3.3. NETWORK-BASED DETECTION 45
u
i
E 2 f0; 1g
mN
E
ij
D 1 u
i
a
j
E
ij
D 0
x
i
x
i
x
i
Q
x
i
x
i
; i D 1; :::; m
Q
x
1
;
Q
x
2
; :::;
Q
x
m
i
h
i1
Q
x
i
h
i
h
i
i
h
m
a
j
D tanh.Wh
m
C b/ b
a
j
Embedding Layer
h
x̃
x̃
i
x̃
m
...
h
i
x
i
x
...
h
m
W a
j
x
m
3.3.4 INTERACTION NETWORK MODELING
46 3. HOW SOCIAL CONTEXT HELPS
News
Content
Embedding
User
Embedding
Linear
Classifie
User-News
Interaction
Embedding
Publisher-News
Relation
Embedding
d
m k
k
k
k
k
n
k
m
m
m + r
n – r
n – r
m + r
r
r
N = N
× k
×
m
= m
=
= p
l
= r
× n
× k
× k
× k
× k
× k
k d
X
A U
U
o
FB
⎴
× k
F
L
F
U
y
U
p
q
F
L
p
y
L
L
T U
T
U
T
F
T
F V
T
Interaction Network
Tri-Relationship Embedding Fake News Prediction
L
B W A
p
p
a
a
a
u
u
u
u
News Embedding
F
User Embedding
A 2 f0; 1g
mm
U 2 R
mk
C
min
U;T0
kY ˇ .A UTU
T
/k
2
F
;
U T 2 R
kk
C
Y 2 R
mm
A A Y D
3.3. NETWORK-BASED DETECTION 47
sign.A/
User-News Embedding
y
Lj
s D fs
1
; s
2
; :::; s
m
g
s
i
2 Œ0; 1 u
i
E 2 f0; 1g
mN
E
ij
D 1 u
i
a
j
E
ij
D 0
min
m
X
iD1
r
X
j D1
E
ij
s
i
1
1 C y
Lj
2
jjU
i
F
j
jj
2
2
„ ƒ‚ …
C
m
X
iD1
r
X
j D1
E
ij
.1 s
i
/
1 C y
Lj
2
jjU
i
F
j
jj
2
2
„ ƒ‚ …
;
y
L
2 R
r1
y
Lj
D 1
y
Lj
D 1
Publisher-News Embedding
o
o 2 R
l1
B 2 R
lN
min k
N
BFQ ok
2
2
;
N
BD
N
B
N
B
kj
D
B
kj
P
n
j D1
B
kj
Q 2 R
k1
o
..................Content has been hidden....................
You can't read the all page of ebook, please click here login for view all page.