This is a table of type bigram and their frequencies. Use it to search & browse the list to learn more about your study carrel.
bigram | frequency |
---|---|
contact tracing | 466 |
mental health | 152 |
social media | 149 |
public health | 119 |
data collection | 79 |
social network | 77 |
social networks | 72 |
machine learning | 67 |
ml systems | 63 |
user seal | 63 |
personality traits | 60 |
natural language | 59 |
hate speech | 59 |
usable security | 57 |
digital contact | 56 |
seal check | 55 |
cord uid | 55 |
doc id | 55 |
gross leakage | 54 |
smart contract | 54 |
location data | 53 |
platform openness | 53 |
side openness | 52 |
health care | 50 |
social recommendation | 50 |
negative disconfirmation | 50 |
proximity tracing | 48 |
user profile | 48 |
deep learning | 48 |
users may | 46 |
personal data | 44 |
recommender systems | 43 |
tracing apps | 43 |
attention mechanism | 42 |
signal strength | 42 |
based contact | 41 |
anonymous ids | 41 |
user interfaces | 41 |
health authorities | 41 |
quantum moves | 41 |
user data | 39 |
information processing | 37 |
platform performance | 37 |
virtual reality | 36 |
easy reading | 35 |
infected person | 34 |
label propagation | 34 |
collaborative filtering | 34 |
social distancing | 34 |
actual gross | 34 |
contact recommendation | 33 |
infected user | 33 |
matrix factorization | 33 |
question answering | 33 |
proposed model | 32 |
infected users | 32 |
palliative care | 32 |
bloom filter | 32 |
health information | 32 |
verified users | 31 |
user interface | 31 |
mobile device | 31 |
word embeddings | 30 |
recommendation framework | 30 |
gcg app | 30 |
encounter information | 30 |
two different | 30 |
data protection | 29 |
demand diversity | 29 |
information retrieval | 29 |
based approach | 29 |
ground truth | 29 |
mood score | 29 |
large number | 29 |
device id | 29 |
mobile app | 29 |
end users | 28 |
infection status | 28 |
vr system | 28 |
united states | 28 |
tracing proposals | 28 |
dcts app | 27 |
fit testing | 27 |
systematic processing | 27 |
training data | 26 |
time period | 26 |
phone number | 26 |
table shows | 26 |
user may | 26 |
trustworthy comment | 26 |
mobile devices | 26 |
knowledge complexity | 26 |
time interval | 26 |
government agency | 26 |
data sets | 26 |
recommendation systems | 25 |
review embedding | 25 |
user engagement | 25 |
validated network | 25 |
mobile application | 25 |
prox tree | 24 |
may also | 24 |
information technology | 24 |
regression model | 24 |
infected individual | 24 |
sentiment analysis | 24 |
infectious diseases | 24 |
smart contracts | 24 |
different types | 24 |
mac addresses | 24 |
user behaviour | 24 |
nan doi | 24 |
tested positive | 24 |
bluetooth low | 24 |
low energy | 23 |
mobile apps | 23 |
two users | 23 |
diversity constraint | 23 |
phishing susceptibility | 23 |
infected people | 23 |
manual contact | 23 |
official accounts | 23 |
depression detection | 22 |
right wing | 22 |
electric scooters | 22 |
infectious disease | 22 |
tracing technology | 22 |
close contact | 22 |
data collected | 22 |
target object | 22 |
word embedding | 22 |
data privacy | 22 |
user interaction | 22 |
proximity sensing | 22 |
health behaviors | 22 |
vr systems | 22 |
even though | 22 |
nan sha | 22 |
collected data | 21 |
interaction design | 21 |
data set | 21 |
blockchain database | 21 |
tracing service | 21 |
interest correlation | 21 |
wifi sensing | 21 |
data points | 21 |
information systems | 21 |
results show | 21 |
health status | 21 |
tracing app | 21 |
user experience | 21 |
proximity chain | 21 |
user embeddings | 21 |
heuristic processing | 21 |
among users | 20 |
allows users | 20 |
privacy concerns | 20 |
side users | 20 |
online social | 20 |
mac address | 20 |
help users | 20 |
positive user | 20 |
depressed users | 20 |
level attention | 20 |
selected apps | 20 |
future work | 20 |
bloom filters | 20 |
set intersection | 20 |
community transmission | 19 |
surveillance systems | 19 |
sensor data | 19 |
novel coronavirus | 19 |
proposed method | 19 |
widely used | 19 |
recommendation performance | 19 |
truth discovery | 19 |
national mood | 19 |
scooter users | 19 |
predictive values | 19 |
health organization | 19 |
total number | 19 |
diagnosed carriers | 19 |
therapy game | 19 |
anxiety apps | 19 |
health officials | 19 |
big five | 19 |
health professionals | 18 |
user reliability | 18 |
language processing | 18 |
user vr | 18 |
anxiety disorders | 18 |
phishing emails | 18 |
decentralized approach | 18 |
deep breathing | 18 |
ml system | 18 |
learning model | 18 |
target user | 18 |
health management | 18 |
use cases | 18 |
institution accounts | 18 |
twitter users | 18 |
world health | 18 |
correlation vector | 18 |
base stations | 17 |
based models | 17 |
healthcare interventions | 17 |
private set | 17 |
every day | 17 |
third party | 17 |
tracing system | 17 |
case study | 17 |
two main | 17 |
knowledge graph | 17 |
information behavior | 17 |
infection chain | 17 |
centric approach | 17 |
design goals | 17 |
registered users | 16 |
decentralized proposals | 16 |
data analysis | 16 |
users whose | 16 |
many countries | 16 |
disease surveillance | 16 |
time series | 16 |
location information | 16 |
data source | 16 |
experimental results | 16 |
infected individuals | 16 |
exposure notification | 16 |
web search | 16 |
tentative solution | 16 |
social relations | 16 |
learning models | 16 |
received signal | 16 |
bipartite network | 16 |
contact trace | 16 |
next step | 16 |
neural networks | 16 |
phishing attacks | 16 |
anonymous id | 16 |
mobile phone | 16 |
user privacy | 16 |
