30 3. HOW SOCIAL CONTEXT HELPS
3.1.2 USER BEHAVIOR MODELING
flag
when-to-fact-check
what-to-fact-check
When-to-Fact-Check
U
C endogenous events
exogenous events
exogenous events
N
e
.t/
e
.t/
t N
f
.t/
flags
t
N
N .t/
N
N .t/ WD p.y D 1jf D 1/N
f
.t/ C p.y D 1jf D 0/.N
e
.t/ N
f
.t//;
p.y D 1jf D 1/ p.y D 1jf D 0/
y D 1 f D 1
f D 1
N
N .t/
https://newsroom.fb.com/news/2016/12/news-feed-fyi-addressing-hoaxes-and-fake-news/
https://www.washingtonpost.com/news/the-switch/wp/2017/06/29/twitter-is-looking-for-ways-to-
let-users-flag-fake-news
https://www.scmp.com/news/china/policies-politics/article/2055179/how-chinas-highly-
censored-wechat-and-weibo-fight-fake
3.1. USER-BASED DETECTION 31
Q
O
dt D E
f .t/;f
Œd
N
N .t/
D E
f .t/;f
h
.p.y D 1jf D 1/ p.y D 1jf D 0/f .t/ C p.y D 1jf D 0/
i
e
.t/dt;
f .t/
b.t
0
;t
f
E
.
O
.t
f
// C
Z
t
f
t
0
`.
O
./; b.//d
b.t/ 0 8t 2 .t
0
; t
f
;
b.t/ ./
`.; /
O
.t
f
/ b.t/
./ `.; /
.
O
.t
f
// D
1
2
.
O
.t
f
//
2
`.
O
.t/; b.t// D
1
2
.
O
.t//
2
C
1
2
qb
2
.t/;
q
What-to-Fact-Check
U
t D 1; 2; ; T
t A
t
D
fa
t
1
; ; a
t
N
g Y
t
D fy
t
1
; ; y
t
N
g
a
t
i
32 3. HOW SOCIAL CONTEXT HELPS
p
t
i
a
t
i
2 A
t
t1
.s/ D fg
t1
.a/ D fg
t a 2 A
t
u 2 U
a l
t
.a/
t
.a/ a
u
2 Œ0; 1 u
u
u
˛
u
2 Œ0; 1 u a a
ˇ
u
2 Œ0; 1 u a a
u a
.
N
u
;
u
/
N
u
1
u
1
N
u
u
D
1 1
0 0
C .1
u
/
˛
u
1 ˇ
u
1 ˛
u
0 ˇ
u
;
N
u
u
N
u
D p.y
u
.a/ D 0jy.a/ D 0/
1
N
u
D p.y
u
.a/ D 1jy.a/ D 0/
u
D p.y
u
.a/ D 1jy.a/ D 1/
1
u
D p.y
u
.a/ D 0jy.a/ D 1/:
t S
t
saved a
S
t
t t D 1; ; T
T
X
tD1
E
"
X
s2S
t
1
fy.s/D1g
.j
1
.a/j j
t
.a/j/
#
;
j
1
.a/j a j
t
.a/j
a t
S
t
t
..................Content has been hidden....................
You can't read the all page of ebook, please click here login for view all page.