Social Science Computer Review,
Год журнала:
2022,
Номер
41(6), С. 1986 - 2009
Опубликована: Сен. 24, 2022
This
study
aims
to
identify
effective
predictors
that
influence
publics’
emotional
reactions
COVID-19
vaccine
misinformation
as
well
corrective
messages.
We
collected
a
large
sample
of
related
and
messages
on
Facebook
the
users’
(i.e.,
emojis)
these
Focusing
three
clusters
features
such
messages’
linguistic
features,
source
characteristics,
network
positions,
we
examined
whether
information
would
differ.
used
random
forest
models
most
salient
among
over
70
for
both
types
Our
analysis
found
misinformation,
political
ideology
message
was
feature
predicted
anxious
enthusiastic
reactions,
followed
by
highlight
personal
concerns
positions.
For
messages,
while
sources’
still
key
raising
anxiety,
important
triggering
enthusiasm
positions
quality.
IEEE Transactions on Affective Computing,
Год журнала:
2023,
Номер
15(3), С. 815 - 827
Опубликована: Июль 17, 2023
The
proliferation
of
COVID-19
fake
news
on
social
media
poses
a
severe
threat
to
the
health
information
ecosystem.
We
show
that
affective
computing
can
make
significant
contributions
combat
this
infodemic.
Given
is
often
presented
with
emotional
appeals,
we
propose
new
perspective
role
emotion
in
attitudes,
perceptions,
and
behaviors
dissemination
information.
study
emotions
conjunction
news,
explore
different
aspects
their
interaction.
To
process
both
'falsehood'
based
same
set
data,
auto-tag
existing
datasets
following
an
established
taxonomy.
More
specifically,
distribution
seven
basic
(e.g.
Happiness,
Like,
Fear,
Sadness,
Surprise,
Disgust,
Anger
),
find
across
domains
styles
dominated
by
xmlns:xlink="http://www.w3.org/1999/xlink">Fear
(e.g.,
coronavirus),
xmlns:xlink="http://www.w3.org/1999/xlink">Disgust
conflicts).
In
addition,
framing
terms
gain-versus-loss
reveals
close
correlation
between
emotions,
collective
human
reactions.
Our
analysis
confirms
spreading
especially
when
contextualized
loss
frame.
points
future
direction
incorporating
footprints
models
automatic
detection,
establishes
approach
quality
general
detection
particular.
Social Science Computer Review,
Год журнала:
2022,
Номер
41(6), С. 1986 - 2009
Опубликована: Сен. 24, 2022
This
study
aims
to
identify
effective
predictors
that
influence
publics’
emotional
reactions
COVID-19
vaccine
misinformation
as
well
corrective
messages.
We
collected
a
large
sample
of
related
and
messages
on
Facebook
the
users’
(i.e.,
emojis)
these
Focusing
three
clusters
features
such
messages’
linguistic
features,
source
characteristics,
network
positions,
we
examined
whether
information
would
differ.
used
random
forest
models
most
salient
among
over
70
for
both
types
Our
analysis
found
misinformation,
political
ideology
message
was
feature
predicted
anxious
enthusiastic
reactions,
followed
by
highlight
personal
concerns
positions.
For
messages,
while
sources’
still
key
raising
anxiety,
important
triggering
enthusiasm
positions
quality.