diagnosed carrier | 15 |
publicly available | 15 |
google analytics | 15 |
network embedding | 15 |
table presents | 15 |
visual information | 15 |
surveillance system | 15 |
tests positive | 15 |
big data | 15 |
relation network | 15 |
based methods | 15 |
structural equation | 15 |
social networking | 15 |
data sources | 15 |
business value | 15 |
information dissemination | 15 |
historical data | 15 |
first step | 15 |
user needs | 15 |
distance estimation | 15 |
high supply | 15 |
ir models | 15 |
neural network | 15 |
risk assessment | 15 |
tracing applications | 15 |
contract location | 15 |
false positive | 15 |
healthcare recommendation | 15 |
data elements | 15 |
citizen science | 15 |
retweet network | 15 |
pilot study | 15 |
evolving relation | 15 |
recommendation task | 15 |
better performance | 14 |
real world | 14 |
service layer | 14 |
one hand | 14 |
social engineering | 14 |
preserving proximity | 14 |
see section | 14 |
structural gameplay | 14 |
based model | 14 |
security mechanisms | 14 |
users will | 14 |
breathing exercises | 14 |
infection window | 14 |
cloud application | 14 |
proposed approach | 14 |
personal information | 14 |
may lead | 14 |
mood scores | 14 |
two types | 14 |
among labels | 14 |
electronic health | 14 |
generic reflections | 14 |
retweet prediction | 14 |
comparative analysis | 14 |
user representation | 14 |
centralized proposals | 14 |
telco company | 14 |
exploratory search | 14 |
privacy protection | 14 |
fake news | 14 |
physical distancing | 14 |
statistically significant | 14 |
contract group | 14 |
dual approach | 14 |
semantic parsing | 14 |
end user | 14 |
fog nodes | 14 |
fog computing | 14 |
locations visited | 14 |
infection chains | 14 |
confirmed covid | 13 |
intersection cardinality | 13 |
web content | 13 |
privacy issues | 13 |
information security | 13 |
information diffusion | 13 |
previous works | 13 |
mobile applications | 13 |
adaptive user | 13 |
per day | 13 |
previous studies | 13 |
unique id | 13 |
user will | 13 |
tentative solutions | 13 |
determine whether | 13 |
user behavior | 13 |
mobile tracing | 13 |
app will | 13 |
linear regression | 13 |
candidate users | 13 |
creative commons | 13 |
id i | 13 |
ios apps | 13 |
influenza pandemic | 13 |
benchmark models | 13 |
decision making | 13 |
coronavirus disease | 13 |
future research | 13 |
italia viva | 13 |
sequential question | 13 |
recommendation methods | 13 |
recommendation design | 13 |
safe paths | 13 |
reading framework | 13 |
learning algorithms | 13 |
raw data | 13 |
data will | 13 |
access points | 13 |
expressive writing | 12 |
visual programming | 12 |
wechat official | 12 |
graph convolutional | 12 |
central server | 12 |
mass quarantine | 12 |
potential exposure | 12 |
close proximity | 12 |
real time | 12 |
reverse prox | 12 |
following two | 12 |
user interactions | 12 |
worth noting | 12 |
modal features | 12 |
steel blue | 12 |
feature engineering | 12 |
health impacts | 12 |
previous section | 12 |
south korea | 12 |
community detection | 12 |
networking sites | 12 |
time duration | 12 |
management methods | 12 |
window size | 12 |
knowledge base | 12 |
user study | 12 |
comment embeddings | 12 |
data processing | 12 |
implicit association | 12 |
section iv | 12 |
see table | 12 |
suspected cases | 12 |
user embedding | 12 |
healthcare chatbots | 12 |
blog posts | 12 |
qualitative comparative | 12 |
decision tree | 12 |
different users | 12 |
use scenarios | 12 |
make use | 12 |
non reputable | 12 |
medical institution | 12 |
shifting individuals | 12 |
related information | 12 |
model components | 12 |
omnidirectional camera | 12 |
sensitive information | 12 |
via bluetooth | 12 |
motivational interviewing | 12 |
information network | 12 |
user information | 12 |
bluetooth signal | 12 |
system will | 11 |
time window | 11 |
allow users | 11 |
passive wifi | 11 |
online healthcare | 11 |
care professionals | 11 |
health tracing | 11 |
app store | 11 |
new york | 11 |
care workers | 11 |
five personality | 11 |
legitimate users | 11 |
next section | 11 |
many different | 11 |
data mining | 11 |
previous work | 11 |
positive users | 11 |
health issues | 11 |
social support | 11 |
app users | 11 |
prediction model | 11 |
push notification | 11 |
age group | 11 |
individual user | 11 |
contextual information | 11 |
negative users | 11 |
nonmedical institution | 11 |
review text | 11 |
scooter share | 11 |
physical activity | 11 |
healthcare provision | 11 |
google assistant | 11 |
advertising packet | 11 |
negative user | 11 |
proximity tree | 11 |
five proposals | 11 |
high demand | 11 |
network phishing | 11 |
learning framework | 11 |
equation modeling | 11 |
navigation methods | 11 |
proximity chains | 11 |
unverified users | 11 |
expressive interviewing | 11 |
random tcns | 11 |
based proximity | 11 |
every user | 11 |
contact data | 11 |
contact history | 11 |
search queries | 11 |
false positives | 11 |
test results | 11 |
hybrid model | 11 |
contact time | 11 |
scooter use | 11 |
probabilistic matrix | 11 |
provo city | 11 |
associations among | 11 |
challenge embeddings | 11 |
existing literature | 11 |
ir axioms | 11 |
candidate user | 11 |
security measures | 11 |
mental illness | 11 |
allows us | 11 |
help us | 11 |
latent trustworthy | 11 |
heart rate | 10 |
aarogya setu | 10 |
better understand | 10 |
loss challenges | 10 |
false negative | 10 |
semantic information | 10 |
healthcare system | 10 |
replay attacks | 10 |
toy example | 10 |
location trail | 10 |
proposed framework | 10 |
word vec | 10 |
two large | 10 |
will also | 10 |
