I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
37
,
No
.
3
,
Ma
r
ch
20
25
,
p
p
.
1
97
6
~1
98
4
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
37.
i
3
.
p
p
1
97
6
-
1
98
4
1976
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Ling
uistic f
ea
ture
select
io
n
for pe
rso
na
lity trait ide
nt
ificatio
n
from te
x
tual
data
Ang
a
d Sin
g
h
1
,
P
rit
i Ma
he
s
h
wa
ry
1
,
Nit
in K
um
a
r
M
is
hra
2
,
T
im
o
t
hy
M
a
lche
3
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
R
a
b
i
n
d
r
a
n
a
t
h
T
a
g
o
r
e
U
n
i
v
e
r
si
t
y
,
B
h
o
p
a
l
,
I
n
d
i
a
2
S
c
h
o
o
l
o
f
C
o
m
p
u
t
i
n
g
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
r
i
n
g
,
V
I
T
B
h
o
p
a
l
U
n
i
v
e
r
si
t
y
,
S
e
h
o
r
e
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
A
p
p
l
i
c
a
t
i
o
n
s,
M
a
n
i
p
a
l
U
n
i
v
e
r
si
t
y
Ja
i
p
u
r
,
Jai
p
u
r
,
R
a
j
a
st
h
a
n
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
ul
8
,
2
0
2
4
R
ev
is
ed
Sep
28
,
2
0
2
4
Acc
ep
ted
Oct
7
,
2
0
2
4
P
e
rso
n
a
li
t
y
i
d
e
n
ti
fica
ti
o
n
is
a
c
o
m
m
o
n
a
n
d
c
e
n
tral
p
r
o
b
lem
in
te
x
t
p
ro
c
e
ss
in
g
.
S
e
n
si
n
g
p
e
rso
n
a
li
t
y
is
h
e
lp
f
u
l
fo
r
v
a
rio
u
s
p
u
rp
o
se
s;
fo
r
e
x
a
m
p
le,
e
stim
a
ti
n
g
u
se
rs'
p
e
rso
n
a
li
ti
e
s
b
e
fo
re
p
ro
v
i
d
in
g
t
h
e
m
with
a
n
y
se
rv
ice
is
n
e
c
e
ss
a
ry
.
In
d
i
v
id
u
a
li
ty
is
e
ss
e
n
ti
a
l
in
a
p
e
rso
n
'
s
n
a
tu
re
in
e
v
e
r
y
o
u
tl
o
o
k
,
f
o
r
in
sta
n
c
e
,
i
n
tex
t
writi
n
g
.
Bu
t
,
t
h
i
s
re
m
a
in
s
a
c
o
re
c
h
a
ll
e
n
g
e
b
e
c
a
u
se
o
f
t
h
e
lo
w
a
c
c
u
ra
c
y
a
c
h
iev
e
d
.
Th
e
p
r
o
p
o
se
d
stu
d
y
s
o
lv
e
s
t
h
is
p
r
o
b
lem
a
n
d
p
re
se
n
t
s
a
b
ig
fi
v
e
trait
i
d
e
n
ti
fica
ti
o
n
te
c
h
n
iq
u
e
fro
m
tex
t
d
a
ta,
w
h
ich
a
p
p
li
e
s
a
fe
a
tu
re
se
lec
ti
o
n
m
e
th
o
d
to
i
n
c
re
a
se
a
c
c
u
ra
c
y
.
Th
is
tec
h
n
iq
u
e
is
c
a
ll
e
d
li
n
g
u
isti
c
fe
a
tu
re
se
lec
ti
o
n
fo
r
p
e
rso
n
a
li
t
y
trait
id
e
n
t
ifi
c
a
ti
o
n
(LF
S
P
TI)
.
Th
is
tec
h
n
iq
u
e
first
fin
d
s
fe
a
tu
re
s
b
a
se
d
o
n
m
u
tu
a
l
i
n
fo
rm
a
ti
o
n
(M
I)
,
F
-
sta
ti
stic,
p
rin
c
i
p
a
l
c
o
m
p
o
n
e
n
t
a
n
a
ly
sis
(
P
CA),
a
n
d
c
hi
-
sq
u
a
re
,
t
h
e
n
u
se
s
t
h
e
g
e
n
e
ti
c
a
lg
o
rit
h
m
(G
A)
to
se
lec
t
h
ig
h
-
ra
n
k
e
d
fe
a
tu
re
s
fro
m
a
ll
fe
a
tu
re
s
u
b
s
e
ts.
Th
e
se
fo
u
r
p
a
ra
m
e
ters
p
ro
v
i
d
e
v
a
ri
o
u
s
fo
rm
s
o
f
th
e
d
a
tas
e
t.
Th
e
e
x
p
e
rime
n
tal
re
su
lt
s
e
x
h
i
b
it
th
a
t
th
e
L
F
S
P
TI
m
e
th
o
d
e
n
h
a
n
c
e
s
t
h
e
c
las
sifica
ti
o
n
a
c
c
u
ra
c
y
a
g
a
in
st
t
h
e
b
e
st
o
f
th
e
c
o
m
p
e
ti
n
g
m
e
th
o
d
s
b
y
1
.
1
8
%
,
0
.
8
3
%
,
1
.
6
1
%
.
,
1
.
1
5
%
,
1
.
8
2
%
,
a
n
d
1
.
3
9
%
fo
r
e
x
t
ra
v
e
rsio
n
(EXT
)
,
n
e
u
r
o
ti
c
ism
(NEU),
a
g
re
e
a
b
len
e
ss
(AG
R),
c
o
n
sc
ien
ti
o
u
sn
e
ss
(CON
),
o
p
e
n
n
e
ss
(OPN),
a
n
d
m
e
a
n
o
v
e
ra
ll
p
e
rso
n
a
li
t
y
traits,
re
sp
e
c
ti
v
e
ly
.
K
ey
w
o
r
d
s
:
C
h
i
-
s
q
u
ar
e
Featu
r
e
s
elec
tio
n
F
-
s
tatis
tic
Gen
etic
alg
o
r
ith
m
Mu
tu
al
in
f
o
r
m
atio
n
Per
s
o
n
ality
tr
ait
id
en
tific
atio
n
Prin
cip
al
co
m
p
o
n
en
t a
n
al
y
s
is
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
:
An
g
ad
Sin
g
h
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
,
R
ab
in
d
r
an
ath
T
ag
o
r
e
Un
iv
er
s
ity
B
h
o
p
al
,
I
n
d
ia
E
m
ail: a
n
g
ad
a2
0
0
7
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Per
s
o
n
ality
is
th
e
co
m
b
in
atio
n
o
f
all
th
o
s
e
ac
tiv
ities
th
at
c
an
b
e
d
is
co
v
er
ed
b
y
ac
tu
al
o
b
s
er
v
atio
n
o
v
er
a
lo
n
g
p
er
io
d
o
f
tim
e
to
g
iv
e
u
s
ef
u
l
in
f
o
r
m
atio
n
.
Per
s
o
n
ality
d
escr
ib
es
a
p
er
s
o
n
f
r
o
m
m
u
ltip
le
p
er
s
p
ec
tiv
es,
s
u
ch
as
th
o
u
g
h
ts
,
b
eh
av
i
o
r
,
b
elief
s
,
f
ee
lin
g
s
,
a
n
d
em
o
tio
n
s
[
1
]
.
Acc
o
r
d
in
g
t
o
p
s
y
ch
o
lo
g
y
,
e
v
er
y
p
er
s
o
n
ality
h
as
a
s
ig
n
if
ican
t
i
n
f
lu
en
ce
s
u
ch
th
at
it
af
f
ec
ts
li
f
e
p
r
io
r
ities
,
well
-
b
ein
g
,
h
ea
lth
,
an
d
m
an
y
o
t
h
e
r
ch
o
ices
in
d
aily
life
.
Per
s
o
n
ality
is
an
en
d
u
r
in
g
s
et
o
f
ten
d
e
n
cies
an
d
s
ty
les
th
at
an
in
d
iv
id
u
al
ex
h
ib
its
in
h
is
o
r
h
er
life
.
I
t
r
ef
lects
in
d
iv
id
u
als’
in
clin
atio
n
s
a
n
d
d
if
f
e
r
e
n
tiates
th
em
f
r
o
m
th
e
"i
d
ea
l
in
d
iv
id
u
al"
in
th
e
g
en
er
al
p
u
b
lic
o
r
s
o
ciety
.
Her
e,
th
e
ch
ar
ac
ter
is
tic
ex
a
m
in
es
th
e
co
m
m
itm
en
t
a
n
d
p
er
s
o
n
al
em
o
tio
n
al
attitu
d
e
in
a
p
ar
ticu
lar
ty
p
e
o
f
b
eh
av
i
o
r
.
T
h
er
e
ar
e
two
c
o
m
m
o
n
ly
u
s
ed
m
o
d
els
f
o
r
p
er
s
o
n
ality
class
if
icatio
n
.
First,
a
b
ig
-
f
iv
e
m
o
d
el
co
n
s
is
ts
o
f
f
iv
e
p
er
s
o
n
ality
tr
aits
[
2
]
,
[
3
]
:
ex
tr
av
er
s
io
n
v
er
s
u
s
r
e
v
o
lt,
a
g
r
ee
ab
len
ess
v
er
s
u
s
u
n
p
leasan
tn
ess
,
co
n
s
cien
tio
u
s
n
ess
v
er
s
u
s
ca
r
eles
s
n
ess
,
n
eu
r
o
ticis
m
v
er
s
u
s
eq
u
an
im
ity
,
an
d
r
eser
v
e
v
er
s
u
s
o
p
en
n
ess
.
Seco
n
d
,
t
h
er
e
is
th
e
m
y
er
s
‐
b
r
ig
g
s
ty
p
e
in
d
icato
r
(
MBTI
)
m
o
d
el
[
3
]
-
[
5
]
,
wh
ich
h
as
f
o
u
r
p
er
s
o
n
ality
tr
aits
.
C
o
r
r
elatio
n
b
etwe
en
b
ig
-
f
iv
e
m
o
d
el
an
d
MBTI
m
o
d
e
l
s
h
o
wn
in
[
3
]
.
Ho
wev
e
r
,
th
e
b
ig
f
iv
e
tr
ait
m
o
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Lin
g
u
is
tic
fea
tu
r
e
s
elec
tio
n
fo
r
p
ers
o
n
a
lity tra
it id
en
tifi
ca
tio
n
fr
o
m
textu
a
l d
a
ta
(
A
n
g
a
d
S
i
n
g
h
)
1977
is
s
tan
d
ar
d
f
o
r
d
ee
p
lear
n
in
g
an
d
m
ac
h
in
e
lear
n
i
n
g
p
ar
a
d
i
g
m
s
b
ec
au
s
e
o
f
its
p
r
o
p
er
lin
g
u
is
tic
p
er
s
o
n
ality
b
eh
av
io
r
[
6
]
-
[
9
]
.
Au
to
m
atio
n
o
f
p
er
s
o
n
ality
tr
ait
r
ec
o
g
n
itio
n
h
as
m
u
ltip
le
ap
p
licatio
n
s
,
s
u
ch
as
in
h
u
m
an
r
eso
u
r
ce
m
an
ag
em
en
t,
d
ec
is
io
n
-
m
a
k
in
g
,
m
ar
k
etin
g
s
tr
ateg
y
,
to
u
r
is
m
,
m
en
tal
h
ea
lth
,
a
n
d
f
o
r
en
s
i
cs.
Per
s
o
n
ality
tr
aits
h
elp
h
u
m
a
n
r
eso
u
r
ce
m
a
n
ag
er
s
to
s
elec
t
th
e
r
ig
h
t
em
p
lo
y
ee
s
f
o
r
s
p
ec
if
ic
p
o
s
itio
n
s
in
h
u
m
an
r
eso
u
r
ce
m
an
ag
em
en
t
[
1
]
.
I
n
d
ec
is
io
n
-
m
ak
in
g
,
it
h
elp
s
o
n
e
to
u
n
d
er
s
tan
d
th
e
b
eh
av
i
o
r
o
f
em
p
lo
y
ee
s
in
s
p
ec
if
ic
s
itu
atio
n
s
.
I
n
m
en
tal
h
ea
lth
,
c
o
n
tex
tu
al
an
al
y
s
is
is
r
elate
d
to
ce
r
tain
p
er
s
o
n
ality
tr
aits
.
I
n
f
o
r
en
s
ics,
a
r
elev
an
t
p
er
s
o
n
ality
t
r
ait
h
elp
s
n
ar
r
o
w
th
e
ar
ea
o
f
s
u
s
p
icio
n
.
I
n
m
ar
k
etin
g
,
p
er
s
o
n
ality
tr
aits
in
f
lu
en
ce
m
ar
k
etin
g
s
tr
ateg
ies
f
o
r
co
n
s
u
m
er
g
o
o
d
s
.
