PLoS ONE,
Год журнала:
2021,
Номер
16(2), С. e0247086 - e0247086
Опубликована: Фев. 18, 2021
The
explosion
of
disinformation
accompanying
the
COVID-19
pandemic
has
overloaded
fact-checkers
and
media
worldwide,
brought
a
new
major
challenge
to
government
responses
worldwide.
Not
only
is
creating
confusion
about
medical
science
amongst
citizens,
but
it
also
amplifying
distrust
in
policy
makers
governments.
To
help
tackle
this,
we
developed
computational
methods
categorise
disinformation.
categories
could
be
used
for
a)
focusing
fact-checking
efforts
on
most
damaging
kinds
disinformation;
b)
guiding
who
are
trying
deliver
effective
public
health
messages
counter
effectively
This
paper
presents:
1)
corpus
containing
what
currently
largest
available
set
manually
annotated
categories;
2)
classification-aware
neural
topic
model
(CANTM)
designed
category
classification
discovery;
3)
an
extensive
analysis
with
respect
time,
volume,
false
type,
type
origin
source.
Journal of Medical Internet Research,
Год журнала:
2023,
Номер
25, С. e40922 - e40922
Опубликована: Янв. 3, 2023
Chatbots
have
become
a
promising
tool
to
support
public
health
initiatives.
Despite
their
potential,
little
research
has
examined
how
individuals
interacted
with
chatbots
during
the
COVID-19
pandemic.
Understanding
user-chatbot
interactions
is
crucial
for
developing
services
that
can
respond
people's
needs
global
emergency.
Frontiers in Communication,
Год журнала:
2021,
Номер
6
Опубликована: Март 16, 2021
The
words
we
use
to
talk
about
the
current
epidemiological
crisis
on
social
media
can
inform
us
how
are
conceptualizing
pandemic
and
reacting
its
development.
This
paper
provides
an
extensive
explorative
analysis
of
discourse
Covid-19
reported
Twitter
changes
through
time,
focusing
first
wave
this
pandemic.
Based
corpus
tweets
(produced
between
20th
March
1st
July
2020)
show
topics
associated
with
development
changed
using
topic
modeling.
Second,
sentiment
polarity
language
used
in
from
a
relatively
positive
valence
during
lockdown,
toward
more
negative
correspondence
reopening.
Third
average
subjectivity
increased
linearly
fourth,
popular
frequently
figurative
frame
WAR
when
real
riots
fights
entered
discourse.
Journal of Medical Internet Research,
Год журнала:
2021,
Номер
23(4), С. e27341 - e27341
Опубликована: Апрель 1, 2021
Background
The
COVID-19
pandemic
has
disrupted
human
societies
around
the
world.
This
public
health
emergency
was
followed
by
a
significant
loss
of
life;
ensuing
social
restrictions
led
to
employment,
lack
interactions,
and
burgeoning
psychological
distress.
As
physical
distancing
regulations
were
introduced
manage
outbreaks,
individuals,
groups,
communities
engaged
extensively
on
media
express
their
thoughts
emotions.
internet-mediated
communication
self-reported
information
encapsulates
emotional
mental
well-being
all
individuals
impacted
pandemic.
Objective
research
aims
investigate
emotions
related
expressed
over
time,
using
an
artificial
intelligence
(AI)
framework.
Methods
Our
study
explores
emotion
classifications,
intensities,
transitions,
profiles,
as
well
alignment
key
themes
topics,
across
four
stages
pandemic:
declaration
global
crisis
(ie,
prepandemic),
first
lockdown,
easing
restrictions,
second
lockdown.
employs
AI
framework
comprised
natural
language
processing,
word
embeddings,
Markov
models,
growing
self-organizing
map
algorithm,
which
are
collectively
used
conversations.
investigation
carried
out
73,000
Twitter
conversations
posted
users
in
Australia
from
January
September
2020.
Results
outcomes
this
enabled
us
analyze
visualize
different
concerns
that
reflected
during
pandemic,
could
be
gain
insights
into
citizens’
health.
First,
topic
analysis
showed
diverse
common
people
had
It
noted
personal-level
escalated
broader
time.
Second,
intensity
state
transitions
fear
sadness
more
prominently
at
first;
however,
transitioned
anger
disgust
Negative
emotions,
except
for
sadness,
significantly
higher
(P<.05)
showing
increased
frustration.
Temporal
conducted
modeling
changes
demonstrated
how
emerged
shifted
Third,
categorized
where
differences
seen
between
lockdown
profiles.
Conclusions
recorded
general
public.
While
established
use
discover
informed
time
when
impossible,
also
contribute
toward
postpandemic
recovery
understanding
impact
via
changes,
they
potentially
inform
care
decision
making.
exploited
enhance
our
behaviors
emergencies,
lead
improved
planning
policy
making
future
crises.
PLoS ONE,
Год журнала:
2021,
Номер
16(2), С. e0247086 - e0247086
Опубликована: Фев. 18, 2021
The
explosion
of
disinformation
accompanying
the
COVID-19
pandemic
has
overloaded
fact-checkers
and
media
worldwide,
brought
a
new
major
challenge
to
government
responses
worldwide.
Not
only
is
creating
confusion
about
medical
science
amongst
citizens,
but
it
also
amplifying
distrust
in
policy
makers
governments.
To
help
tackle
this,
we
developed
computational
methods
categorise
disinformation.
categories
could
be
used
for
a)
focusing
fact-checking
efforts
on
most
damaging
kinds
disinformation;
b)
guiding
who
are
trying
deliver
effective
public
health
messages
counter
effectively
This
paper
presents:
1)
corpus
containing
what
currently
largest
available
set
manually
annotated
categories;
2)
classification-aware
neural
topic
model
(CANTM)
designed
category
classification
discovery;
3)
an
extensive
analysis
with
respect
time,
volume,
false
type,
type
origin
source.