based social | 10 |
contract tracing | 10 |
confusion matrix | 10 |
support vector | 10 |
infected cases | 10 |
service providers | 10 |
source code | 10 |
lockdown measures | 10 |
mab without | 10 |
proposed system | 10 |
session duration | 10 |
media users | 10 |
medical personnel | 10 |
grounded theory | 10 |
conversational interface | 10 |
creative drawing | 10 |
detection using | 10 |
supplementary material | 10 |
reliability score | 10 |
card sort | 10 |
based feature | 10 |
google play | 10 |
dcts law | 10 |
rating prediction | 10 |
visual impairment | 10 |
recent years | 10 |
wide range | 10 |
many people | 10 |
related work | 10 |
theoretical model | 10 |
bluetooth technology | 10 |
list box | 10 |
systematic review | 10 |
healthcare recommendations | 10 |
network structure | 10 |
usage patterns | 10 |
section presents | 10 |
law proposal | 10 |
objective function | 10 |
mass surveillance | 10 |
people may | 10 |
prototype system | 10 |
computer vision | 10 |
based approaches | 10 |
model performs | 10 |
user control | 10 |
item i | 10 |
hate generation | 10 |
data storage | 10 |
privacy design | 10 |
reinforcement learning | 10 |
best performance | 10 |
virtual environment | 10 |
gps location | 10 |
proximity report | 10 |
oriented dimension | 10 |
current study | 10 |
likelihood ratios | 10 |
new interaction | 10 |
observed signatures | 10 |
task completion | 10 |
less likely | 10 |
means clustering | 10 |
test result | 10 |
features representing | 9 |
related injuries | 9 |
information needs | 9 |
wing parties | 9 |
cnn model | 9 |
international conference | 9 |
critical mass | 9 |
location trails | 9 |
seed keys | 9 |
contact network | 9 |
different scenarios | 9 |
personality trait | 9 |
association labels | 9 |
speech detection | 9 |
everyday life | 9 |
mental disorders | 9 |
performance effect | 9 |
sample size | 9 |
seed key | 9 |
made available | 9 |
id generation | 9 |
physiological signals | 9 |
pure exploitation | 9 |
visited items | 9 |
point cloud | 9 |
specific user | 9 |
data element | 9 |
great potential | 9 |
users based | 9 |
mobile service | 9 |
users need | 9 |
natural person | 9 |
health center | 9 |
position information | 9 |
pure exploration | 9 |
directed validated | 9 |
social influence | 9 |
label information | 9 |
daily lives | 9 |
representation learning | 9 |
infected area | 9 |
weight loss | 9 |
behavioral therapy | 9 |
starting point | 9 |
contact rate | 9 |
tracing services | 9 |
using vr | 9 |
whose stress | 9 |
various types | 9 |
news articles | 9 |
mobile phones | 9 |
recommender system | 9 |
results indicate | 9 |
individuals may | 9 |
individual accounts | 9 |
simulation engine | 9 |
test time | 9 |
document attention | 9 |
virtual therapy | 9 |
path loss | 9 |
proximity data | 9 |
major issues | 9 |
political parties | 9 |
av treatment | 9 |
online hate | 9 |
time point | 9 |
good enough | 9 |
vector space | 9 |
device ids | 9 |
exogenous signals | 9 |
location privacy | 9 |
logistic regression | 9 |
electric scooter | 9 |
healthcare needs | 9 |
user profiles | 9 |
smartphone apps | 9 |
disease control | 9 |
may need | 9 |
three weeks | 9 |
two devices | 9 |
computer system | 9 |
pandemic influenza | 9 |
quantum computer | 9 |
local storage | 9 |
likert scale | 9 |
timing information | 9 |
compartmental model | 9 |
commons licence | 9 |
three different | 9 |
client application | 8 |
data may | 8 |
recommendation algorithms | 8 |
significant difference | 8 |
based filtering | 8 |
security design | 8 |
increasing number | 8 |
unintentional misuse | 8 |
following three | 8 |
term frequency | 8 |
rssi values | 8 |
health record | 8 |
take advantage | 8 |
high accuracy | 8 |
empirical study | 8 |
platform innovation | 8 |
semantic parser | 8 |
future directions | 8 |
average challenge | 8 |
seal checks | 8 |
browser extension | 8 |
another one | 8 |
scooters may | 8 |
negative predictive | 8 |
bike lanes | 8 |
qualitative data | 8 |
persuasion principles | 8 |
verified user | 8 |
security requirements | 8 |
enable contact | 8 |
security incidents | 8 |
proposed recommendation | 8 |
model outperforms | 8 |
query expression | 8 |
many studies | 8 |
implicit associations | 8 |
two categories | 8 |
cognitive disabilities | 8 |
innovation attribute | 8 |
collect data | 8 |
advertised tcns | 8 |
epidemic control | 8 |
study also | 8 |
transaction attribute | 8 |
significantly worse | 8 |
level user | 8 |
day period | 8 |
helps us | 8 |
health histories | 8 |
second order | 8 |
digital signature | 8 |
liking behavior | 8 |
user tests | 8 |
covid safe | 8 |
one user | 8 |
prediction task | 8 |
user base | 8 |
third parties | 8 |
behavior patterns | 8 |
app stores | 8 |
hateful tweets | 8 |
user tweets | 8 |
cognitive behavioral | 8 |
rotation navigation | 8 |
modeling assumption | 8 |
also show | 8 |
application will | 8 |
exposure risk | 8 |
nearby devices | 8 |
contract contract | 8 |
proximity detection | 8 |
computer security | 8 |
passive disuse | 8 |
scooter injuries | 8 |
design process | 8 |
personal privacy | 8 |
another user | 8 |
research question | 8 |
convolutional networks | 8 |
preserving contact | 8 |
data usage | 8 |
mood status | 8 |
robust estimation | 8 |
location history | 8 |
content analysis | 8 |
selection rate | 8 |
respirator fit | 8 |
future studies | 8 |
based tracing | 8 |
air pollution | 8 |
length normalization | 8 |
learning methods | 8 |
encountered tcns | 8 |
connectable advertising | 8 |
convolutional neural | 8 |
european union | 8 |
training set | 8 |
attention weights | 8 |
tracing protocol | 8 |
best performing | 8 |