Per
s
o
n
ality
tr
ait
r
ec
o
g
n
itio
n
is
im
ag
in
ed
as
an
ex
ce
llen
t
tech
n
iq
u
e
to
a
d
d
r
ess
th
e
is
s
u
es
an
d
is
a
p
r
o
m
is
in
g
m
eth
o
d
in
all
m
en
tio
n
ed
ap
p
licatio
n
s
.
Nev
er
t
h
eless
,
p
er
s
o
n
ality
tr
ait
id
en
tific
atio
n
tech
n
iq
u
es
n
o
t
ice
a
s
m
all
ac
cu
r
ac
y
s
co
r
e.
Var
io
u
s
d
ee
p
lear
n
in
g
a
n
d
m
ac
h
in
e
lear
n
in
g
p
ar
ad
ig
m
s
h
a
v
e
r
ec
en
tly
b
ee
n
s
u
g
g
ested
to
s
o
lv
e
th
is
lim
itatio
n
[
6
]
.
T
h
e
b
i
g
-
f
iv
e
tr
ait
m
o
d
el
is
wid
ely
u
s
ed
as
a
p
er
s
o
n
ality
tr
ai
t
m
o
d
el
in
p
er
s
o
n
ality
class
if
icatio
n
.
I
t
is
a
well
-
an
aly
ze
d
an
d
o
b
s
er
v
ed
m
o
d
el
o
f
p
er
s
o
n
ality
ar
c
h
itectu
r
e
th
at
m
o
s
t
r
esear
ch
er
s
u
s
e.
T
h
er
ef
o
r
e,
m
o
s
t
s
tu
d
ies
u
s
e
th
e
b
ig
-
f
i
v
e
tr
ait
m
o
d
el
r
eg
a
r
d
in
g
p
er
s
o
n
ality
tax
o
n
o
m
y
.
E
x
tr
ac
t
u
s
er
in
f
o
r
m
ati
o
n
to
r
ec
o
g
n
ize
th
e
p
er
s
o
n
'
s
p
er
s
o
n
ality
b
ased
o
n
th
e
b
eh
a
v
io
r
o
f
d
if
f
e
r
en
t
u
s
er
s
.
Ho
wev
er
,
p
e
r
s
o
n
ality
id
e
n
tity
is
co
n
v
en
tio
n
ally
f
o
u
n
d
in
a
u
s
er
'
s
s
tatu
s
u
p
d
ates,
s
u
ch
as
tex
t
m
ess
ag
es
an
d
p
r
o
f
ile
d
ata.
T
h
e
m
ajo
r
ity
o
f
th
is
in
f
o
r
m
atio
n
co
m
es
f
r
o
m
tex
t
f
o
r
m
.
T
h
er
e
f
o
r
e,
th
e
an
aly
s
is
o
f
te
x
tu
al
d
a
ta
allo
ws
f
o
r
th
e
ju
d
g
i
n
g
o
f
e
s
s
en
tial
p
er
s
o
n
ality
tr
aits
[
8
]
.
T
h
e
f
o
cu
s
o
f
th
is
wo
r
k
is
th
e
p
r
ed
ictio
n
o
f
p
er
s
o
n
ality
t
r
aits
f
r
o
m
te
x
tu
al
d
ata
.
T
h
e
r
e
ar
e
v
ar
io
u
s
m
ac
h
in
e
lear
n
i
n
g
m
o
d
els
th
at
ca
n
p
r
e
d
ict
th
e
p
e
r
s
o
n
ality
tr
a
its
o
f
an
in
d
iv
id
u
al.
Featu
r
e
s
elec
tio
n
tech
n
iq
u
es
h
av
e
b
ee
n
ap
p
lied
in
s
o
m
e
r
ec
en
t
wo
r
k
s
to
in
c
r
ea
s
e
ac
c
u
r
ac
y
;
h
o
wev
er
,
lo
w
ac
c
u
r
ac
y
r
em
ain
s
a
co
r
e
ch
allen
g
e.
T
h
is
p
ap
e
r
ad
d
r
es
s
es
th
e
p
r
o
b
lem
s
b
y
in
teg
r
ati
n
g
f
ea
tu
r
e
e
x
tr
ac
tio
n
f
r
o
m
te
x
tu
al
d
ata,
f
ea
tu
r
e
s
elec
tio
n
,
an
d
g
e
n
etic
alg
o
r
ith
m
(
GA)
.
I
n
r
ec
en
t
tim
es,
m
an
y
r
esear
ch
s
tu
d
ies
h
av
e
b
ee
n
b
ased
o
n
m
ac
h
in
e
lear
n
in
g
a
n
d
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
es
f
o
r
p
e
r
s
o
n
ality
r
ec
o
g
n
itio
n
[
1
0
]
.
Per
s
o
n
ality
r
ec
o
g
n
itio
n
f
r
o
m
s
o
cial
n
etwo
r
k
s
i
s
wid
ely
ac
ce
p
ted
,
with
Face
b
o
o
k
p
r
o
m
in
e
n
tly
c
o
n
s
id
er
in
g
s
en
tim
en
t
a
n
aly
s
is
.
Nev
er
th
eless
,
m
o
s
t
p
er
s
o
n
ality
r
esear
ch
f
o
cu
s
es
o
n
f
ea
tu
r
e
ex
tr
ac
tio
n
tec
h
n
iq
u
es
b
ased
o
n
d
ata
co
llectio
n
o
r
p
r
ep
r
o
ce
s
s
in
g
.
I
n
tr
a
d
itio
n
al
m
ac
h
in
e
lear
n
in
g
,
class
if
icatio
n
alg
o
r
ith
m
s
an
d
m
u
lti
-
lay
er
n
eu
r
al
n
etwo
r
k
s
d
eter
m
in
e
p
er
s
o
n
ality
id
en
tifi
ca
tio
n
.
Pra
ctica
lly
,
tex
t
f
ea
tu
r
es,
f
o
r
ex
am
p
le,
o
n
e
-
g
r
am
,
two
-
g
r
am
,
o
r
lin
g
u
is
tic
f
ea
tu
r
es,
o
r
in
teg
r
atio
n
o
f
b
o
th
lin
g
u
is
tic
an
d
tex
tu
al
f
ea
tu
r
es,
ar
e
u
s
ed
in
all
p
er
s
o
n
ality
m
o
d
els.
I
n
s
tead
o
f
s
elec
tin
g
th
e
e
n
tire
s
et
o
f
f
ea
tu
r
es,
th
e
p
r
ed
ictio
n
m
o
d
el
p
er
f
o
r
m
an
c
e
ca
n
b
e
im
p
r
o
v
ed
u
s
in
g
f
ea
tu
r
e
s
elec
tio
n
tech
n
i
q
u
es
[
1
1
]
,
[
1
2
]
o
n
s
m
aller
d
atasets
.
Pas
t
r
esear
ch
o
n
p
er
s
o
n
ality
p
r
ed
ictio
n
h
as
b
ee
n
d
o
n
e
u
s
in
g
th
e
Face
b
o
o
k
s
o
cial
p
latf
o
r
m
an
d
a
f
ew
r
elev
an
t
f
ea
t
u
r
es
s
u
ch
as
lin
g
u
is
tic
in
q
u
ir
y
wo
r
d
co
u
n
t
(
L
I
W
C
)
f
ea
tu
r
es,
tim
e
-
r
elate
d
f
ea
tu
r
es,
s
o
cial
n
etwo
r
k
an
aly
s
is
(
SNA
)
f
ea
tu
r
es,
an
d
m
o
r
e
[
1
3
]
,
[
1
4
]
.
L
in
g
u
is
tic
E
ti
q
u
ette
[
1
5
]
was
a
m
ajo
r
wo
r
k
d
em
o
n
s
tr
atin
g
th
at
co
m
p
o
s
ed
lan
g
u
ag
e
is
u
n
iq
u
e
f
o
r
ev
er
y
in
d
iv
id
u
al'
s
p
er
s
o
n
ality
tr
aits
,
p
er
h
ap
s
r
ec
o
g
n
ized
b
y
u
s
in
g
lan
g
u
ag
e
cu
es.
L
I
W
C
[
1
]
is
a
m
ec
h
an
i
s
m
o
f
tex
t
an
aly
s
is
th
at
co
u
n
ts
th
e
f
r
eq
u
en
cy
o
f
v
ar
io
u
s
g
r
o
u
p
s
o
f
wo
r
d
s
in
a
g
iv
en
tex
t.
I
n
v
esti
g
ato
r
s
h
av
e
d
is
co
v
er
ed
n
o
tab
le
co
r
r
elatio
n
s
b
etwe
en
p
er
s
o
n
ality
tr
aits
an
d
lin
g
u
is
tic
ch
ar
ac
ter
is
tics
.
An
o
th
er
r
esear
ch
o
n
p
er
s
o
n
ality
p
r
ed
ictio
n
[
1
6
]
was
d
o
n
e
u
s
in
g
Face
b
o
o
k
s
tatu
s
an
d
f
ea
tu
r
es
lik
e
o
p
en
v
o
ca
b
u
lar
y
d
i
f
f
er
en
t
ial
lan
g
u
ag
e
an
aly
s
is
(
DL
A)
a
n
d
L
I
W
C
[
1
7
]
,
[
1
8
]
.
An
o
th
er
r
esear
ch
s
tu
d
y
u
s
e
d
T
witter
d
ata
f
o
r
p
er
s
o
n
ality
p
r
ed
ictio
n
with
f
ea
tu
r
es lik
e
L
I
W
C
an
d
m
ed
ical
r
esear
ch
co
u
n
cil
(
MRC
)
[
1
9
]
.
All
th
e
ab
o
v
e
r
esear
ch
s
tu
d
ie
s
p
r
ed
icted
p
er
s
o
n
ality
u
s
in
g
s
o
cial
m
ed
ia
p
latf
o
r
m
s
in
E
n
g
lis
h
u
s
in
g
th
e
b
ig
-
f
iv
e
p
e
r
s
o
n
ality
m
o
d
el
.
Ma
ir
ess
e
et
a
l.
[
2
0
]
u
s
e
co
n
v
er
s
atio
n
al
an
d
tex
t
d
atasets
in
ex
p
e
r
im
en
ts
with
L
I
W
C
f
o
r
th
e
b
ig
-
f
iv
e
p
er
s
o
n
ality
tr
ait
m
o
d
el.
T
h
e
Ma
ir
ess
e
cr
iter
io
n
r
elies
o
n
th
e
c
o
r
r
elatio
n
b
etwe
en
p
er
s
o
n
ality
tr
aits
an
d
lin
g
u
is
tic
f
ea
tu
r
es
f
o
r
te
x
tu
al
d
atasets
.
I
t
m
in
ed
1
0
2
f
ea
t
u
r
es:
1
4
M
R
C
PD
[
2
1
]
f
ea
tu
r
es
f
r
o
m
th
e
MRC
Ps
y
ch
o
lin
g
u
is
tic
Data
b
ase
an
d
8
8
L
I
W
C
f
ea
tu
r
es
f
r
o
m
th
e
L
I
W
C
m
ec
h
an
is
m
.
Fin
eE
m
o
tio
n
[
2
2
]
is
an
em
o
tio
n
-
b
ased
h
ash
tag
tech
n
o
lo
g
y
.
I
t
co
n
s
id
er
s
s
ix
em
o
tio
n
s
:
h
ap
p
in
ess
,
an
g
er
,
f
ea
r
,
s
u
r
p
r
is
e,
s
ad
n
ess
an
d
d
is
g
u
s
t.
Fin
eE
m
o
tio
n
ap
p
lies
wo
r
d
-
b
ased
s
en
tim
en
t
p
o
o
ls
to
in
cr
ea
s
e
p
er
s
o
n
ality
p
r
ed
ictio
n
ac
cu
r
ac
y
o
n
E
s
s
ay
d
atasets
.
I
t
is
also
im
p
o
r
tan
t
to
co
n
s
id
er
th
at
em
o
tio
n
s
h
av
e
a
p
o
wer
f
u
l
r
elatio
n
s
h
ip
with
p
er
s
o
n
ality
tr
aits
.
L
I
W
C
an
d
f
ea
tu
r
e
r
ed
u
ctio
n
(
FR
)
is
a
p
er
s
o
n
ality
tr
ait
r
ec
o
g
n
itio
n
tech
n
i
q
u
e
[
2
3
]
-
[
2
5
]
u
s
in
g
f
ea
tu
r
e
r
ed
u
ctio
n
a
n
d
L
I
W
C
f
ea
tu
r
es.
I
t
u
s
es
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM
)
an
d
L
R
f
o
r
class
if
icatio
n
,
an
d
f
o
r
f
ea
tu
r
e
r
e
d
u
ctio
n
,
it
u
s
es
p
r
in
cip
al
co
m
p
o
n
en
t
a
n
aly
s
is
(
PC
A
)
an
d
i
n
f
o
r
m
atio
n
g
ain
.
I
t
w
o
r
k
s
in
s
u
c
h
a
way
th
at
d
im
en
s
io
n
ality
r
e
d
u
ctio
n
r
ed
u
ce
s
tim
e
co
m
p
le
x
ity
an
d
im
p
r
o
v
es
th
e
class
if
ier
ac
cu
r
ac
y
.
