25
How Social Context Helps
user-based post-based network-based
3.1 USER-BASED DETECTION
3.1.1 USER FEATURE MODELING
Profile Features
explicit im-
plicit
26 3. HOW SOCIAL CONTEXT HELPS
Explicit Features
Profile-Related.
– Verified
– RegisterTime
Content-Related.
– StatusCount
– FavorCount
Network-Related.
– FollowerCount
– FollowingCount
Implicit Features
unsuper-
vised
Age:
Personality:
E
A C
N O
Political Bias:
3.1. USER-BASED DETECTION 27
RegisterTime* RegisterTime*
4,000
3,000
2,000
1,000
0
4,000
3,000
2,000
1,000
0
Fake Real Fake Real
(a) RegisterTime on PolitiFact (b) RegisterTime on GossipCop
Profile Features Comparison.
RegisterTime
800
700
600
500
400
300
200
100
0
500
400
300
200
100
0
0 20 40 60 80 0 20 40 60 80
Users sharing fake news
Users sharing real news
Users sharing fake news
Users sharing real news
User Age
No. of Users
No. of Users
User Age
(a) Age on PolitiFact (b) Age on GossipCop
Age Comparison.
28 3. HOW SOCIAL CONTEXT HELPS
Psychology-Related Features
Motivational Factors:
uncertainty
discrep
tentat certain Anxiety
anx Importance or outcome-
relevance
importance anxiety
futurefocus lack of control
belief
Demographics:
swear
Social Engagement:
Position in the Network:
3.1. USER-BASED DETECTION 29
influence popularity
Relationship Enhancement:
p
p
Feature Category Feature Name Metric Example Words
Motivational Factors Tentativeness
Discrepancy
Certainty
Anxiety
Lack of Control
LIWC
tentat
LIWC
discrep
LIWC
certain
LIWC
anx
LIWC
focusfuture
maybe, perhaps
should, would
always, never
worried, fearful
may, will, soon
Demographics Demographics LIWC swear damn
Social Engagement Social Engagement Avg Tweets per day -
Position in the Network Infl uence
Polularity
#Folowees
#Followers
-
-
Reationship Enhancement Boosting #Retweets
Boosting #Likes
Increase in Retweets
Increase in Likes
-
-
..................Content has been hidden....................
You can't read the all page of ebook, please click here login for view all page.