modalities attribute | 8 |
wifi network | 8 |
reliable users | 8 |
positive influence | 8 |
weak ties | 8 |
design review | 8 |
individual differences | 8 |
health services | 8 |
play store | 8 |
human computation | 8 |
university campuses | 8 |
potential users | 8 |
among others | 8 |
empirical material | 8 |
privacy risks | 8 |
chief complaints | 8 |
online media | 8 |
interaction concept | 8 |
direct contact | 8 |
community question | 8 |
generated content | 8 |
basic workflow | 8 |
positive cases | 8 |
least one | 8 |
based method | 8 |
manufacturing companies | 8 |
existing studies | 8 |
activity history | 8 |
rss value | 8 |
gcg backend | 8 |
feature vector | 8 |
closely related | 8 |
drawing game | 8 |
large scale | 8 |
mobile contact | 8 |
trace data | 8 |
check whether | 8 |
sky blue | 8 |
privacy preserving | 8 |
test centers | 8 |
recommendation model | 8 |
system provides | 8 |
data using | 8 |
related issues | 8 |
interval number | 8 |
confirmed cases | 8 |
personal use | 8 |
vast majority | 8 |
mobile number | 8 |
hash function | 8 |
years old | 8 |
gleamviz tool | 8 |
manufacturing industry | 8 |
discussion forums | 8 |
gleamviz proxy | 7 |
six different | 7 |
operating systems | 7 |
tracing technologies | 7 |
two sets | 7 |
tolerable error | 7 |
core categories | 7 |
using deep | 7 |
economic crisis | 7 |
centralized approach | 7 |
individual users | 7 |
small number | 7 |
user uploads | 7 |
email phishing | 7 |
access point | 7 |
transaction tx | 7 |
health records | 7 |
design principles | 7 |
global epidemic | 7 |
respiratory syndrome | 7 |
degree sequence | 7 |
device mac | 7 |
real network | 7 |
distributed manufacturing | 7 |
design approaches | 7 |
text data | 7 |
user vertex | 7 |
risk group | 7 |
prior literature | 7 |
may affect | 7 |
smartphone application | 7 |
alert dialog | 7 |
lockdown area | 7 |
will notify | 7 |
ca persons | 7 |
comment embedding | 7 |
iot systems | 7 |
globally distributed | 7 |
common neighbors | 7 |
usability science | 7 |
input data | 7 |
android apps | 7 |
donald trump | 7 |
inversely proportional | 7 |
recommendation context | 7 |
pseudorandom id | 7 |
model based | 7 |
information sharing | 7 |
general data | 7 |
random mac | 7 |
different political | 7 |
phishing email | 7 |
error behaviour | 7 |
dialogue systems | 7 |
qr code | 7 |
unsupervised machine | 7 |
gps data | 7 |
global scale | 7 |
probability distribution | 7 |
app user | 7 |
operating cost | 7 |
scooter program | 7 |
review score | 7 |
way anova | 7 |
dialogue system | 7 |
artificial intelligence | 7 |
will change | 7 |
motivate users | 7 |
civil liberties | 7 |
controlled trial | 7 |
location tracking | 7 |
signature protocol | 7 |
will lead | 7 |
healthcare providers | 7 |
offline precision | 7 |
standard deviation | 7 |
high knowledge | 7 |
depression symptoms | 7 |
public database | 7 |
health authority | 7 |
physical therapy | 7 |
data security | 7 |
challenge selection | 7 |
per post | 7 |
null model | 7 |
exponential growth | 7 |
post reliability | 7 |
two decentralized | 7 |
share programs | 7 |
infected status | 7 |
privacy dashboard | 7 |
game elements | 7 |
tolerable errors | 7 |
global pandemic | 7 |
smartphone will | 7 |
tcn generation | 7 |
minimal data | 7 |
least squares | 7 |
user reports | 7 |
attribute features | 7 |
risk score | 7 |
dark orange | 7 |
high risk | 7 |
recommendation approaches | 7 |
tracing tools | 7 |
achieve better | 7 |
existing research | 7 |
positive test | 7 |
large amount | 7 |
short period | 7 |
also provide | 7 |
tutorial levels | 7 |
emergency management | 7 |
dimensional vector | 7 |
short time | 7 |
user consent | 7 |
secret key | 7 |
cuckoo filter | 7 |
vision techniques | 7 |
gleamviz client | 7 |
behavior change | 7 |
platform users | 7 |
demand side | 7 |
rss values | 7 |
dataset contains | 7 |
smart contact | 7 |
four main | 7 |
social context | 7 |
knowledge bases | 7 |
electronic medical | 7 |
information system | 7 |
helping users | 7 |
several studies | 7 |
range mobility | 7 |
higher weights | 7 |
threat models | 7 |
security research | 7 |
query terms | 7 |
general locations | 7 |
targeted users | 7 |
recommendation diversity | 7 |
two major | 7 |
iot devices | 7 |
theoretical sampling | 7 |
different features | 7 |
registration process | 7 |
help people | 7 |
negative influence | 7 |
challenge types | 7 |
protection regulation | 7 |
data flow | 7 |
observed tcns | 7 |
structured interviews | 7 |
hash functions | 7 |
provide users | 7 |
internet access | 7 |
may help | 7 |
multiple devices | 7 |
high level | 7 |
news sources | 7 |
information need | 7 |
users tend | 7 |
time span | 7 |
provide information | 7 |
based covid | 7 |
weight management | 7 |
means algorithm | 7 |
blue community | 7 |
looking forward | 7 |
openness will | 7 |
network users | 7 |
wing community | 7 |
results using | 7 |
graph algorithm | 7 |
helmet use | 7 |
positively tested | 7 |
two weeks | 7 |
current covid | 7 |
cloud data | 7 |
zip code | 7 |
non trivial | 7 |
living room | 7 |
interest correlations | 7 |
cognitive load | 7 |
armed bandit | 7 |
average pooling | 7 |
prior studies | 7 |
personalized recommendation | 7 |
web services | 7 |
precise proximity | 7 |
informed consent | 7 |
political sub | 7 |
hard level | 7 |
users tested | 7 |
political polarization | 7 |
advertising channels | 7 |
currently available | 7 |
analysis methods | 7 |
ble signals | 7 |
review process | 7 |
sct system | 7 |
effect size | 7 |
leakage detection | 7 |
order proximity | 7 |
two approaches | 7 |
proxy middleware | 7 |
bipartite directed | 7 |
information regarding | 7 |