Mish
r
a
et
a
l.
[
1
]
p
r
o
p
o
s
ed
a
p
er
s
o
n
ality
class
if
icatio
n
m
eth
o
d
i
n
th
e
f
o
r
m
o
f
m
u
lti
-
lab
el
class
if
icatio
n
to
estab
lis
h
lin
g
u
is
tic
b
eh
av
io
r
a
n
d
f
ea
t
u
r
e
s
elec
tio
n
.
I
t
is
a
m
o
d
el
o
f
f
ea
tu
r
e
s
elec
tio
n
th
at
d
ep
en
d
s
o
n
th
e
r
a
n
k
i
n
g
p
r
o
ce
s
s
.
I
t
th
en
s
elec
ts
th
e
b
est
h
ig
h
-
r
an
k
e
d
f
e
atu
r
es
f
r
o
m
t
h
e
m
er
g
e
d
f
ea
tu
r
e
s
et.
T
h
e
m
er
g
e
d
f
ea
tu
r
e
s
et
is
a
u
n
io
n
o
f
L
I
W
C
an
d
MRC
f
ea
tu
r
es
th
at
ap
p
lies
m
u
tu
al
in
f
o
r
m
atio
n
(
MI
)
,
ch
i
-
s
q
u
ar
e,
an
d
F
-
s
tatis
tic.
I
t
is
a
lab
el
-
wis
e
s
ea
r
ch
tech
n
iq
u
e.
First,
it
m
i
n
es
L
I
W
C
an
d
MRC
f
ea
tu
r
es
f
o
r
e
v
er
y
lab
el;
th
en
,
th
e
in
d
icate
d
f
ea
tu
r
es
ar
e
m
er
g
e
d
t
o
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
37
,
No
.
3
,
Ma
r
ch
20
25
:
1
97
6
-
1
98
4
1978
f
in
d
a
o
n
e
-
f
ea
tu
r
e
s
u
b
s
et.
T
h
e
h
ig
h
-
lev
el
f
ea
tu
r
es
ar
e
s
elec
ted
f
r
o
m
th
e
m
er
g
ed
f
ea
t
u
r
e
s
u
b
s
et.
F
-
s
tatis
t
ics,
ch
i
-
s
q
u
ar
e,
a
n
d
MI
an
al
y
s
is
o
f
v
ar
ian
ce
wer
e
a
p
p
lied
to
cla
s
s
if
y
f
ea
tu
r
es
u
s
in
g
th
e
wr
ap
p
er
m
eth
o
d
t
o
o
b
tain
b
etter
f
ea
tu
r
e
s
ets
f
r
o
m
d
iv
e
r
s
e
f
ea
tu
r
es.
T
h
e
f
ea
tu
r
e
r
elatio
n
s
h
ip
s
u
s
ed
in
v
ar
io
u
s
p
o
p
u
lar
m
eth
o
d
s
ar
e
s
h
o
wn
in
T
ab
le
1
.
T
ab
le
1
.
Featu
r
es
with
r
esp
ec
t
to
v
ar
io
u
s
tech
n
iq
u
es
S
.
n
o
.
Ti
t
l
e
F
e
a
t
u
r
e
C
l
a
s
si
f
i
e
r
u
se
d
R
e
s
u
l
t
s (
a
c
c
u
r
a
c
y
)
1.
M
a
i
r
e
sse
C
r
i
t
e
r
i
o
n
[
2
0
]
1
0
2
(
LI
W
C
+
M
R
C
)
S
V
M
5
6
.
9
7
%
2.
F
i
n
e
Em
o
t
i
o
n
[
2
2
]
1
0
2
(
LI
W
C
+
M
R
C
)
+
h
a
s
h
t
a
g
l
e
x
i
c
o
n
(
5
8
5
)
S
V
M
5
7
.
6
4
%
3.
LI
W
C
&F
R
[
2
3
]
5
6
(
P
C
A
)
a
n
d
1
0
(
I
G
)
LR
,
S
V
M
5
7
.
9
2
%
4.
P
TLFM
t
e
c
h
n
i
q
u
e
[
1
]
1
0
2
(
LI
W
C
+
M
R
C
)
S
V
M
,
L
R
6
0
.
2
2
%
T
h
eo
r
etica
lly
,
e
v
er
y
o
n
e
o
f
t
h
e
g
iv
e
n
tech
n
iq
u
es
is
s
im
ilar
.
T
h
e
y
u
s
e
ea
ch
f
ea
tu
r
e,
f
o
r
ex
am
p
le,
L
I
W
C
o
n
ly
o
r
b
o
th
L
I
W
C
an
d
MRC
in
teg
r
ated
.
As
a
r
esu
l
t,
th
e
ac
h
iev
ed
ac
cu
r
ac
y
is
s
till
lo
w
an
d
ca
n
b
e
im
p
r
o
v
e
d
.
T
o
s
o
lv
e
th
is
p
r
o
b
l
em
,
we
p
r
o
p
o
s
e
th
e
L
FS
PTI
m
eth
o
d
,
wh
ich
u
tili
ze
s
L
I
W
C
,
E
MPAT
H
[
2
6
]
,
an
d
MRC
f
ea
tu
r
es.
T
h
e
p
u
r
p
o
s
e
o
f
th
is
m
eth
o
d
is
to
in
cr
ea
s
e
ac
c
u
r
ac
y
f
o
r
p
e
r
s
o
n
ality
tr
aits
.
T
h
e
m
ajo
r
c
o
n
tr
ib
u
tio
n
s
o
f
t
h
is
r
esear
ch
s
tu
d
y
ar
e
m
en
tio
n
e
d
b
elo
w.
a)
T
h
is
wo
r
k
p
r
esen
ts
a
u
n
iq
u
e
ap
p
r
o
ac
h
ca
lled
lin
g
u
is
tic
f
ea
tu
r
e
s
elec
tio
n
f
o
r
p
e
r
s
o
n
ality
tr
ait
id
en
tific
atio
n
(
L
FS
PTI
)
f
o
r
m
i
n
in
g
f
ea
tu
r
es.
b)
I
t e
x
tr
ac
ts
f
ea
tu
r
es lik
e
L
I
W
C
,
MRC
,
an
d
E
MPAT
H
f
r
o
m
th
e
tex
tu
al
d
atasets
.
c)
I
t a
p
p
lies
f
ea
tu
r
e
s
elec
tio
n
m
et
h
o
d
s
: F
-
s
tatis
tic,
ch
i
-
s
q
u
ar
e,
MI
,
an
d
PC
A.
d)
I
t u
s
es th
e
GA
to
s
elec
t h
ig
h
-
r
an
k
in
g
f
ea
tu
r
es f
r
o
m
all
th
e
f
e
atu
r
e
s
u
b
s
ets.
e)
Nex
t,
it
ap
p
lies
m
ac
h
in
e
lear
n
in
g
m
o
d
els,
SVM
,
lo
g
is
tic
r
eg
r
ess
io
n
(
LR
)
,
an
d
d
ec
is
io
n
tr
e
e
(
DT
)
to
th
e
s
elec
ted
f
ea
tu
r
e
s
et.
f)
T
h
e
r
esu
lts
o
n
th
e
p
o
p
u
la
r
E
s
s
ay
d
ataset
s
h
o
w
th
at
th
e
L
FS
PTI
m
eth
o
d
’
s
ac
cu
r
ac
y
o
u
tp
er
f
o
r
m
s
t
h
e
cu
r
r
en
t
p
er
s
o
n
ality
id
e
n
tific
atio
n
m
eth
o
d
s
.
I
n
tex
t
co
m
p
u
tin
g
,
th
is
is
u
n
iq
u
e
r
esear
ch
wo
r
k
th
at
ass
o
ciate
s
L
I
W
C
,
E
MPAT
H
an
d
M
R
C
f
ea
tu
r
es
ac
co
r
d
in
g
to
o
u
r
p
ast
an
d
p
r
esen
t
k
n
o
wled
g
e.
T
h
e
n
GA
b
ased
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es
in
clu
d
in
g
F
-
s
tatis
t
ics,
ch
i
-
s
q
u
ar
e,
MI
an
d
PC
A
ar
e
ap
p
lied
to
ch
o
o
s
e
h
ig
h
r
an
k
e
d
f
ea
tu
r
es
f
o
r
tr
ait
r
ec
o
g
n
itio
n
i
n
p
er
s
o
n
ality
co
m
p
u
tin
g
.
T
h
e
r
e
m
ain
in
g
p
ar
t o
f
th
e
p
a
p
er
is
o
r
g
an
ized
as
f
o
llo
ws.
Sectio
n
2
o
u
tlin
es
th
e
r
elate
d
co
n
ce
p
ts
an
d
wo
r
k
in
g
o
f
t
h
e
p
r
o
p
o
s
ed
m
eth
o
d
alo
n
g
with
th
e
d
etails
o
f
th
e
d
ataset
u
s
ed
in
t
h
e
ex
p
er
im
en
tatio
n
.
Sectio
n
3
d
escr
ib
es
th
e
r
esu
lts
an
d
ex
p
er
im
en
tal
d
is
cu
s
s
io
n
.
Fin
ally
,
s
ec
tio
n
4
co
n
clu
d
es
with
p
o
s
s
ib
le
f
u
tu
r
e
r
esear
c
h
s
co
p
e
.
2.
M
E
T
H
O
D
T
h
is
p
o
r
tio
n
d
escr
ib
es
th
e
p
r
o
p
o
s
ed
L
FS
PTI
m
eth
o
d
.
T
h
e
m
eth
o
d
r
elies
o
n
MRC
,
E
MPAT
H,
L
I
W
C
f
ea
tu
r
es,
F
-
s
tatis
tics
,
ch
i
-
s
q
u
ar
e
,
MI
,
an
d
PC
A
.
So
,
th
e
f
ir
s
t
t
wo
s
u
b
-
s
ec
tio
n
s
d
escr
ib
e
th
es
e
co
n
ce
p
ts
,
an
d
th
e
last
s
u
b
-
s
ec
tio
n
d
escr
ib
es th
e
L
FS
PTI
m
eth
o
d
.
2
.
1
.
F
e
a
t
ures (
M
RC,
E
M
P
A
T
H
a
nd
L
I
WC)
T
h
is
wo
r
k
in
co
r
p
o
r
ated
m
an
y
f
ea
tu
r
es
an
d
in
v
esti
g
ated
th
e
r
elev
an
t
ca
p
ab
ilit
y
an
d
p
er
f
o
r
m
an
ce
o
f
v
ar
io
u
s
attr
ib
u
tes
f
o
r
p
er
s
o
n
ali
ty
co
m
p
u
tin
g
.
W
e
u
s
ed
MRC
,
E
MPAT
H,
an
d
L
I
W
C
lin
g
u
is
tic
f
ea
tu
r
es f
o
r
th
is
m
eth
o
d
.
T
h
e
m
i
n
ed
MRC
f
e
atu
r
es
in
clu
d
e
t
h
e
n
u
m
b
er
o
f
letter
s
,
s
y
llab
les,
in
to
n
atio
n
,
co
n
cisen
ess
,
an
d
f
am
iliar
ity
r
atin
g
s
.
E
MPAT
H
is
a
tex
t
an
aly
s
is
to
o
l
th
at
d
r
aws
m
ea
n
in
g
b
etwe
en
wo
r
d
s
an
d
p
h
r
ases
an
d
g
en
er
ates
n
ew
lex
ical
ca
te
g
o
r
ies
o
n
d
em
a
n
d
f
r
o
m
a
s
m
all
s
et
o
f
s
ee
d
wo
r
d
s
.
W
e
h
av
e
al
s
o
d
esig
n
ed
L
I
W
C
f
ea
tu
r
es
lik
e
wo
r
d
co
u
n
t,
wo
r
d
s
p
er
s
en
ten
ce
,
p
o
s
itiv
e
em
o
tio
n
s
,
an
g
er
,
wo
r
k
,
jo
b
,
h
o
m
e,
co
m
m
a,
co
lo
n
,
an
d
ap
o
s
tr
o
p
h
e,
s
im
ilar
to
th
e
Ma
i
r
ess
e
b
aselin
e.
2
.
2
.
F
e
a
t
ure
s
elec
t
io
n t
ec
hn
iqu
es
F
-
s
tatis
tic
is
a
s
tati
s
tical
te
s
t
t
h
at
is
ap
p
lied
in
h
y
p
o
th
esis
test
in
g
to
ch
ec
k
wh
eth
er
t
h
e
v
ar
ian
ce
o
f
two
s
am
p
les
d
ata
is
eq
u
al
o
r
n
o
t.
T
h
is
test
u
s
es
th
e
F
-
s
tatis
ti
c
to
co
m
p
ar
e
two
v
ar
ian
ce
s
b
y
d
iv
id
i
n
g
th
e
m
.
