r
De
p
re
s
s
i
o
n
a
n
d
An
x
i
e
ty
Dis
o
rd
e
rs
.
S
e
c
o
n
d
Ed
i
,
Vo
l
.
2
6
.
L
o
n
d
o
n
:
T
h
e
Gu
i
l
fo
r
d
Pre
s
s
.
2
0
1
2
:
1
7
,
8
8
,
1
4
5
,
1
6
5
,
5
5
6
,
6
1
5
.
[1
0
]
RISKESD
AS
Ris
e
t
Ke
s
e
h
a
ta
n
Das
a
r Ke
m
e
n
te
ri
a
n
Ke
s
e
h
a
ta
n
Re
p
u
b
l
i
k
I
n
d
o
n
e
s
i
a
.
2
0
1
3
:
1
-
384.
[1
1
]
M
o
h
an
N,
Und
e
l
a
n
d
T
M
,
Rob
b
i
n
s
W
P
.
Po
w
e
r
El
e
c
tr
o
n
i
c
s
.
New
Y
o
rk
:
J
o
h
n
W
i
l
e
y
&
S
o
n
s
.
2
0
0
5
:
11
-
13
Ha
m
p
t
o
n
,
D.
Be
a
t
Dep
re
s
s
i
o
n
a
n
d
An
x
i
e
ty
b
y
Cha
n
g
i
n
g
Yo
u
r
Bra
i
n
:
W
i
th
Si
m
p
l
e
Pra
c
ti
c
e
s
Th
a
t
Wi
l
l
Im
p
ro
v
e
Yo
u
r
L
i
fe
.
C
re
a
te
Sp
a
c
e
I
n
d
e
p
e
n
d
e
n
t
Pu
b
l
i
s
h
i
n
g
Pl
a
tf
o
rm
.
2
0
1
5
:
1
-
1
3
8
.
[1
2
]
Ko
l
o
m
v
a
t
s
o
s
K,
A
n
a
g
n
o
s
t
o
p
o
u
l
o
s
C,
Had
j
i
e
f
th
y
m
i
a
d
e
s
S.
An
e
ff
i
c
i
e
n
t
t
i
m
e
o
p
ti
m
i
z
e
d
s
c
h
e
m
e
f
o
r
p
ro
g
re
s
s
i
v
e
a
n
a
l
y
ti
c
s
i
n
b
i
g
d
a
ta
.
Bi
g
Da
ta
Re
s
e
a
r
c
h
.
2
0
1
5
;
2
(4
):
1
5
5
-
6
5
.
[1
3
]
Bru
n
s
w
i
c
k
e
r
S,
Be
rt
i
n
o
E,
M
a
te
i
S.
Bi
g
d
a
ta
fo
r
o
p
e
n
d
i
g
i
t
a
l
i
n
n
o
v
a
ti
o
n
–
a
re
s
e
a
r
c
h
ro
a
d
m
a
p
.
Bi
g
Da
t
a
Res
e
a
r
c
h
.
2
0
1
5
J
u
n
3
0
;
2
(2
)
:
5
3
-
8
.
[1
4
]
Vi
n
a
y
A,
Sh
e
k
h
a
r
VS,
Rit
u
p
a
rn
a
J
,
A
g
g
ra
w
a
l
T
,
M
u
rth
y
K
B,
Nat
a
ra
j
a
n
S.
Cl
o
u
d
b
a
s
e
d
b
i
g
d
a
t
a
a
n
a
l
y
ti
c
s
fra
m
e
w
o
rk
f
o
r
f
a
c
e
re
c
o
g
n
i
ti
o
n
i
n
s
o
c
i
a
l
n
e
tw
o
rk
s
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
rn
i
n
g
.
Pro
c
e
d
i
a
Com
p
u
te
r Sc
i
e
n
c
e
.
2
0
1
5
;
5
0
:
6
2
3
-
3
0
.
[1
5
]
Cram
e
r
S
,
Ka
m
p
o
u
ri
d
i
s
M
,
Fre
i
ta
s
AA,
Al
e
x
a
n
d
ri
d
i
s
AK.
An
e
x
te
n
s
i
v
e
e
v
a
l
u
a
t
i
o
n
o
f
s
e
v
e
n
m
a
c
h
i
n
e
l
e
a
rn
i
n
g
m
e
th
o
d
s
fo
r
r
a
i
n
fa
l
l
p
re
d
i
c
ti
o
n
i
n
w
e
a
th
e
r
d
e
ri
v
a
ti
v
e
s
.
Ex
p
e
rt
Sy
s
te
m
s
wit
h
Ap
p
l
i
c
a
ti
o
n
s
.
2017
;
8
5
:
169
-
81.
[1
6
]
Rua
n
G
,
Zh
a
n
g
H.
Clo
s
e
d
-
l
o
o
p
b
i
g
d
a
ta
a
n
a
l
y
s
i
s
w
i
th
v
i
s
u
a
l
i
z
a
ti
o
n
a
n
d
s
c
a
l
a
b
l
e
c
o
m
p
u
ti
n
g
.
Bi
g
Dat
a
Res
e
a
r
c
h
.
2
0
1
7
;
8
:
12
-
2
6
.
[1
7
]
O
n
e
to
L
,
Fu
m
e
o
E
,
Cl
e
ri
c
o
G
,
Can
e
p
a
R,
Pa
p
a
F,
Dam
b
ra
C,
M
a
z
z
i
n
o
N,
An
g
u
i
t
a
D.
T
ra
i
n
Del
a
y
Pre
d
i
c
ti
o
n
Sy
s
te
m
s
:
A
Bi
g
Da
t
a
An
a
l
y
ti
c
s
P
e
rs
p
e
c
t
i
v
e
.
Bi
g
d
a
ta
re
s
e
a
r
c
h
.
2
0
1
8
;
1
1
:
54
-
64.
[1
8
]
Y
o
u
n
i
s
EM
.
Se
n
ti
m
e
n
t
a
n
a
l
y
s
i
s
a
n
d
te
x
t
m
i
n
i
n
g
fo
r
s
o
c
i
a
l
m
e
d
i
a
m
i
c
ro
b
l
o
g
s
u
s
i
n
g
o
p
e
n
s
o
u
rc
e
to
o
l
s
:
An
e
m
p
i
ri
c
a
l
s
tu
d
y
.
In
te
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Com
p
u
te
r A
p
p
l
i
c
a
ti
o
n
s
.
2
0
1
5
;
1
1
2
(5
)
:
44
-
48
.
[1
9
]
Ba
r
-
Hai
m
Y
,
L
a
m
y
D,
Pe
rg
a
m
i
n
L
,
Ba
k
e
rm
a
n
s
-
Kr
a
n
e
n
b
u
r
g
M
J
,
Va
n
Ij
z
e
n
d
o
o
rn
M
H
.
T
h
re
a
t
-
re
l
a
te
d
a
tt
e
n
t
i
o
n
a
l
b
i
a
s
i
n
a
n
x
i
o
u
s
a
n
d
n
o
n
a
n
x
i
o
u
s
i
n
d
i
v
i
d
u
a
l
s
:
a
m
e
ta
-
a
n
a
l
y
ti
c
s
t
u
d
y
.
Ps
y
c
h
o
l
o
g
i
c
a
l
b
u
l
l
e
ti
n
.
2
0
0
7
;
1
3
3
(
1
):
1
-
24
.
Evaluation Warning : The document was created with Spire.PDF for Python.