embedding model | 7 |
story understanding | 6 |
security awareness | 6 |
dictionary learning | 6 |
heterogeneous evolving | 6 |
semantic meaning | 6 |
system using | 6 |
technology acceptance | 6 |
recurrent neural | 6 |
known locations | 6 |
measurement data | 6 |
threat modeling | 6 |
approach uses | 6 |
gold standard | 6 |
based therapy | 6 |
emergency department | 6 |
large networks | 6 |
epinions dataset | 6 |
mobility layer | 6 |
hybrid deep | 6 |
uses bluetooth | 6 |
negative correlation | 6 |
motor vehicles | 6 |
current results | 6 |
dirichlet allocation | 6 |
easy level | 6 |
initial conditions | 6 |
health problems | 6 |
using multi | 6 |
smart home | 6 |
time spent | 6 |
much information | 6 |
undirected version | 6 |
following sections | 6 |
user might | 6 |
search query | 6 |
prior research | 6 |
two iterations | 6 |
order contact | 6 |
reputable sources | 6 |
recommendation system | 6 |
bluetooth mac | 6 |
latter two | 6 |
wifi networks | 6 |
tracing systems | 6 |
configuration model | 6 |
art methods | 6 |
affective statuses | 6 |
using natural | 6 |
table i | 6 |
perform contact | 6 |
stored data | 6 |
criminal law | 6 |
user input | 6 |
annotated challenge | 6 |
computing framework | 6 |
user profiling | 6 |
advertising mode | 6 |
general purpose | 6 |
user length | 6 |
new challenges | 6 |
literature review | 6 |
user adoption | 6 |
subcommunity contains | 6 |
extracted features | 6 |
android app | 6 |
contact records | 6 |
will use | 6 |
intensity level | 6 |
completion time | 6 |
unlinkable design | 6 |
user name | 6 |
indian inst | 6 |
interestingly enough | 6 |
weighted posts | 6 |
may include | 6 |
lockdown management | 6 |
multifaceted interest | 6 |
also observe | 6 |
acute respiratory | 6 |
wise attention | 6 |
generated texts | 6 |
classification problem | 6 |
tracing process | 6 |
three centralized | 6 |
health outcomes | 6 |
text classification | 6 |
classification performance | 6 |
computational tool | 6 |
affective state | 6 |
government officials | 6 |
sequence features | 6 |
mab framework | 6 |
class imbalance | 6 |
false news | 6 |
contextual variables | 6 |
users interact | 6 |
tracing using | 6 |
one study | 6 |
user based | 6 |
see sect | 6 |
data structure | 6 |
highly rated | 6 |
clustering algorithm | 6 |
personal health | 6 |
system used | 6 |
digital ariadne | 6 |
tracing solutions | 6 |
term discrimination | 6 |
share information | 6 |
games like | 6 |
normal breathing | 6 |
service provisioning | 6 |
search engine | 6 |
detecting depression | 6 |
trained word | 6 |
qca method | 6 |
traditional methods | 6 |
signature generation | 6 |
health emergency | 6 |
study makes | 6 |
two models | 6 |
linkage attacks | 6 |
information provided | 6 |
exposure notifications | 6 |
second scenario | 6 |
identify users | 6 |
high number | 6 |
vr therapy | 6 |
blue subcommunity | 6 |
predictive value | 6 |
many times | 6 |
device key | 6 |
users often | 6 |
takes place | 6 |
diffusion dynamics | 6 |
given respirator | 6 |
via social | 6 |
long sequences | 6 |
per user | 6 |
vr integration | 6 |
contract service | 6 |
mobile unit | 6 |
topics discussed | 6 |
user i | 6 |
scooter riders | 6 |
error recovery | 6 |
computing party | 6 |
item embeddings | 6 |
multiple dimensions | 6 |
limited number | 6 |
distancing score | 6 |
first two | 6 |
user satisfaction | 6 |
comparative method | 6 |
feature space | 6 |
without user | 6 |
malicious party | 6 |
use computer | 6 |
active users | 6 |
model builder | 6 |
second layer | 6 |
textual features | 6 |
since i | 6 |
located users | 6 |
layout planning | 6 |
get used | 6 |
also used | 6 |
baseline methods | 6 |
graph embedding | 6 |
centralized database | 6 |
covid positive | 6 |
exogenous attention | 6 |
neighboring devices | 6 |
across different | 6 |
might also | 6 |
error may | 6 |
visiting records | 6 |
ids broadcast | 6 |
latent dirichlet | 6 |
enables us | 6 |
health organizations | 6 |
tablet users | 6 |
card sorting | 6 |
design considerations | 6 |
user tracking | 6 |
echo chambers | 6 |
strength index | 6 |
system uses | 6 |
retweet dynamics | 6 |
new ways | 6 |
tracking model | 6 |
central authority | 6 |
use case | 6 |
loss rate | 6 |
beta version | 6 |
citizen cyberscience | 6 |
play counts | 6 |
reading reasoner | 6 |
media platforms | 6 |
functionality features | 6 |
loss function | 6 |
sidewalk riding | 6 |
across multiple | 6 |
optimization problem | 6 |
also important | 6 |
global graph | 6 |
insert table | 6 |
approximated review | 6 |
time periods | 6 |
selection histories | 6 |
system needs | 6 |
certain period | 6 |
five users | 6 |
risk users | 6 |
openness decision | 6 |
health crisis | 6 |
small effect | 6 |
government agencies | 6 |
game design | 6 |
information broadcast | 6 |
computer interaction | 6 |
community severance | 6 |
web application | 6 |
management dimensions | 6 |
severe acute | 6 |
specific users | 6 |
programming language | 6 |
knowledge innovation | 6 |
location spoofing | 6 |
every time | 6 |
life cycle | 6 |
per session | 6 |
test set | 6 |
activation function | 6 |
virtual environments | 6 |
rating matrix | 6 |
period weight | 6 |
paramount importance | 6 |
available posts | 6 |
standing vr | 6 |
feature extraction | 6 |
wireless technology | 6 |
operating system | 6 |
hybrid design | 6 |
see appendix | 6 |
base station | 6 |
contract city | 6 |
recent studies | 6 |
propagation algorithm | 6 |
suspected victim | 6 |
several limitations | 6 |
economic activities | 6 |
vr environment | 6 |
representative task | 6 |
randomly generated | 6 |
may make | 6 |
epidemiological models | 6 |