I
n
th
is
co
n
tex
t,
to
co
m
p
u
te
F
-
s
tatis
tic
with
r
esp
ec
t
to
th
e
x
th
f
ea
t
u
r
e
c
o
r
r
esp
o
n
d
in
g
to
th
e
y
th
p
e
r
s
o
n
ality
tr
ait
a
n
d
,
it selects ap
p
r
o
p
r
iate
f
ea
tu
r
es f
r
o
m
x
th
f
ea
tu
r
e
u
s
in
g
(
1
)
an
d
i
n
ap
p
r
o
p
r
iate
f
ea
tu
r
es f
r
o
m
x
th
f
ea
tu
r
e
u
s
in
g
(
2
)
.
1
(
)
=
{
:
=
1
=
1
,
2
,
3
,
…
…
…
}
(
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Lin
g
u
is
tic
fea
tu
r
e
s
elec
tio
n
fo
r
p
ers
o
n
a
lity tra
it id
en
tifi
ca
tio
n
fr
o
m
textu
a
l d
a
ta
(
A
n
g
a
d
S
i
n
g
h
)
1979
0
(
)
=
{
:
=
1
=
1
,
2
,
3
,
…
…
…
}
(
2
)
Fu
r
th
er
,
we
ca
lcu
late
Mea
n
M
1
o
f
th
e
s
et
1
(
)
an
d
0
o
f
th
e
s
et
0
(
)
u
s
in
g
(
3
)
an
d
(
4
)
.
1
=
∑
1
(
)
1
ℎ
1
=
|
1
(
)
|
(
3
)
A
nd
0
=
∑
0
(
)
0
ℎ
0
=
|
0
(
)
|
(
4
)
No
w,
f
in
ally
(
5
)
co
m
p
u
tes x
th
f
ea
tu
r
es F
-
s
tatis
tic.
(
)
=
(
0
−
)
2
+
(
1
−
)
2
1
+
2
ℎ
,
1
=
1
n0
∑
(
−
0
(
)
0
)
2
2
=
1
n1
∑
(
−
1
)
2
1
(
)
(
5
)
a)
C
h
i
-
s
q
u
ar
e
m
eth
o
d
is
a
s
tatis
tical
tech
n
iq
u
e
u
s
ed
to
ca
lcu
lat
e
if
two
ca
te
g
o
r
ical
v
ar
iab
les
ar
e
r
elate
d
o
r
in
d
ep
en
d
en
t.
T
o
co
m
p
u
te
ch
i
-
s
q
u
ar
e
with
r
esp
ec
t
to
th
e
x
th
f
ea
tu
r
e
co
r
r
esp
o
n
d
in
g
to
th
e
y
th
p
er
s
o
n
alit
y
tr
ait
u
s
in
g
(
6
)
:
(
)
=
∑
(
(
,
)
(
)
−
(
,
)
(
)
)
2
(
,
)
(
)
{
0
,
1
}
(
6
)
w
h
er
e
(
,
)
(
)
is
o
b
s
er
v
ed
v
al
u
es
o
f
x
th
f
ea
tu
r
e
f
o
r
th
e
y
th
p
er
s
o
n
ality
tr
ait
an
d
(
,
)
(
)
is
ex
p
ec
ted
v
alu
e
s
o
f
x
th
f
ea
tu
r
e
f
o
r
th
e
y
th
p
er
s
o
n
ality
t
r
ait
an
d
i d
e
n
o
tes th
e
r
elev
a
n
c
y
o
f
th
e
in
s
tan
ce
s
.
b)
MI
i
s
a
s
ta
t
is
ti
c
t
o
m
e
as
u
r
e
t
h
e
r
e
l
at
i
o
n
s
h
i
p
b
et
w
e
e
n
t
w
o
r
a
n
d
o
m
v
a
r
i
a
b
l
es
t
h
a
t
a
r
e
s
a
m
p
l
e
d
s
i
m
u
l
ta
n
e
o
u
s
l
y
.
I
t
d
et
e
r
m
i
n
e
s
th
e
d
e
p
e
n
d
e
n
c
e
o
f
t
w
o
v
a
r
i
a
b
l
es
a
n
d
i
s
c
o
m
p
u
t
e
d
u
s
i
n
g
(
7
)
:
M
I
(
X
,
Y
)
=
E
n
tr
o
py
(
X
)
–
C
on
dit
ion
a
l
E
n
tr
opy
(
X
/
Y
)
(
7
)
T
h
e
d
i
s
o
r
d
e
r
a
v
a
i
l
a
b
l
e
i
n
d
a
t
a
is
d
e
t
e
r
m
i
n
e
d
b
y
e
n
t
r
o
p
y
.
I
t
is
co
m
p
u
t
e
d
b
y
(
8
)
f
o
r
a
r
a
n
d
o
m
v
a
r
i
a
b
l
e
X
.
E
n
tr
opy
(
X
)
=
−
∑
(
)
∗
l
og
(
(
)
)
=
1
whe
r
e
(
)
is
the
pr
ob
a
b
il
ity
(
8
)
I
f
two
r
an
d
o
m
v
ar
iab
les
r
ely
o
n
o
n
e
an
o
th
er
,
th
e
e
n
tr
o
p
y
o
f
o
n
e
v
a
r
iab
le
d
ec
r
ea
s
es
af
ter
n
o
ticin
g
th
e
s
ec
o
n
d
v
ar
iab
le.
T
h
e
r
esti
n
g
u
n
ce
r
tain
ty
o
f
a
v
a
r
iab
le
o
n
a
n
o
th
er
is
estab
lis
h
ed
b
y
co
n
d
i
tio
n
al
en
tr
o
p
y
.
I
t
is
ca
lcu
lated
b
y
(
9
)
c
o
n
ce
r
n
i
n
g
v
ar
iab
le
X
an
d
v
ar
iab
le
Y
C
on
dit
ion
a
l
E
n
tr
opy
(
X
/
Y
)
=
−
∑
∑
(
)
(
/
)
)
=
1
∗
l
og
(
(
)
)
=
1
(
9
)
w
h
er
e
(
/
)
is
k
n
o
wn
as th
e
co
n
d
itio
n
al
p
r
o
b
ab
ilit
y
o
f
an
d
is
g
iv
en
.
c)
PC
A
i
s
a
v
er
y
f
am
o
u
s
s
tatis
tic
al
m
eth
o
d
f
o
r
d
ata
o
r
d
in
atio
n
an
d
d
im
en
s
io
n
ality
r
ed
u
ctio
n
o
f
d
ata.
I
t
is
a
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
th
at
s
im
p
lifie
s
a
h
u
g
e
d
ata
s
et
in
to
a
s
m
aller
o
n
e.
PC
A
ca
n
b
e
b
r
o
k
e
n
d
o
w
n
in
to
th
e
f
o
llo
win
g
s
tep
s
:
Step
1
: Stan
d
ar
d
ize
th
e
lim
it
o
f
co
n
tin
u
o
u
s
in
itial v
ar
iab
les.
Step
2
: Co
m
p
u
te
th
e
c
o
v
ar
ian
ce
m
atr
ix
to
id
e
n
tify
co
r
r
elatio
n
s
b
etwe
en
v
ar
iab
les.
Step
3
: Co
m
p
u
te
th
e
eig
e
n
v
ec
t
o
r
s
an
d
eig
e
n
v
alu
es o
f
th
e
co
v
ar
ian
ce
m
atr
ix
to
id
en
tify
th
e
p
r
in
cip
al
co
m
p
o
n
en
ts
.
Step
4
: D
eter
m
in
in
g
wh
ic
h
co
m
p
o
n
e
n
ts
ar
e
r
elev
an
t to
th
e
a
n
aly
s
is
b
y
cr
ea
tin
g
a
f
ea
tu
r
e
v
ec
to
r
.
Step
5
: Rear
r
an
g
e
th
e
d
ata
alo
n
g
th
e
p
r
in
cip
al
co
m
p
o
n
en
t a
x
es.
2
.
3
.
P
r
o
po
s
ed
m
et
ho
d
T
h
e
t
r
a
i
n
i
n
g
p
r
o
c
e
s
s
o
f
L
FS
P
T
I
m
e
t
h
o
d
f
o
r
y
th
p
e
r
s
o
n
a
l
i
t
y
t
r
ai
t
is
s
h
o
w
n
i
n
F
i
g
u
r
e
1
a
n
d
Alg
o
r
i
t
h
m
1
.
First,
it
g
ets
a
ll
th
e
f
ea
tu
r
es
o
f
L
I
W
C
(
X
L
)
,
f
ea
tu
r
es
o
f
MRC
(
X
M
)
,
an
d
f
ea
tu
r
es
o
f
E
MP
AT
H
(
X
E
)
f
r
o
m
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
37
,
No
.
3
,
Ma
r
ch
20
25
:
1
97
6
-
1
98
4
1980
in
p
u
t
tr
ain
in
g
d
ataset
T
R
.
T
h
en
co
m
b
in
e
L
I
W
C
,
MRC
,
an
d
E
MPAT
H
f
ea
tu
r
es
to
f
in
d
a
f
ea
t
u
r
e
s
et
S=X
L
∪
X
M
∪
X
E
.
T
h
en
,
it
co
m
p
u
tes
MI
,
ch
i
-
s
q
u
a
r
e
,
F
-
s
tatis
tic,
an
d
PC
A
f
o
r
ea
ch
f
ea
tu
r
e
f
r
o
m
f
ea
tu
r
e
s
et
S u
s
in
g
GA
to
f
in
d
b
est h
ig
h
r
an
k
ed
f
ea
t
u
r
es f
o
r
p
er
s
o
n
ality
class
if
icatio
n
.
Fig
u
r
e
1
.
Pro
ce
s
s
o
f
tr
ain
in
g
m
o
d
el
T
h
e
test
in
g
p
r
o
ce
s
s
o
f
L
FS
PTI
m
eth
o
d
f
o
r
y
th
p
er
s
o
n
ality
tr
ait
is
s
h
o
wn
in
Fig
u
r
e
2
.
An
a
lo
g
o
u
s
to
tr
ain
in
g
,
f
ir
s
t,
it
g
ets
all
th
e
f
ea
tu
r
es
o
f
L
I
W
C
(
X
L
)
,
f
ea
tu
r
es
o
f
MRC
(
X
M
)
,
an
d
f
ea
tu
r
e
s
o
f
E
MPAT
H
(
X
E
)
f
r
o
m
th
e
in
p
u
t
test
d
ataset
T
S
.
T
h
en
,
it
s
elec
ts
th
e
h
ig
h
-
r
an
k
ed
f
ea
tu
r
es,
as
d
ec
id
e
d
d
u
r
i
n
g
tr
ain
in
g
,
to
f
o
r
m
th
e
ex
tr
ac
ted
d
ataset
f
o
r
p
r
ed
i
ctin
g
th
e
y
th
p
er
s
o
n
ality
tr
ait.
Fig
u
r
e
2
.
Pro
ce
s
s
o
f
test
in
g
m
o
d
el
Alg
o
r
ith
m
1.
L
FS
PTI
(
T
R
,
F,
f
)
Input parameter
-
(1) Input Training Dataset TR = (X, Y), where Xϵ B
n×m
, Y ϵ {0, 1}
n×
l
(2) P = {P
1,
P
2,
P
3
… P
m
} is the feature set.
(3
)
f
is
th
e
nu
mb
er
of
fe
at
ur
es
fo
r
ev
er
y
fe
at
u
re
li
st
an
d
F
is
th
e
se
le
ct
ed
re
le
va
nt
number of features.
Output
-
The best
selected feature subset P
F
for y = 1, 2, 3……,
l
1.
X
L
← LIWC features from X
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Lin
g
u
is
tic
fea
tu
r
e
s
elec
tio
n
fo
r
p
ers
o
n
a
lity tra
it id
en
tifi
ca
tio
n
fr
o
m
textu
a
l d
a
ta
(
A
n
g
a
d
S
i
n
g
h
)
1981
2.
X
M
←MRC features from X
3.
X
E
← EMPATH features from X
4.
S
← combine LIWC, MRC and EMPATH such as (X
L
∪
X
M
∪
X
E
)
5.
P
F
← null
6.
For y← 1 to
l //
for every personality trait
(i)
P
F
-
sta
← null, P
Chi
← null, P
MI
← null and P
PCA
← null
(ii)
For x ← 1 to m
(a)
P
F
-
sta
[x] ←
(
)
// compute F
-
statistic using equation (5)
(b)
P
Chi
[x] ←
(
)
// compute Chi
-
square using equation (6)
(c)
P
MI
[x] ←
(
)
// compute Mutual information using equation (7)
(d)
P
PCA
[x]
←
(
)
// compute PCA using PCA method
(iii)
Se
le
ct
hi
gh
ra
nk
ed
f
f
ea
tu
re
s
fr
om
P
F
-
sta
,
P
Chi
,
P
MI
an
d
P
PCA
us
in
g
g
en
et
ic
algorithm(see
in
Algorit
hm
A
2
)
an
d
sa
ve
in
P
F
-
sta
(H
R)
,
P
Chi
(H
R)
,
P
MI
(H
R)
an
d
P
PCA
(HR), separately.
