A deep understanding of influencer marketing in the tourism industry: a structural analysis of unstructured text
Current Issues in Tourism,
Год журнала:
2024,
Номер
unknown, С. 1 - 11
Опубликована: Июнь 26, 2024
Using
both
a
word
frequency
approach
and
cutting-edge
transfer
learning
technique
for
natural
language
processing
with
BERTopic,
the
present
study
analysed
entire
texts
from
top
40
travel
influencers'
Instagram
posts
(n
=
23,223).
Among
256
features
that
we
initially
extracted,
ranked
19
using
machine
algorithm
XGBoost
estimated
effects
of
these
on
consumer
engagement
Negative
Binomial
regression.
The
results
show
seasonal
trips,
destination
recommendations,
recommendations
fashion
during
trip,
emphasising
travel-related
emotion
generate
higher
level
engagement.
For
message
strategy,
specifically
focusing
linguistic
features,
it
is
recommended
influencers
use
analytic,
authentic,
want-related,
space-related
words
in
caption
but
should
avoid
too
many
hashtags.
Also,
overall,
sending
messages
night,
are
long
or
emojis.
Язык: Английский
Leveraging LLMs for Efficient Topic Reviews
Applied Sciences,
Год журнала:
2024,
Номер
14(17), С. 7675 - 7675
Опубликована: Авг. 30, 2024
This
paper
presents
the
topic
review
(TR),
a
novel
semi-automatic
framework
designed
to
enhance
efficiency
and
accuracy
of
literature
reviews.
By
leveraging
capabilities
large
language
models
(LLMs),
TR
addresses
inefficiencies
error-proneness
traditional
methods,
especially
in
rapidly
evolving
fields.
The
significantly
improves
processes
by
integrating
advanced
text
mining
machine
learning
techniques.
Through
case
study
approach,
offers
step-by-step
methodology
that
begins
with
query
generation
refinement,
followed
semi-automated
identify
relevant
articles.
LLMs
are
then
employed
extract
categorize
key
themes
concepts,
facilitating
an
in-depth
analysis.
approach
demonstrates
transformative
potential
natural
processing
With
average
similarity
69.56%
between
generated
indexed
keywords,
effectively
manages
growing
volume
scientific
publications,
providing
researchers
robust
strategies
for
complex
synthesis
advancing
knowledge
various
domains.
An
expert
analysis
highlights
positive
Fleiss’
Kappa
score,
underscoring
significance
interpretability
results.
Язык: Английский
Navigating artificial general intelligence development: societal, technological, ethical, and brain-inspired pathways
Scientific Reports,
Год журнала:
2025,
Номер
15(1)
Опубликована: Март 11, 2025
This
study
examines
the
imperative
to
align
artificial
general
intelligence
(AGI)
development
with
societal,
technological,
ethical,
and
brain-inspired
pathways
ensure
its
responsible
integration
into
human
systems.
Using
PRISMA
framework
BERTopic
modeling,
it
identifies
five
key
shaping
AGI's
trajectory:
(1)
societal
integration,
addressing
broader
impacts,
public
adoption,
policy
considerations;
(2)
technological
advancement,
exploring
real-world
applications,
implementation
challenges,
scalability;
(3)
explainability,
enhancing
transparency,
trust,
interpretability
in
AGI
decision-making;
(4)
cognitive
ethical
considerations,
linking
evolving
architectures
frameworks,
accountability,
consequences;
(5)
systems,
leveraging
neural
models
improve
learning
efficiency,
adaptability,
reasoning
capabilities.
makes
a
unique
contribution
by
systematically
uncovering
underexplored
themes,
proposing
conceptual
that
connects
AI
advancements
practical
multifaceted
technical,
challenges
of
development.
The
findings
call
for
interdisciplinary
collaboration
bridge
critical
gaps
governance,
alignment
while
strategies
equitable
access,
workforce
adaptation,
sustainable
integration.
Additionally,
highlights
emerging
research
frontiers,
such
as
AGI-consciousness
interfaces
collective
offering
new
integrate
human-centered
applications.
By
synthesizing
insights
across
disciplines,
this
provides
comprehensive
roadmap
guiding
ways
balance
innovation
responsibilities,
advancing
progress
well-being.
Язык: Английский
Leveraging social media for public health: NLP implementations for blood donation data analysis in Japan
Roberto Espinoza,
Kazumasa Kishimoto,
Chang Liu
и другие.