hong kong | 6 |
gated recurrent | 6 |
streaming api | 6 |
stress bef | 6 |
positive covid | 6 |
social relation | 6 |
vector representations | 6 |
randomized controlled | 6 |
notification system | 6 |
epidemic containment | 6 |
phone app | 6 |
regression models | 6 |
may find | 6 |
active abuse | 6 |
tracing approach | 6 |
usability testing | 6 |
two smartphones | 6 |
privacy considerations | 6 |
time frame | 6 |
section describes | 6 |
platform business | 6 |
will provide | 6 |
nursing students | 6 |
object detection | 6 |
better understanding | 6 |
user preferences | 6 |
based null | 6 |
learning scheme | 6 |
evolving network | 6 |
existing methods | 6 |
hate diffusion | 6 |
three main | 6 |
two people | 6 |
special needs | 6 |
ap locations | 6 |
product families | 6 |
near future | 6 |
factorization model | 6 |
language models | 6 |
family members | 6 |
macbook pro | 6 |
management experiences | 6 |
user id | 6 |
users use | 6 |
given user | 6 |
learning objective | 6 |
bef ore | 6 |
scooter companies | 6 |
prime minister | 6 |
mood model | 6 |
implemented using | 6 |
positive rate | 6 |
body movement | 6 |
temporary contact | 6 |
recent advances | 6 |
recommendation results | 6 |
context extraction | 6 |
graphical user | 6 |
findings show | 6 |
model performance | 6 |
health use | 6 |
system based | 6 |
interaction information | 6 |
label user | 6 |
user pseudonyms | 6 |
bluetooth contact | 6 |
ipad pro | 6 |
performance gain | 6 |
relationships among | 6 |
advertising interval | 6 |
computer algorithms | 6 |
item recommendation | 5 |
location infection | 5 |
binary classification | 5 |
intensive care | 5 |
results suggest | 5 |
political debate | 5 |
trending hashtags | 5 |
measurement model | 5 |
accuracy obtained | 5 |
pivoted normalization | 5 |
weak negative | 5 |
tracing mobile | 5 |
online therapy | 5 |
quantifying sars | 5 |
nearby users | 5 |
core game | 5 |
healthcare platforms | 5 |
play trajectories | 5 |
network logs | 5 |
platform provides | 5 |
ble beacons | 5 |
terms used | 5 |
many users | 5 |
contact information | 5 |
graph structure | 5 |
every mins | 5 |
large numbers | 5 |
participants said | 5 |
helps users | 5 |
daily national | 5 |
tracing protocols | 5 |
categorical data | 5 |
validated projection | 5 |
suggests epidemic | 5 |
standing configurations | 5 |
data sparsity | 5 |
two participants | 5 |
highly popular | 5 |
user timeline | 5 |
pseudo random | 5 |
detect depression | 5 |
apps addressed | 5 |
one participant | 5 |
mobile health | 5 |
label semantic | 5 |
problems related | 5 |
also take | 5 |
baseline case | 5 |
also developed | 5 |
chinese nursing | 5 |
may consider | 5 |
vice versa | 5 |
axis shows | 5 |
personal devices | 5 |
disease containment | 5 |
first year | 5 |
user query | 5 |
time intervals | 5 |
automated contact | 5 |
significant differences | 5 |
online posts | 5 |
official account | 5 |
author flairs | 5 |
reputable news | 5 |
invite code | 5 |
story types | 5 |
physics education | 5 |
give us | 5 |
health condition | 5 |
health system | 5 |
value eroding | 5 |
north america | 5 |
often used | 5 |
user relationships | 5 |
different parts | 5 |
edge weight | 5 |
forward layer | 5 |
hateful behavior | 5 |
high levels | 5 |
offline availability | 5 |
influence user | 5 |
hateful content | 5 |
network analysis | 5 |
may take | 5 |
two layers | 5 |
query likelihood | 5 |
non verified | 5 |
random tcn | 5 |
one day | 5 |
semantic representation | 5 |
bipartite networks | 5 |
meta attributes | 5 |
different things | 5 |
hate detection | 5 |
public locations | 5 |
angular distance | 5 |
kurdistan region | 5 |
public places | 5 |
countries around | 5 |
positive predictive | 5 |
xxx journal | 5 |
blockchain network | 5 |
second stage | 5 |
world datasets | 5 |
crucial role | 5 |
ehr vendors | 5 |
good performance | 5 |
clean data | 5 |
contact tracers | 5 |
search results | 5 |
product design | 5 |
single day | 5 |
panic attacks | 5 |
location report | 5 |
submission post | 5 |
contextual conditions | 5 |
filtered data | 5 |
results demonstrate | 5 |
discriminant validity | 5 |
current contact | 5 |
laptop computer | 5 |
learns user | 5 |
data gathering | 5 |
users within | 5 |
study found | 5 |
level contract | 5 |
improve existing | 5 |
phone models | 5 |
topic modelling | 5 |
reducing anxiety | 5 |
performing contact | 5 |
last two | 5 |
high school | 5 |
took place | 5 |
complex questions | 5 |
gone rogue | 5 |
previous subsection | 5 |
design choices | 5 |
loss model | 5 |
potentially infectious | 5 |
network representation | 5 |
based recommender | 5 |
behavioural patterns | 5 |
upload data | 5 |
ble devices | 5 |
strength indicator | 5 |
preserving signature | 5 |
first stage | 5 |
phone numbers | 5 |
privacy issue | 5 |
axiomatic analysis | 5 |
active days | 5 |
visual representation | 5 |
mobility patterns | 5 |
nonconnectable advertising | 5 |
user activity | 5 |
present study | 5 |
based collaborative | 5 |
mobile network | 5 |
also tracks | 5 |
voluntary nature | 5 |
health workers | 5 |
next generation | 5 |
interaction layer | 5 |
performs significantly | 5 |
regularization term | 5 |
i i | 5 |
learning rate | 5 |
behavioural vulnerabilities | 5 |
main text | 5 |
topic model | 5 |
violet red | 5 |
set relations | 5 |
security designs | 5 |
early detection | 5 |
bluetooth signals | 5 |
integrated mobile | 5 |
ap node | 5 |
also allows | 5 |
quantum physics | 5 |
users also | 5 |
semantic space | 5 |
blockchain databases | 5 |
relaxing music | 5 |
efficient graph | 5 |
research questions | 5 |
will help | 5 |
language interface | 5 |