(iv)
P
temp
← null, count ← null, and accuracy ← 0
(v)
For k ← 1 to F
(a)
Pool ← {P
F
-
sta
(HR) [k] , P
Chi
(HR) [k] , P
MI
(HR) [k] and P
PCA
(HR) [k]}
(b)
while Pool ← not null
1
-
P
← select and delete a random feature from pool
2
-
Tr
ai
n
a
cl
as
si
fi
er
ap
pl
yi
ng
P
temp
∪
P
as
fe
at
ur
e
se
t
an
d
ge
t
it
s
ac
cu
ra
cy
as accuracy1
3
-
If accuracy1 > accuracy then: P
temp
= P
temp
∪
P
and count increment (count++)
4
-
If count = F then: break
(vi)
H
y
: S
P temp
→Y
y
// train a classifier for the y
th
personality
(vii)
P
F
[y] = P
temp
/
/ Subset of features for the y
th
personality
7.
Return P
F
2
.
4
.
E
s
s
a
y
s
da
t
a
s
et
a
nd
ev
a
l
ua
t
io
n
Ou
r
in
v
esti
g
atio
n
f
o
cu
s
es
o
n
E
s
s
ay
s
Data
s
et
[
1
5
]
,
wh
ich
is
th
e
b
en
ch
m
ar
k
d
ataset
f
o
r
p
er
s
o
n
ality
id
en
tific
atio
n
f
r
o
m
tex
tu
al
d
a
ta.
I
t
h
as
2
,
4
6
8
s
tr
ea
m
-
of
-
co
n
s
cio
u
s
n
ess
es
s
ay
s
.
T
h
e
b
r
ea
k
d
o
wn
o
f
th
e
E
s
s
ay
d
ataset
in
ter
m
s
o
f
p
er
s
o
n
ality
tr
aits
is
g
iv
en
in
T
ab
le
2
.
T
ab
le
2
.
T
h
e
b
r
ea
k
d
o
wn
o
f
t
h
e
E
s
s
ay
d
ataset
S
.
N
o
.
B
i
n
a
r
y
v
a
l
u
e
Ex
t
r
a
v
e
r
si
o
n
(
EX
T)
N
e
u
r
o
t
i
c
i
sm
(
N
EU
)
A
g
r
e
e
a
b
l
e
n
e
ss
(
A
G
R
)
C
o
n
sc
i
e
n
t
i
o
u
s
n
e
ss
(
C
O
N
)
O
p
e
n
n
e
ss
(OPN)
1.
0
1
1
9
1
1
2
3
4
1
1
5
7
1
2
1
4
1
1
9
6
2.
1
1
2
7
6
1
2
3
3
1
3
1
0
1
2
5
3
1
2
7
1
As
p
er
all
th
e
p
r
ev
io
u
s
s
tu
d
ies,
we
s
elec
ted
ac
cu
r
ac
y
as
th
e
p
r
im
e
m
etr
ic
f
o
r
ev
a
lu
atin
g
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
class
if
ier
m
o
d
el.
T
h
e
ac
cu
r
ac
y
f
o
t t
h
e
y
t
h
pe
r
s
o
n
ality
tr
ait
is
co
m
p
u
ted
b
y
(
1
0
)
.
A
c
c
ura
c
y
y
=
∑
‖
H
y
(
r
)
=
V
y
‖
1
r
ϵ
TS
t
(
1
0
)
W
h
er
e
T
S th
e
test
d
ata
s
et,
t is
th
e
n
u
m
b
e
r
o
f
ex
am
p
les in
T
S,
r
is
a
test
in
s
tan
ce
,
an
d
V
y
is
ac
tu
al
v
alu
e
f
o
r
th
e
y
th
p
er
s
o
n
ality
tr
ait.
Her
e,
th
e
h
ig
h
er
th
e
ac
cu
r
ac
y
v
alu
e,
th
e
b
etter
th
e
class
if
icatio
n
p
er
f
o
r
m
an
ce
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
th
is
p
ar
t,
we
ex
p
r
ess
th
e
ex
p
er
im
en
t
ex
ec
u
ted
to
ju
d
g
e
th
e
p
r
o
p
o
s
ed
tech
n
iq
u
e
a
n
d
i
ts
co
m
p
ar
is
o
n
m
ad
e
with
r
elate
d
ex
is
tin
g
s
tat
e
-
of
-
th
e
-
ar
t te
ch
n
iq
u
es a
s
g
iv
e
n
b
elo
w:
−
I
n
th
e
Ma
ir
esee
C
r
iter
io
n
[
2
0
]
,
th
e
SVM
class
if
ier
tr
ain
s
with
all
th
e
MRC
an
d
L
I
W
C
f
ea
tu
r
es.
−
I
n
Fin
eE
m
o
[
2
2
]
tech
n
iq
u
e,
t
h
e
SVM
class
if
ier
wo
r
k
s
with
th
e
Ma
ir
s
ee
cr
iter
io
n
f
ea
tu
r
e,
e
m
o
tio
n
-
b
ased
h
ash
tag
lex
ico
n
f
ea
tu
r
e,
an
d
v
ar
io
u
s
co
n
f
i
g
u
r
atio
n
s
lik
e
clu
s
ter
in
g
-
b
ased
lex
ic
o
n
f
ea
t
u
r
es.
−
T
h
e
L
I
W
C
an
d
FR
[
2
3
]
tech
n
iq
u
e
ap
p
lies
v
ar
io
u
s
class
if
i
er
s
with
s
e
lecte
d
f
ea
tu
r
es
wit
h
in
f
o
r
m
atio
n
g
ain
,
PC
A
,
an
d
th
e
e
n
tire
f
ea
t
u
r
es.
−
I
n
C
NN
an
d
Ma
ir
esee
[
2
4
]
,
f
o
u
r
d
is
tin
ct
lay
o
u
ts
wer
e
u
s
e
d
:
1
)
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
(
MLP
)
;
2
)
ML
P
p
lu
s
en
tire
ly
co
n
n
ec
ted
(
E
C
)
lay
er
; 3
)
ML
P p
l
u
s
m
ax
p
o
o
lin
g
lay
er
; 4
)
ML
P p
lu
s
C
NN
f
ilter
.
−
T
h
e
PTL
FM
tech
n
iq
u
e
[
1
]
u
s
es
two
cla
s
s
if
ier
s
s
u
ch
as
SV
M
an
d
L
R
,
in
clu
d
in
g
a
b
alan
ce
d
weig
h
in
g
m
ec
h
an
is
m
.
Ou
r
p
r
o
p
o
s
ed
tec
h
n
iq
u
e
u
s
es
th
r
ee
class
if
ier
s
,
SVM,
L
R
,
an
d
DT
,
b
ased
o
n
a
g
e
n
etic
s
elec
tio
n
o
f
f
ea
tu
r
es.
Fo
r
SVM,
th
e
p
ar
am
eter
s
ar
e
r
eg
u
lar
izatio
n
p
a
r
a
m
eter
C
=1
.
0
with
l2
s
q
u
ar
ed
p
en
alty
,
r
ad
ial
b
asis
f
u
n
ctio
n
k
er
n
el
with
t
h
r
ee
d
e
g
r
ee
s
,
an
d
to
ler
a
n
ce
=0
.
0
0
1
.
Fo
r
L
R
,
th
e
p
ar
am
eter
s
ar
e
r
eg
u
la
r
izatio
n
p
ar
am
ete
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
37
,
No
.
3
,
Ma
r
ch
20
25
:
1
97
6
-
1
98
4
1982
C
=1
.
0
with
l2
p
e
n
alty
,
to
le
r
an
ce
=0
.
0
0
0
1
,
an
d
class
weig
h
t
as
b
alan
ce
d
.
Fo
r
DT
,
th
e
p
ar
am
eter
s
ar
e
as
f
o
llo
ws:
C
r
iter
io
n
as
'
g
in
i,'
s
p
litt
er
as
'
r
an
d
o
m
,
'
m
in
im
u
m
s
am
p
les
at
th
e
leaf
as
o
n
e
,
an
d
class
_
weig
h
t
as
b
alan
ce
d
.
R
ests
o
f
th
e
p
ar
a
m
e
ter
s
ar
e
d
ef
au
lt
as
g
iv
e
n
in
[
2
7
]
.
Fo
r
th
e
GA
,
we
k
ep
t
th
e
s
iz
e
o
f
th
e
p
o
p
u
latio
n
at
5
0
,
th
e
p
r
o
b
ab
ilit
y
f
o
r
m
u
ta
tio
n
at
0
.
0
1
,
a
n
d
th
e
m
ax
im
u
m
n
u
m
b
er
o
f
g
e
n
er
atio
n
s
at
1
0
0
.
T
h
e
d
ataset
was
d
iv
id
ed
u
s
in
g
5
-
f
o
ld
cr
o
s
s
v
a
lid
atio
n
an
d
ex
p
e
r
im
en
ts
wer
e
r
ep
ea
ted
1
0
tim
es
an
d
t
h
e
av
er
ag
e
v
alu
es
ae
r
ep
o
r
ted
.
T
ab
le
3
r
e
p
r
esen
ts
th
e
ex
p
e
r
im
en
tal
r
esu
lts
f
o
r
ac
cu
r
ac
y
o
n
th
e
E
s
s
ay
s
d
ataset.
I
t
is
ev
id
en
t
f
r
o
m
th
e
tab
le
th
at
th
e
L
FS
PTI
m
eth
o
d
p
er
f
o
r
m
s
b
etter
th
a
n
all
th
e
o
th
er
ex
is
tin
g
tech
n
iq
u
es.
T
h
e
b
est
r
esu
lts
f
o
r
all
th
e
o
th
er
c
o
m
p
etin
g
m
eth
o
d
s
ar
e
5
9
.
2
6
,
6
1
.
3
2
,
5
9
.
0
6
,
5
8
.
9
4
,
an
d
6
3
.
0
3
f
o
r
E
XT
,
NE
U,
AGR,
C
ON,
an
d
OPN,
r
esp
ec
tiv
ely
,
wh
er
ea
s
t
h
e
L
FS
PTI
m
eth
o
d
g
iv
es
5
9
.
9
6
,
6
1
.
8
3
,
6
0
.
0
1
,
5
9
.
6
2
,
an
d
6
4
.
1
8
f
o
r
E
XT
,
NE
U,
AGR,
C
ON,
an
d
OPN,
r
esp
ec
tiv
ely
.
T
h
e
im
p
r
o
v
em
e
n
t
in
cl
ass
if
icatio
n
p
er
f
o
r
m
an
ce
a
g
ai
n
s
t
th
e
b
est
o
v
er
t
h
e
co
m
p
etin
g
m
eth
o
d
s
is
1
.
1
8
%,
0
.
8
3
%,
1
.
6
1
%.,
1
.
1
5
%,
an
d
1
.
8
2
%,
f
o
r
E
XT
,
NE
U,
AGR,
C
ON,
an
d
OPN,
r
esp
ec
tiv
ely
.
C
o
n
ce
p
tu
ally
,
t
h
e
m
o
r
e
in
f
o
r
m
atio
n
g
i
v
en
to
th
e
m
ac
h
in
e
lear
n
in
g
m
o
d
el,
th
e
b
etter
its
p
er
f
o
r
m
an
ce
;
h
o
wev
er
,
i
f
th
e
in
f
o
r
m
atio
n
g
iv
e
n
is
n
o
t
h
elp
f
u
l,
it
ce
r
tain
ly
d
eg
r
a
d
es
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
class
if
ier
s
.
T
h
is
is
v
er
y
tr
u
e
f
o
r
in
p
u
t
f
ea
tu
r
e
s
p
ac
e.
Hen
ce
,
L
FS
PTI
r
em
o
v
es
th
e
u
n
u
s
ef
u
l
f
ea
tu
r
es
a
n
d
p
r
o
v
id
es th
e
f
ea
tu
r
e
i
n
a
way
t
h
at
tr
an
s
f
o
r
m
s
th
e
i
n
p
u
t
d
ataset
to
b
e
v
er
y
in
f
o
r
m
ativ
e
f
o
r
p
r
ed
ictio
n
p
u
r
p
o
s
es.
T
ab
le
3
.
Per
s
o
n
ality
class
if
icatio
n
o
u
tc
o
m
es in
ter
m
s
o
f
ac
cu
r
ac
y
f
o
r
d
is
tin
ct
tech
n
iq
u
es
Te
c
h
n
i
q
u
e
EX
T
N
EU
AGR
C
O
N
O
P
N
M
e
a
n
M
a
i
r
e
se
e
+
S
V
M
5
5
.
4
9
5
8
.
4
3
5
5
.
5
6
5
5
.
2
7
6
0
.
1
0
5
6
.
9
7
F
i
n
e
Em
o
+
S
V
M
5
6
.
4
5
5
8
.
3
3
5
6
.
0
3
5
6
.
7
3
6
0
.
6
8
5
7
.
6
4
LI
W
C
a
n
d
F
R
+
v
a
r
i
o
u
s
c
l
a
ss
i
f
i
e
r
s
5
5
.
7
5
5
8
.
3
1
5
7
.
5
4
5
6
.
0
4
6
1
.