Social Network Analysis and Mining,
Год журнала:
2025,
Номер
15(1)
Опубликована: Апрель 3, 2025
Язык: Английский
Product Detection in Unmanned Supermarkets Based on Optimized YOLOv8
Communications in computer and information science,
Год журнала:
2025,
Номер
unknown, С. 233 - 240
Опубликована: Янв. 1, 2025
Язык: Английский
Unraveling media perspectives: a comprehensive methodology combining large language models, topic modeling, sentiment analysis, and ontology learning to analyse media bias
Journal of Computational Social Science,
Год журнала:
2025,
Номер
8(2)
Опубликована: Фев. 25, 2025
Язык: Английский
Agenda-setting effects for covid-19 vaccination: Insights from 10 million textual data from social media and news articles using BERTopic
International Journal of Information Management,
Год журнала:
2025,
Номер
83, С. 102907 - 102907
Опубликована: Апрель 8, 2025
Язык: Английский
Machine Learning for Depression Detection on Web and Social Media
International Journal on Semantic Web and Information Systems,
Год журнала:
2024,
Номер
20(1), С. 1 - 28
Опубликована: Апрель 26, 2024
Depression,
a
significant
psychiatric
disorder,
affects
individuals'
physical
well-being
and
daily
functioning.
This
focused
analysis
provides
comprehensive
exploration
of
contemporary
research
conducted
between
2012
2023
that
delves
into
the
utilization
sophisticated
machine
learning
methodologies
aimed
at
identifying
correlates
depression
within
social
media
content.
Our
study
meticulously
dissects
various
data
sources
performs
examination
different
algorithms
cited
in
researched
articles
literature,
aiming
to
pinpoint
an
approach
can
enhance
detection
accuracy.
Furthermore,
we
have
scrutinized
use
varied
from
platforms
pinpointed
emerging
trends,
notably
spotlighting
novel
applications
artificial
neural
networks
for
image
processing
classification,
along
with
advanced
gait
models.
results
offer
essential
direction
future
on
enhancing
precision,
acting
as
valuable
reference
academic
industry
scholars
this
field.
Язык: Английский
Topic Modeling as a Tool to identify Research Diversity: A Study Across Dental Disciplines
Опубликована: Авг. 22, 2024
This
study
investigates
the
diversity
and
evolution
of
research
topics
within
dental
sciences
from
1994
to
2023
using
topic
modeling
Shannon's
entropy
as
a
measure
diversity.
We
analyzed
dataset
412036
scientific
articles
across
six
disciplines:
Orthodontics,
Pros-thodontics,
Periodontics,
Implant
Dentistry,
Oral
Surgery,
Restorative
Dentistry.
relies
on
BERTopic
identify
distinct
each
field.
The
revealed
significant
shifts
in
focus
over
time,
with
some
disciplines
exhibiting
robust
growth
article
numbers
such
Periodontics
Prosthodontics.
application
an
increasing
diversification
efforts
while
others,
like
Prosthodontics,
spite
their
size
high
number
topics,
maintain
more
specialized
focus.
Taken
together,
our
findings
describe
dynamic
nature
re-search
highlight
balance
several
key
areas
Язык: Английский
Topic Modeling as a Tool to Identify Research Diversity: A Study across Dental Disciplines
Metrics,
Год журнала:
2024,
Номер
1(1), С. 3 - 3
Опубликована: Окт. 13, 2024
This
study
investigates
the
diversity
and
evolution
of
research
topics
within
dental
sciences
from
1994
to
2023,
using
Topic
modeling
Shannon’s
entropy
as
a
measure
diversity.
We
analyzed
dataset
412,036
scientific
articles
across
six
disciplines:
Orthodontics,
Prosthodontics,
Periodontics,
Implant
Dentistry,
Oral
Surgery,
Restorative
Dentistry.
relies
on
BERTopic
identify
distinct
each
field.
The
revealed
significant
shifts
in
focus
over
time,
with
some
disciplines
exhibiting
robust
growth
article
numbers,
such
Periodontics
Prosthodontics.
However,
despite
overall
increase
publications,
number
per
discipline
varied,
Dentistry
increasing
at
faster
rate
exceeding
50
last
15
years.
observed
an
diversification
efforts
levels
consistently
above
2
progressively
increasing.
In
contrast,
fields
high
publication
output,
maintained
more
specialized
focus,
reflected
remaining
below
1.5.
Surgery
showed
steep
until
2000,
after
which
it
stabilized.
Taken
together,
our
findings
describe
dynamic
nature
highlight
balance
several
key
areas
Язык: Английский