digital solution | 5 |
backend service | 5 |
causality queries | 5 |
temporal information | 5 |
private information | 5 |
section ii | 5 |
without either | 5 |
complexity required | 5 |
use different | 5 |
compliance states | 5 |
provide feedback | 5 |
log files | 5 |
epidemic spread | 5 |
social features | 5 |
users broadcast | 5 |
apps gone | 5 |
tracing method | 5 |
helping people | 5 |
order contacts | 5 |
evaluation results | 5 |
potentially infected | 5 |
estimated distance | 5 |
embedding space | 5 |
decentralized proximity | 5 |
key role | 5 |
high degree | 5 |
security threats | 5 |
centred design | 5 |
maximum number | 5 |
infectious period | 5 |
item rating | 5 |
infected victim | 5 |
user check | 5 |
data obtained | 5 |
social anxiety | 5 |
accessed pallicovid | 5 |
exploration tradeoff | 5 |
topic embedding | 5 |
unique signature | 5 |
checks whether | 5 |
random forest | 5 |
hateful contents | 5 |
platform attributes | 5 |
identifiable natural | 5 |
user reliabilities | 5 |
fact checking | 5 |
event detection | 5 |
complex queries | 5 |
positive impact | 5 |
social collaborative | 5 |
structuration theory | 5 |
two stages | 5 |
information may | 5 |
usability evaluation | 5 |
value erosion | 5 |
network information | 5 |
main goal | 5 |
quality improvement | 5 |
encrypted packet | 5 |
oriented challenges | 5 |
original query | 5 |
affect recognition | 5 |
adaptive structuration | 5 |
infected persons | 5 |
operating costs | 5 |
healthcare services | 5 |
different areas | 5 |
positive effect | 5 |
world events | 5 |
one location | 5 |
different levels | 5 |
adoption rate | 5 |
daily basis | 5 |
statistical significance | 5 |
summative testing | 5 |
wifi logs | 5 |
following negative | 5 |
suicide risk | 5 |
learning algorithm | 5 |
compartmental models | 5 |
semantic features | 5 |
user receives | 5 |
relevant information | 5 |
central application | 5 |
general public | 5 |
health conditions | 5 |
mobile crowdsensing | 5 |
naive bayes | 5 |
recent work | 5 |
time difference | 5 |
providing personalized | 5 |
one person | 5 |
another device | 5 |
technical details | 5 |
much i | 5 |
centric contact | 5 |
users reported | 5 |
following section | 5 |
infection probability | 5 |
latent variables | 5 |
also include | 5 |
rssi value | 5 |
shared task | 5 |
using social | 5 |
asterics model | 5 |
vol xxx | 5 |
prior knowledge | 5 |
one another | 5 |
disease outbreaks | 5 |
postal code | 5 |
different models | 5 |
model trained | 5 |
first scenario | 5 |
last days | 5 |
interaction mechanism | 5 |
user groups | 5 |
european privacy | 5 |
support tool | 5 |
save time | 5 |
personal identity | 5 |
scientific levels | 5 |
based service | 5 |
users must | 5 |
two parts | 5 |
i think | 5 |
model learned | 5 |
jointly based | 5 |
seated vr | 5 |
findings suggest | 5 |
data management | 5 |
health data | 5 |
cosine similarity | 5 |
computational models | 5 |
computer science | 5 |
encourage users | 5 |
young adults | 5 |
data used | 5 |
important step | 5 |
initial negative | 5 |
government framework | 5 |
diversity distribution | 5 |
user types | 5 |
quantitative performance | 5 |
probability matrix | 5 |
nn regressor | 5 |
tracing data | 5 |
distancing rule | 5 |
analyze whether | 5 |
supervised learning | 5 |
data minimization | 5 |
next user | 5 |
last trip | 5 |
national level | 5 |
conversational agents | 5 |
relation types | 5 |
compromised accounts | 5 |
neural models | 5 |
contact graph | 5 |
fall victim | 5 |
users via | 5 |
transfer learning | 5 |
three types | 5 |
temporal dynamics | 5 |
allowing users | 5 |
epidemic spreading | 5 |
left wing | 5 |
tracetogether app | 5 |
level features | 5 |
keep track | 5 |
also known | 5 |
using machine | 5 |
randomized mac | 5 |
service provision | 5 |
input feature | 5 |
partners healthcare | 5 |
engineering procedure | 5 |
performance evaluation | 5 |
i needed | 5 |
aggregated number | 5 |
verified twitter | 5 |
tutorial level | 5 |
positive case | 5 |
prediction errors | 5 |
search string | 5 |
also consider | 5 |
blockchain platform | 5 |
section iii | 5 |
web users | 5 |
detection method | 5 |
acceptable fit | 5 |
general population | 5 |
early risk | 5 |
platform architecture | 5 |
proximity based | 5 |
technology value | 5 |
apps may | 5 |
last one | 5 |
health issue | 5 |
tracing application | 5 |
secondary contacts | 5 |
better privacy | 5 |
list boxes | 5 |
user must | 5 |
using google | 5 |
application frameworks | 5 |
user models | 5 |
model using | 5 |
web service | 5 |
eight security | 5 |
using bluetooth | 5 |
social graph | 5 |
may decide | 5 |
authors propose | 5 |
organic diffusion | 5 |
political situation | 5 |
based apps | 5 |
recommendation algorithm | 5 |
ambient environmental | 5 |
relative importance | 5 |
whether users | 5 |
user representations | 5 |
data available | 5 |
perceived usefulness | 5 |
app may | 5 |
room light | 5 |
retweeter prediction | 5 |
box plot | 5 |
prediction time | 5 |
biggest communities | 5 |
two nodes | 5 |
indirect contact | 5 |
filter based | 5 |
wireless sensor | 5 |
word representations | 5 |
invitation code | 5 |
immersive vr | 5 |
urban areas | 5 |
methods identified | 5 |
spoofed websites | 5 |
user location | 5 |
latent features | 5 |
using technology | 5 |
tracing purposes | 5 |
computational model | 5 |
crossed paths | 5 |
google partner | 5 |
eating disorders | 5 |
exposure time | 5 |
medical records | 5 |
maintaining personal | 5 |
mentioned earlier | 5 |
open source | 5 |
table ii | 5 |
recommendations based | 5 |
keys uploaded | 5 |
controlling covid | 5 |
without revealing | 5 |