9
5
5
7
.
9
2
C
N
N
a
n
d
M
a
i
r
e
s
e
e
+
M
LP
5
5
.
5
4
5
8
.
4
2
5
5
.
4
0
5
6
.
3
0
6
2
.
6
8
5
7
.
6
7
C
N
N
a
n
d
M
a
i
r
e
s
e
e
+
M
LP
+
EC
5
4
.
6
1
5
7
.
8
1
5
5
.
8
4
5
7
.
3
0
6
2
.
1
3
5
7
.
5
4
C
N
N
a
n
d
M
a
i
r
e
s
e
e
+
M
LP
+
m
a
x
p
o
o
l
i
n
g
5
8
.
0
9
5
7
.
3
3
5
6
.
7
1
5
6
.
7
1
6
0
.
1
3
5
7
.
9
9
C
N
N
a
n
d
M
a
i
r
e
s
e
e
+
M
LP
+
C
N
N
f
i
l
t
e
r
s
5
5
.
0
7
5
9
.
3
8
5
5
.
0
8
5
5
.
1
4
6
0
.
5
1
5
7
.
0
4
P
TLFM
w
i
t
h
S
V
M
5
8
.
8
5
6
1
.
3
2
5
8
.
8
5
5
8
.
8
5
6
2
.
9
0
6
0
.
1
5
P
TLFM
w
i
t
h
LR
5
9
.
2
6
6
0
.
8
0
5
9
.
0
6
5
8
.
9
4
6
3
.
0
3
6
0
.
2
2
S
u
p
e
r
i
o
r
r
e
s
u
l
t
i
n
a
l
l
o
f
t
h
e
a
b
o
v
e
t
e
c
h
n
i
q
u
e
s
5
9
.
2
6
6
1
.
3
2
5
9
.
0
6
5
8
.
9
4
6
3
.
0
3
6
0
.
2
2
LFS
P
TI
w
i
t
h
S
V
M
5
8
.
9
7
6
1
.
5
3
5
8
.
8
9
5
8
.
9
1
6
3
.
1
0
6
0
.
2
8
LFS
P
TI
w
i
t
h
LR
5
9
.
9
6
6
1
.
8
3
6
0
.
0
1
5
9
.
6
2
6
4
.
1
8
6
1
.
1
2
LFS
P
TI
w
i
t
h
D
T
5
8
.
1
9
5
9
.
8
8
6
0
.
0
1
5
9
.
0
2
6
2
.
8
8
5
9
.
9
9
T
h
is
s
tu
d
y
in
v
esti
g
ated
th
e
ef
f
ec
ts
o
f
MRC
,
E
MPAT
H,
L
I
W
C
f
ea
tu
r
es,
F
-
s
tati
s
tic
s
,
ch
i
-
s
q
u
ar
e
,
MI
,
an
d
PC
A
.
I
n
co
n
t
r
ast,
th
e
ea
r
lier
s
tu
d
ies
h
av
e
ex
p
lo
r
ed
th
e
im
p
ac
t
o
f
o
n
ly
a
f
ew
o
f
t
h
e
s
e.
T
h
ey
h
av
e
n
o
t
ex
p
licitly
ad
d
r
ess
ed
th
e
in
f
lu
e
n
ce
o
f
all
th
e
co
m
b
in
ed
ap
p
r
o
ac
h
es.
Als
o
,
th
e
r
esu
lts
d
em
o
n
s
tr
ate
th
at
a
g
o
o
d
f
ea
tu
r
e
s
elec
tio
n
tech
n
i
q
u
e
ca
n
p
o
ten
tially
in
c
r
ea
s
e
th
e
p
r
e
d
ictiv
e
p
er
f
o
r
m
an
ce
.
W
e
n
o
t
o
n
ly
co
m
p
ar
e
t
h
e
p
er
f
o
r
m
an
ce
o
n
in
d
iv
i
d
u
al
p
er
s
o
n
ality
tr
aits
b
u
t
also
o
n
th
e
m
ea
n
v
alu
e
o
v
er
all
th
e
p
e
r
s
o
n
ality
tr
aits
.
T
h
e
b
est
m
ea
n
v
al
u
e
f
o
r
ac
c
u
r
ac
y
ac
r
o
s
s
all
th
e
tr
aits
f
o
r
co
m
p
etin
g
m
et
h
o
d
s
is
6
0
.
2
8
,
wh
er
ea
s
L
FS
PTI
g
iv
es
an
ac
cu
r
ac
y
o
f
6
0
.
6
2
.
T
h
e
i
m
p
r
o
v
e
m
en
t
in
class
if
icatio
n
p
er
f
o
r
m
an
ce
a
g
ain
s
t
th
e
b
est
o
v
er
t
h
e
c
o
m
p
etin
g
m
eth
o
d
s
is
1
.
3
9
%.
T
h
ese
r
esu
lts
d
em
o
n
s
tr
ate
th
at
L
FS
PTI
g
iv
es
s
u
p
er
io
r
o
u
tco
m
es
ac
r
o
s
s
all
th
e
p
er
s
o
n
ality
tr
aits
co
m
p
ar
e
d
to
all
th
e
co
m
p
etin
g
tech
n
i
q
u
es.
T
h
e
o
u
tco
m
es
v
e
r
if
y
th
e
u
s
ef
u
ln
ess
o
f
L
FS
PTI
as
a
g
en
etic
-
b
ased
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
e
f
o
r
im
p
r
o
v
in
g
t
h
e
class
if
icatio
n
o
f
p
er
s
o
n
ality
tr
aits
.
Ou
r
s
tu
d
y
d
em
o
n
s
tr
ates
th
at
th
e
GA
,
b
e
in
g
ev
o
l
u
tio
n
ar
y
,
is
m
o
r
e
r
esil
ien
t
th
an
th
e
o
t
h
er
co
m
p
etin
g
a
p
p
r
o
ac
h
es;
h
en
ce
,
u
s
in
g
b
etter
e
v
o
lu
tio
n
ar
y
alg
o
r
ith
m
s
lik
e
m
em
etic
alg
o
r
ith
m
s
in
f
u
tu
r
e
wo
r
k
m
ay
im
p
r
o
v
e
it f
u
r
th
er
.
4.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
a
d
d
r
ess
es
th
e
co
r
e
ch
allen
g
e
o
f
t
h
e
lo
w
ac
c
u
r
ac
y
in
p
r
ed
ictin
g
p
er
s
o
n
ality
tr
a
its
u
s
in
g
tex
t
p
r
o
ce
s
s
in
g
.
T
h
e
p
r
o
p
o
s
ed
L
FS
PTI
m
eth
o
d
h
as
s
o
lv
ed
th
is
p
r
o
b
lem
with
th
e
b
ig
-
f
i
v
e
p
er
s
o
n
ality
tr
ait
m
o
d
el
f
r
o
m
tex
t
d
ata,
wh
ich
a
p
p
lie
s
a
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
to
in
cr
ea
s
e
ac
cu
r
ac
y
.
L
FS
PTI
g
iv
es
ex
ce
llen
t
ab
s
o
lu
te
an
d
co
m
p
ar
ativ
e
e
n
h
an
ce
m
en
t
c
o
m
p
a
r
ed
t
o
p
o
p
u
lar
m
eth
o
d
s
,
in
wh
ich
m
o
r
e
th
an
9
0
%
o
f
th
e
f
ea
tu
r
es
ar
e
r
ejec
ted
o
r
r
em
o
v
ed
.
T
h
e
in
v
esti
g
atio
n
r
esu
lts
s
h
o
w
th
at
th
e
p
r
esen
ted
L
FS
PTI
m
eth
o
d
im
p
r
o
v
e
s
th
e
class
if
icatio
n
ac
cu
r
ac
y
a
g
ain
s
t
th
e
b
est
o
f
t
h
e
co
m
p
etin
g
m
eth
o
d
s
f
o
r
all
th
e
p
er
s
o
n
al
ity
tr
aits
an
d
m
ea
n
o
v
er
all.
T
h
e
r
ea
s
o
n
f
o
r
th
e
im
p
r
o
v
em
e
n
ts
in
th
e
p
r
ed
ictio
n
p
er
f
o
r
m
an
ce
is
th
at
d
if
f
er
e
n
t
p
ar
am
eter
s
p
r
o
v
id
e
d
if
f
er
en
t
asp
ec
ts
o
f
th
e
d
ataset,
an
d
s
elec
tin
g
f
ea
t
u
r
es
u
s
i
n
g
g
en
etic
s
elec
tio
n
g
iv
es
u
s
th
e
m
o
s
t
v
alu
a
b
le
f
ea
tu
r
es
f
r
o
m
th
e
c
o
m
b
in
atio
n
o
f
th
ese
asp
ec
ts
.
Du
e
to
th
e
h
ig
h
am
o
u
n
t
o
f
in
f
o
r
m
atio
n
a
n
d
th
e
s
m
all
n
u
m
b
er
o
f
f
ea
tu
r
es,
th
e
m
eth
o
d
h
as
b
ec
o
m
e
s
tab
le
a
n
d
s
tr
aig
h
tf
o
r
war
d
.
I
n
th
e
f
u
t
u
r
e,
we
p
la
n
to
u
s
e
a
m
em
etic
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Lin
g
u
is
tic
fea
tu
r
e
s
elec
tio
n
fo
r
p
ers
o
n
a
lity tra
it id
en
tifi
ca
tio
n
fr
o
m
textu
a
l d
a
ta
(
A
n
g
a
d
S
i
n
g
h
)
1983
alg
o
r
ith
m
to
s
elec
t
th
e
b
est
f
ea
tu
r
es
in
s
tead
o
f
g
en
etic
s
elec
tio
n
.
Fu
r
th
er
,
s
o
m
e
o
th
er
as
p
ec
ts
o
f
th
e
d
ataset
m
ay
b
e
co
n
s
id
er
ed
u
s
in
g
o
th
er
f
ea
tu
r
e
s
elec
tio
n
tech
n
i
q
u
es.
Als
o
,
d
atasets
o
th
er
th
an
tex
ts
m
ay
b
e
co
n
s
id
er
ed
,
wh
e
r
e
th
e
n
u
m
b
er
o
f
in
s
tan
ce
s
f
o
r
ea
ch
tr
ait
v
ar
i
es h
ea
v
ily
f
o
r
d
if
f
er
en
t p
e
r
s
o
n
ality
tr
aits
to
ch
ec
k
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
L
FS
PTI
m
eth
o
d
.
RE
F
E
R
E
NC
E
S
[
1
]
N
.
K
.
M
i
s
h
r
a
,
A
.
S
i
n
g
h
,
a
n
d
P
.
K
.
S
i
n
g
h
,
“
M
u
l
t
i
-
l
a
b
e
l
p
e
r
so
n
a
l
i
t
y
t
r
a
i
t
i
d
e
n
t
i
f
i
c
a
t
i
o
n
f
r
o
m
t
e
x
t
,
”
M
u
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
1
,
n
o
.
1
5
,
p
p
.
2
1
5
0
3
–
2
1
5
1
9
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
0
4
2
-
0
2
2
-
1
2
5
4
8
-
1.
[
2
]
W
.
K
a
n
g
,
F
.
S
t
e
f
f
e
n
s,
S
.
P
i
n
e
d
a
,
K
.
W
i
d
u
c
h
,
a
n
d
A
.
M
a
l
v
a
so
,
“
P
e
r
so
n
a
l
i
t
y
t
r
a
i
t
s
a
n
d
d
i
me
n
si
o
n
s
o
f
me
n
t
a
l
h
e
a
l
t
h
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
v
o
l
.
1
3
,
n
o
.
1
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
8
-
023
-
3
3
9
9
6
-
1.
[
3
]
R
.
D
i
v
i
a
n
d
C
.
S
.
P
o
t
a
l
a
,
“
C
o
r
r
e
l
a
t
i
o
n
b
a
se
d
d
a
t
a
u
n
i
f
i
c
a
t
i
o
n
f
o
r
p
e
r
s
o
n
a
l
i
t
y
t
r
a
i
t
p
r
e
d
i
c
t
i
o
n
,
”
I
n
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
o
f
E
l
e
c
t
ri
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
9
,
n
o
.
1
,
p
p
.
4
0
4
–
4
1
1
,
J
a
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
2
9
.
i
1
.
p
p
4
0
4
-
4
1
1
.
[
4
]
M
.
S
a
l
a
h
a
t
,
L.
A
l
i
,
T.
M
.
G
h
a
z
a
l
,
a
n
d
H
.
M
.
A
l
z
o
u
b
i
,
“
P
e
r
so
n
a
l
i
t
y
a
ss
e
ss
men
t
b
a
s
e
d
o
n
n
a
t
u
r
a
l
st
r
e
a
m
o
f
t
h
o
u
g
h
t
s
e
m
p
o
w
e
r
e
d
w
i
t
h
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
C
o
m
p
u
t
e
rs
,
Ma
t
e
r
i
a
l
s
a
n
d
C
o
n
t
i
n
u
a
,
v
o
l
.
7
6
,
n
o
.
1
,
p
p
.
1
–
1
7
,
2
0
2
3
,
d
o
i
:
1
0
.
3
2
6
0
4
/
c
mc.
2
0
2
3
.
0
3
6
0
1
9
.
[
5
]
I
.
B
.
M
y
e
r
s,
“
M
b
t
i
ma
n
u
a
l
:
a
g
u
i
d
e
t
o
t
h
e
d
e
v
e
l
o
p
m
e
n
t
a
n
d
u
se
o
f
t
h
e
m
y
e
r
s
-
b
r
i
g
g
s
t
y
p
e
i
n
d
i
c
a
t
o
r
,
”
C
o
n
s
u
l
t
i
n
g
Ps
y
c
h
o
l
o
g
i
st
s
Pre
ss,
Pa
l
o
A
l
t
o
,
1
9
9
8
.
[
6
]
R
.
S
i
n
g
h
e
t
a
l
.
,
“
A
n
t
i
so
c
i
a
l
B
e
h
a
v
i
o
r
i
d
e
n
t
i
f
i
c
a
t
i
o
n
f
r
o
m
t
w
i
t
t
e
r
f
e
e
d
s
u
s
i
n
g
t
r
a
d
i
t
i
o
n
a
l
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
EAI
E
n
d
o
rs
e
d
T
r
a
n
s
a
c
t
i
o
n
s
o
n
S
c
a
l
a
b
l
e
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
s
,
v
o
l
.
1
0
,
n
o
.
4
,
p
p
.
1
–
1
7
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
4
1
0
8
/
e
e
t
s
i
s.
v
1
0
i
3
.
3
1
8
4
.
[
7
]
Y
.
M
e
h
t
a
,
N
.
M
a
j
u
md
e
r
,
A
.
G
e
l
b
u
k
h
,
a
n
d
E.
C
a
m
b
r
i
a
,
“
R
e
c
e
n
t
t
r
e
n
d
s
i
n
d
e
e
p
l
e
a
r
n
i
n
g
b
a
s
e
d
p
e
r
s
o
n
a
l
i
t
y
d
e
t
e
c
t
i
o
n
,
”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
Re
v
i
e
w
,
v
o
l
.
5
3
,
n
o
.
4
,
p
p
.
2
3
1
3
–
2
3
3
9
,
O
c
t
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
4
6
2
-
0
1
9
-
0
9
7
7
0
-
z.
[
8
]
G
.
Ji
a
n
g
,
M
.
X
u
,
S
.
Zh
u
,
W
.
H
a
n
,
C
.
Zh
a
n
g
,
a
n
d
Y
.
Z
h
u
,
“
E
v
a
l
u
a
t
i
n
g
a
n
d
i
n
d
u
c
i
n
g
p
e
r
so
n
a
l
i
t
y
i
n
p
r
e
-
t
r
a
i
n
e
d
l
a
n
g
u
a
g
e
mo
d
e
l
s,
”
Ad
v
a
n
c
e
s i
n
N
e
u
r
a
l
I
n
f
o
rm
a
t
i
o
n
Pro
c
e
ssi
n
g
S
y
st
e
m
s
,
v
o
l
.
3
6
,
2
0
2
4
.
[
9
]
R
.
A
r
y
a
,
J.
S
i
n
g
h
,
a
n
d
A
.
K
u
mar
,
“
A
su
r
v
e
y
o
f
mu
l
t
i
d
i
sc
i
p
l
i
n
a
r
y
d
o
m
a
i
n
s c
o
n
t
r
i
b
u
t
i
n
g
t
o
a
f
f
e
c
t
i
v
e
c
o
mp
u
t
i
n
g
,
”
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
Re
v
i
e
w
,
v
o
l
.
4
0
,
p
.
1
0
0
3
9
9
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
sr
e
v
.
2
0
2
1
.
1
0
0
3
9
9
.
[
1
0
]
J.
S
e
r
r
a
n
o
-
G
u
e
r
r
e
r
o
,
B
.
A
l
sh
o
u
h
a
,
M
.
B
a
n
i
-
D
o
u
m
i
,
F
.
C
h
i
c
l
a
n
a
,
F
.
P
.
R
o
mero
,
a
n
d
J
.
A
.
O
l
i
v
a
s,
“
C
o
mb
i
n
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
p
e
r
s
o
n
a
l
i
t
y
t
r
a
i
t
p
r
e
d
i
c
t
i
o
n
,
”
E
g
y
p
t
i
a
n
I
n
f
o
rm
a
t
i
c
s
J
o
u
r
n
a
l
,
v
o
l
.
2
5
,
p
.
1
0
0
4
3
9
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
i
j
.
2
0
2
4
.
1
0
0
4
3
9
.
[
1
1
]
N
.
K
.
M
i
sh
r
a
a
n
d
P
.
K
.
S
i
n
g
h
,
“
F
S
-
M
LC
:
F
e
a
t
u
r
e
se
l
e
c
t
i
o
n
f
o
r
m
u
l
t
i
-
l
a
b
e
l
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
c
l
u
s
t
e
r
i
n
g
i
n
f
e
a
t
u
r
e
sp
a
c
e
,
”
I
n
f
o
rm
a
t
i
o
n
Pr
o
c
e
ssi
n
g
a
n
d
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
5
7
,
n
o
.
4
,
p
.
1
0
2
2
4
0
,
J
u
l
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
p
m.
2
0
2
0
.
1
0
2
2
4
0
.
[
1
2
]
M
.
D
.
K
a
m
a
l
e
s
h
a
n
d
B
.
B
,
“
P
e
r
s
o
n
a
l
i
t
y
p
r
e
d
i
c
t
i
o
n
m
o
d
e
l
f
o
r
s
o
c
i
a
l
me
d
i
a
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
Te
c
h
n
i
q
u
e
,
”
C
o
m
p
u
t
e
rs
a
n
d
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
0
0
,
p
.
1
0
7
8
5
2
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
e
l
e
c
e
n
g
.
2
0
2
2
.
1
0
7
8
5
2
.
[
1
3
]
G
.
F
a
r
n
a
d
i
,
S
.
Z
o
g
h
b
i
,
M
.
F
.
M
o
e
n
s,
a
n
d
M
.
D
e
C
o
c
k
,
“
H
o
w
w
e
l
l
d
o
y
o
u
r
F
a
c
e
b
o
o
k
s
t
a
t
u
s u
p
d
a
t
e
s
e
x
p
r
e
ss y
o
u
r
p
e
r
s
o
n
a
l
i
t
y
?
,
”
I
n
2
2
n
d
E
d
i
t
i
o
n
o
f
t
h
e
An
n
u
a
l
B
e
l
g
i
a
n
-
D
u
t
c
h
C
o
n
f
e
r
e
n
c
e
o
n
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
(
BE
N
ELE
ARN
)
,
p
.
8
8
,
2
0
1
3
.
[
1
4
]
A
.
B
r
u
n
o
a
n
d
G
.
S
i
n
g
h
,
“
P
e
r
so
n
a
l
i
t
y
t
r
a
i
t
s
p
r
e
d
i
c
t
i
o
n
f
r
o
m
t
e
x
t
v
i
a
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
P
ro
c
e
e
d
i
n
g
s
-
2
0
2
2
I
E
EE
W
o
r
l
d
C
o
n
f
e
r
e
n
c
e
o
n
Ap
p
l
i
e
d
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
C
o
m
p
u
t
i
n
g
,
A
I
C
2
0
2
2
,
Ju
n
.
2
0
2
2
,
p
p
.
5
8
8
–
5
9
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
I
C
5
5
0
3
6
.
2
0
2
2
.
9
8
4
8
9
3
7
.
[
1
5
]
J.
W
.
P
e
n
n
e
b
a
k
e
r
a
n
d
L
.
A
.
K
i
n
g
,
“
L
i
n
g
u
i
st
i
c
st
y
l
e
s:
l
a
n
g
u
a
g
e
u
s
e
a
s
a
n
i
n
d
i
v
i
d
u
a
l
d
i
f
f
e
r
e
n
c
e
,
”
J
o
u
r
n
a
l
o
f
Pe
rs
o
n
a
l
i
t
y
a
n
d
S
o
c
i
a
l
Psy
c
h
o
l
o
g
y
,
v
o
l
.
7
7
,
n
o
.
6
,
p
p
.
1
2
9
6
–
1
3
1
2
,
1
9
9
9
,
d
o
i
:
1
0
.
1
0
3
7
/
0
0
2
2
-
3
5
1
4
.
7
7
.
6
.
1
2
9
6
.
[
1
6
]
R
.
K
.
C
h
e
r
u
k
u
r
u
,
A
.
K
u
mar,
S
.
S
r
i
v
a
st
a
v
a
,
a
n
d
V
.
K
.
V
e
r
ma
,
“
P
r
e
d
i
c
t
i
o
n
o
f
p
e
r
so
n
a
l
i
t
y
t
r
a
i
t
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
o
n
o
n
l
i
n
e
t
e
x
t
s,
”
i
n
2
0
2
2
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
f
o
r
A
d
v
a
n
c
e
m
e
n
t
i
n
T
e
c
h
n
o
l
o
g
y
,
I
C
O
N
AT
2
0
2
2
,
Ja
n
.
2
0
2
2
,
p
p
.
1
–
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
O
N
A
T5
3
4
2
3
.
2
0
2
2
.
9
7
2
5
9
1
0
.
[
1
7
]
H
.
A
.
S
c
h
w
a
r
t
z
e
t
a
l
.
,
“
P
e
r
s
o
n
a
l
i
t
y
,
g
e
n
d
e
r
,
a
n
d
a
g
e
i
n
t
h
e
l
a
n
g
u
a
g
e
o
f
so
c
i
a
l
m
e
d
i
a
:
t
h
e
o
p
e
n
-
v
o
c
a
b
u
l
a
r
y
a
p
p
r
o
a
c
h
,
”
PL
o
S
O
N
E
,
v
o
l
.
8
,
n
o
.
9
,
p
.
e
7
3
7
9
1
,
S
e
p
.
2
0
1
3
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
0
7
3
7
9
1
.
[
1
8
]
R
.
L
.
V
á
s
q
u
e
z
a
n
d
J.
O
c
h
o
a
-
Lu
n
a
,
“
Tr
a
n
sf
o
r
m
e
r
-
b
a
s
e
d
a
p
p
r
o
a
c
h
e
s
f
o
r
p
e
r
s
o
n
a
l
i
t
y
d
e
t
e
c
t
i
o
n
u
s
i
n
g
t
h
e
M
B
TI
mo
d
e
l
,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
2
0
2
1
4
7
t
h
L
a
t
i
n
Am
e
r
i
c
a
n
C
o
m
p
u
t
i
n
g
C
o
n
f
e
re
n
c
e
,
C
L
EI
2
0
2
1
,
O
c
t
.
2
0
2
1
,
p
p
.
1
–
7
,
d
o
i
:
1
0
.
1
1
0
9
/
C
LEI
5
3
2
3
3
.
2
0
2
1
.
9
6
4
0
0
1
2
.
[
1
9
]
A
.
W
i
j
a
y
a
,
I
.
P
r
a
se
t
i
a
,
N
.
F
e
b
r
i
a
n
t
o
,
a
n
d
D
.
S
u
h
a
r
t
o
n
o
,
“
Th
e
‘
b
i
g
f
i
v
e
t
r
a
i
t
s
’
p
e
r
so
n
a
l
i
t
y
p
r
e
d
i
c
t
i
o
n
s
y
s
t
e
m
f
r
o
m
t
w
i
t
t
e
r
d
a
t
a,
[
T
r
a
n
sl
a
t
i
o
n
]
(
i
n
I
n
d
o
n
e
s
i
a
:
S
i
st
e
m
p
r
e
d
i
k
si
k
e
p
r
i
b
a
d
i
a
n
‘
t
h
e
b
i
g
f
i
v
e
t
r
a
i
t
s
’
d
a
r
i
d
a
t
a
T
w
i
t
t
e
r
)
,
”
Bi
n
a
N
u
sa
n
t
a
r
a
U
n
i
v
e
r
si
t
y
,
2
0
1
6
.
[
2
0
]
F
.
M
a
i
r
e
sse
,
M
.
A
.
W
a
l
k
e
r
,
M
.
R
.
M
e
h
l
,
a
n
d
R
.
K
.
M
o
o
r
e
,
“
U
si
n
g
l
i
n
g
u
i
s
t
i
c
c
u
e
s
f
o
r
t
h
e
a
u
t
o
m
a
t
i
c
r
e
c
o
g
n
i
t
i
o
n
o
f
p
e
r
s
o
n
a
l
i
t
y
i
n
c
o
n
v
e
r
sa
t
i
o
n
a
n
d
t
e
x
t
,
”
J
o
u
rn
a
l
o
f
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
Re
s
e
a
r
c
h
,
v
o
l
.
3
0
,
p
p
.
4
5
7
–
5
0
0
,
N
o
v
.
2
0
0
7
,
d
o
i
:
1
0
.
1
6
1
3
/
j
a
i
r
.
2
3
4
9
.
[
2
1
]
M
.
C
o
l
t
h
e
a
r
t
,
“
Th
e
mr
c
p
sy
c
h
o
l
i
n
g
u
i
st
i
c
d
a
t
a
b
a
se
,
”
T
h
e
Q
u
a
r
t
e
rl
y
J
o
u
r
n
a
l
o
f
E
x
p
e
ri
m
e
n
t
a
l
P
syc
h
o
l
o
g
y
S
e
c
t
i
o
n
A
,
v
o
l
.
3
3
,
n
o
.
4
,
p
p
.
4
9
7
–
5
0
5
,
N
o
v
.
1
9
8
1
,
d
o
i
:
1
0
.
1
0
8
0
/
1
4
6
4
0
7
4
8
1
0
8
4
0
0
8
0
5
.
[
2
2
]
S
.
M
.
M
o
h
a
mm
a
d
a
n
d
S
.
K
i
r
i
t
c
h
e
n
k
o
,
“
U
si
n
g
h
a
s
h
t
a
g
s
t
o
c
a
p
t
u
r
e
f
i
n
e
e
m
o
t
i
o
n
c
a
t
e
g
o
r
i
e
s
f
r
o
m
t
w
e
e
t
s,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
3
1
,
n
o
.
2
,
p
p
.
3
0
1
–
3
2
6
,
Ja
n
.
2
0
1
5
,
d
o
i
:
1
0
.
1
1
1
1
/
c
o
i
n
.
1
2
0
2
4
.
[
2
3
]
E.
Ti
g
h
e
,
J.
U
r
e
t
a
,
B
.
P
o
l
l
o
,
C
.
C
h
e
n
g
,
a
n
d
R
.
D
.
D
.
B
u
l
o
s,
“
P
e
r
so
n
a
l
i
t
y
t
r
a
i
t
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
e
ss
a
y
s
w
i
t
h
t
h
e
a
p
p
l
i
c
a
t
i
o
n
o
f
f
e
a
t
u
r
e
r
e
d
u
c
t
i
o
n
,
”
I
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
4
t
h
w
o
rks
h
o
p
o
n
S
e
n
t
i
m
e
n
t
A
n
a
l
y
si
s
w
h
e
r
e
AI
m
e
e
t
s
Ps
y
c
h
o
l
o
g
y
(
S
A
AI
P)
,
p
p
.
2
2
–
2
8
,
2
0
1
6
.
[
2
4
]
N
.
M
a
j
u
m
d
e
r
,
S
.
P
o
r
i
a
,
A
.
G
e
l
b
u
k
h
,
a
n
d
E
.
C
a
m
b
r
i
a
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
d
o
c
u
me
n
t
m
o
d
e
l
i
n
g
f
o
r
p
e
r
s
o
n
a
l
i
t
y
d
e
t
e
c
t
i
o
n
f
r
o
m
t
e
x
t
,
”
I
EE
E
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
,
v
o
l
.
3
2
,
n
o
.
2
,
p
p
.
7
4
–
7
9
,
M
a
r
.
2
0
1
7
,
d
o
i
:
1
0
.
1
1
0
9
/
M
I
S
.
2
0
1
7
.
2
3
.
[
2
5
]
J.
W
.
P
e
n
n
e
b
a
k
e
r
,
M
.
E
.
F
r
a
n
c
i
s,
a
n
d
R
.
J.
B
o
o
t
h
,
“
Li
n
g
u
i
st
i
c
i
n
q
u
i
r
y
a
n
d
w
o
r
d
c
o
u
n
t
:
Li
w
c
2
0
0
1
,
”
L
a
w
re
n
c
e
Er
l
b
a
u
m
Asso
c
i
a
t
e
s,
Ma
h
w
a
y
,
2
0
0
1
.
[
2
6
]
E.
F
a
st
,
B
.
C
h
e
n
,
a
n
d
M
.
S
.
B
e
r
n
st
e
i
n
,
“
E
mp
a
t
h
:
U
n
d
e
r
st
a
n
d
i
n
g
t
o
p
i
c
s
i
g
n
a
l
s
i
n
l
a
r
g
e
-
s
c
a
l
e
t
e
x
t
,
”
i
n
C
o
n
f
e
ren
c
e
o
n
H
u
m
a
n
Fa
c
t
o
rs i
n
C
o
m
p
u
t
i
n
g
S
y
st
e
m
s
-
Pr
o
c
e
e
d
i
n
g
s
,
M
a
y
2
0
1
6
,
p
p
.
4
6
4
7
–
4
6
5
7
,
d
o
i
:
1
0
.
1
1
4
5
/
2
8
5
8
0
3
6
.
2
8
5
8
5
3
5
.
[
2
7
]
F
.
P
e
d
r
e
g
o
s
a
e
t
a
l
.
,
“
S
c
i
k
i
t
-
l
e
a
r
n
:
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
i
n
P
y
t
h
o
n
,
”
J
o
u
rn
a
l
o
f
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
R
e
se
a
rc
h
,
p
p
.
2
8
2
5
–
2
8
3
0
,
2
0
1
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
37
,
No
.
3
,
Ma
r
ch
20
25
:
1
97
6
-
1
98
4
1984
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ang
a
d
S
i
n
g
h
is
p
u
rsu
in
g
P
h
.
D.
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
fr
o
m
Ra
b
in
d
ra
n
a
th
Tag
o
re
Un
i
v
e
rsity
,
Bh
o
p
a
l,
In
d
ia.
He
c
o
m
p
lete
d
h
is
M
.
Tec
h
fro
m
S
h
ri
Ra
m
In
stit
u
te
o
f
tec
h
n
o
lo
g
y
,
Ja
b
a
lp
u
r,
In
d
ia
i
n
2
0
1
1
.
He
h
a
s
m
o
re
th
a
n
1
6
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
in
re
p
u
te
d
i
n
stit
u
ti
o
n
s
li
k
e
Ba
n
sa
l
I
n
stit
u
te
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
,
B
h
o
p
a
l.
His
a
re
a
o
f
in
tere
ste
d
is
m
a
c
h
in
e
lea
rn
in
g
a
n
d
d
e
e
p
lea
rn
in
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
n
g
a
d
a
2
0
0
7
@g
m
a
il
.
c
o
m
.
Priti
Ma
h
e
shwa
r
y
is
P
r
o
fe
ss
o
r
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
De
p
a
rtme
n
t
a
t
Ra
b
in
d
ra
n
a
th
Tag
o
re
Un
iv
e
rsit
y
,
B
h
o
p
a
l.
S
h
e
h
a
d
h
e
r
Do
c
to
ra
te
fro
m
M
AN
IT,
Bh
o
p
a
l
i
n
Re
m
o
te
S
e
n
si
n
g
Im
a
g
e
Re
tri
e
v
a
l.
S
h
e
h
a
s
c
o
m
p
lete
d
r
e
se
a
rc
h
p
ro
jec
t
o
n
Cli
m
a
te
Ch
a
n
g
e
d
e
tec
ti
o
n
a
n
d
m
o
n
it
o
ri
n
g
fu
n
d
e
d
b
y
S
AC
a
n
d
En
v
ir
o
n
m
e
n
t
M
o
n
it
o
rin
g
u
sin
g
S
e
n
so
r
d
e
v
ice
s
fu
n
d
e
d
b
y
AIS
ECT
U
n
iv
e
rsity
.
On
g
o
in
g
P
r
o
jec
t
is
o
n
Cr
o
p
M
o
n
i
to
ri
n
g
sp
o
n
so
re
d
b
y
S
AC.
S
h
e
is
t
h
e
a
u
th
o
r
o
f
m
o
re
t
h
a
n
2
0
p
u
b
li
c
a
ti
o
n
s
i
n
d
iffere
n
t
j
o
u
r
n
a
ls
o
f
re
p
u
te.
S
h
e
is
th
e
a
u
th
o
r
o
f
b
o
o
k
c
h
a
p
ter
o
n
S
o
ftw
a
re
Co
p
y
ri
g
h
t
.
He
r
in
tere
sts
in
c
lu
d
e
m
a
c
h
in
e
lea
rn
in
g
,
c
y
b
e
r
p
h
y
sic
a
l
sy
ste
m
s,
m
o
b
il
e
n
e
tw
o
rk
s
,
WS
N,
a
d
h
o
c
n
e
two
r
k
s,
d
a
ta
m
in
i
n
g
,
a
n
d
ima
g
e
p
ro
c
e
ss
in
g
.
He
r
wo
rk
e
x
p
e
rien
c
e
in
c
lu
d
e
s
2
0
y
e
a
rs
in
tea
c
h
i
n
g
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
in
e
e
rin
g
.
S
h
e
is
g
u
id
i
n
g
P
h
.
D.
in
th
e
field
o
f
m
a
c
h
in
e
lea
rn
in
g
,
Io
T
a
n
d
n
e
two
rk
s
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
p
rit
ima
h
e
s
h
wa
ry
@g
m
a
il
.
c
o
m
.
Nitin
K
u
m
a
r
Mi
shra
is
a
S
e
n
io
r
As
sista
n
t
P
r
o
fe
ss
o
r
a
t
t
h
e
S
c
h
o
o
l
o
f
C
o
m
p
u
t
in
g
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
,
VIT
-
B
h
o
p
a
l
Un
i
v
e
rsity
,
I
n
d
ia.
He
h
a
s
a
Do
c
to
ra
te
i
n
In
f
o
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
fr
o
m
Ata
l
Bih
a
ri
Va
jp
a
y
e
e
-
In
d
ian
In
stit
u
te
o
f
In
fo
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
a
n
d
M
a
n
a
g
e
m
e
n
t
(ABV
-
IIIT
M
),
Gw
a
li
o
r.
He
h
a
s
1
6
y
e
a
rs
o
f
a
c
a
d
e
m
ic
e
x
p
e
rien
c
e
.
As
a
re
se
a
rc
h
e
r,
d
e
sig
n
in
g
,
d
e
v
e
lo
p
in
g
,
a
n
d
o
p
ti
m
izin
g
m
a
c
h
in
e
lea
rn
in
g
a
lg
o
rit
h
m
s
f
o
r
m
u
lt
i
-
lab
e
l
c
las
sifica
ti
o
n
p
r
o
b
lem
s
is
h
is
a
re
a
.
He
h
a
s
p
re
se
n
ted
a
n
d
p
u
b
li
sh
e
d
m
a
n
y
re
se
a
rc
h
p
a
p
e
rs
i
n
S
CIE/
S
c
o
p
u
s
-
i
n
d
e
x
e
d
in
ter
n
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
a
n
d
j
o
u
r
n
a
ls.
H
e
re
v
iew
s
v
a
ri
o
u
s
j
o
u
r
n
a
ls
su
c
h
a
s
In
fo
rm
a
ti
o
n
S
c
ien
c
e
s,
In
fo
rm
a
ti
o
n
P
r
o
c
e
ss
in
g
a
n
d
M
a
n
a
g
e
m
e
n
t,
Co
m
p
u
ters
a
n
d
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
,
Ex
p
e
rt
S
y
ste
m
with
Ap
p
li
c
a
ti
o
n
s,
a
n
d
Artifi
c
ial
In
telli
g
e
n
c
e
Re
v
iew
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
k
m
ish
ra
0
7
0
1
@g
m
a
il
.
c
o
m
.
Tim
o
th
y
Ma
lche
is
a
n
As
sista
n
t
P
ro
fe
ss
o
r
in
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
Ap
p
li
c
a
ti
o
n
s
De
p
a
rtme
n
t
a
t
M
a
n
ip
a
l
Un
iv
e
rsit
y
,
Ja
ip
u
r
,
In
d
ia.
He
h
a
s
a
Do
c
to
ra
te
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
Ap
p
li
c
a
ti
o
n
s
fro
m
Ra
b
i
n
d
ra
n
a
t
h
Tag
o
re
Un
iv
e
rsit
y
,
Bh
o
p
a
l.
He
h
a
s
1
8
y
e
a
rs
o
f
a
c
a
d
e
m
ic
e
x
p
e
rien
c
e
a
n
d
C
o
m
p
u
ter
S
p
e
c
i
a
li
st
with
a
d
e
m
o
n
stra
ted
h
ist
o
r
y
o
f
w
o
rk
i
n
g
in
t
h
e
h
ig
h
e
r
e
d
u
c
a
ti
o
n
i
n
d
u
stry
.
S
k
il
led
in
re
se
a
rc
h
,
lec
tu
rin
g
,
tec
h
n
ica
l
writi
n
g
,
tea
c
h
in
g
,
a
n
d
c
o
m
p
u
ter
p
ro
g
ra
m
m
in
g
.
S
tr
o
n
g
in
f
o
rm
a
ti
o
n
tec
h
n
o
l
o
g
y
p
r
o
fe
ss
io
n
a
l
with
a
M
CA+
P
h
.
D.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ti
m
o
t
h
y
.
m
a
lch
e
@ja
ip
u
r.
m
a
n
ip
a
l
.
e
d
u
.
Evaluation Warning : The document was created with Spire.PDF for Python.