contact numbers | 5 |
health applications | 5 |
network data | 5 |
given time | 5 |
personal vehicle | 5 |
account operators | 5 |
behavior paths | 5 |
user characteristics | 5 |
may still | 5 |
web pages | 5 |
qualitative research | 5 |
potential retweeters | 5 |
data contains | 5 |
transmission suggests | 5 |
wide fov | 5 |
sectional study | 5 |
two components | 5 |
open access | 5 |
trained model | 5 |
either directly | 5 |
virus spreading | 5 |
factors like | 5 |
user community | 5 |
proposed solution | 5 |
user requests | 5 |
may become | 5 |
android devices | 5 |
theory method | 5 |
past decade | 5 |
first place | 5 |
tracing tool | 5 |
day questionnaire | 5 |
automated disease | 5 |
conversational assistants | 5 |
better results | 5 |
reproduction number | 5 |
vr technologies | 5 |
homomorphic encryption | 5 |
two reasons | 5 |
signature database | 5 |
allowed us | 5 |
vector machine | 5 |
review embeddings | 5 |
system design | 5 |
distance measurements | 5 |
first day | 5 |
alternative approach | 5 |
makes use | 5 |
bad actors | 5 |
video games | 5 |
third layer | 5 |
distancing threshold | 5 |
target variable | 5 |
querying tool | 5 |
information overload | 5 |
link prediction | 5 |
conventional recommendation | 5 |
dark red | 5 |
dynamic setting | 5 |
benchmark model | 5 |
rounded support | 5 |
users might | 5 |
identify whether | 5 |
fundamental rights | 5 |
air travel | 4 |
body weight | 4 |
perform better | 4 |
game loop | 4 |
better platform | 4 |
effective means | 4 |
times higher | 4 |
two hours | 4 |
extrinsic motivation | 4 |
pseudo smartphone | 4 |
features including | 4 |
quarantine zone | 4 |
york city | 4 |
professional use | 4 |
disease exposure | 4 |
several approaches | 4 |
particular day | 4 |
systematic model | 4 |
packet broadcast | 4 |
unique patterns | 4 |
sensitive data | 4 |
fair information | 4 |
will increase | 4 |
app designer | 4 |
kitchen light | 4 |
daily life | 4 |
performs better | 4 |
two levels | 4 |
unassociated devices | 4 |
energy consumption | 4 |
iccs doi | 4 |
common features | 4 |
use two | 4 |
model achieves | 4 |
particularly important | 4 |
political communities | 4 |
data destruction | 4 |
assess whether | 4 |
vr technology | 4 |
cnn network | 4 |
advanced querying | 4 |
negative likelihood | 4 |
agree strongly | 4 |
hybrid optimization | 4 |
tweets posted | 4 |
crush saga | 4 |
health informatics | 4 |
behavior data | 4 |
better adapt | 4 |
size increases | 4 |
digital contacttracing | 4 |
data within | 4 |
predictive models | 4 |
accurate distance | 4 |
frequently used | 4 |
inversely correlated | 4 |
attack scenarios | 4 |
real people | 4 |
negative health | 4 |
scalar indicator | 4 |
graph structures | 4 |
false sense | 4 |
fully exploit | 4 |
one type | 4 |
clinical settings | 4 |
multiple times | 4 |
opposite direction | 4 |
become infected | 4 |
secure system | 4 |
google map | 4 |
proposed sct | 4 |
study aimed | 4 |
risky users | 4 |
infection dynamics | 4 |
user belongs | 4 |
hence tackling | 4 |
science games | 4 |
generated tcns | 4 |
increasingly important | 4 |
sets qualitative | 4 |
education beyond | 4 |
based neural | 4 |
convenience sample | 4 |
based features | 4 |
exploratory tasks | 4 |
educational content | 4 |
using probabilistic | 4 |
beijing institute | 4 |
real identities | 4 |
tree structure | 4 |
application generates | 4 |
top players | 4 |
smart lockdown | 4 |
users test | 4 |
index rssi | 4 |
training dataset | 4 |
study period | 4 |
system use | 4 |
ehr design | 4 |
empirical analysis | 4 |
may vary | 4 |
public server | 4 |
false contact | 4 |
privacy analysis | 4 |
less effective | 4 |
research method | 4 |
edge computing | 4 |
user behaviors | 4 |
af ter | 4 |
dietary behaviors | 4 |
million users | 4 |
also provides | 4 |
tree obtained | 4 |
environmental conditions | 4 |
conversational approach | 4 |
diverse contexts | 4 |
i got | 4 |
done using | 4 |
three components | 4 |
mobility data | 4 |
cognitive accessibility | 4 |
health impact | 4 |
disease outbreak | 4 |
ten posts | 4 |
implicit label | 4 |
health research | 4 |
ai interaction | 4 |
primary research | 4 |
statistical approach | 4 |
new features | 4 |
word categories | 4 |
driven contact | 4 |
reverse card | 4 |
significant relationships | 4 |
first learn | 4 |
sustained engagement | 4 |
loss status | 4 |
sensitive mobile | 4 |
evolving health | 4 |
contact tracking | 4 |
unverified accounts | 4 |
core loop | 4 |
local blockchain | 4 |
line model | 4 |
successfully used | 4 |
advisory board | 4 |
ranking task | 4 |
different topics | 4 |
several features | 4 |
health chatbots | 4 |
storage layer | 4 |
new product | 4 |
may cause | 4 |
study participants | 4 |
large dataset | 4 |
sensory log | 4 |
may increase | 4 |
articles published | 4 |
query term | 4 |
lombardy region | 4 |
truth data | 4 |
potential risks | 4 |
end time | 4 |
general location | 4 |
share program | 4 |
long term | 4 |
user performance | 4 |
center right | 4 |
systematic reviews | 4 |
virus infection | 4 |
amazon web | 4 |
systems based | 4 |
common friends | 4 |
private kit | 4 |
secret keys | 4 |
challenge features | 4 |
traditional contact | 4 |
shifting users | 4 |
different sources | 4 |
infectious individuals | 4 |
document frequency | 4 |
also confirmed | 4 |
comment ranking | 4 |
mainly composed | 4 |
clinical reference | 4 |
wifi data | 4 |
also shows | 4 |
data must | 4 |
hidden layer | 4 |
models like | 4 |
scan service | 4 |
training graph | 4 |
unit time | 4 |
also includes | 4 |
reasoning behind | 4 |
detection model | 4 |
structural model | 4 |
saved queries | 4 |
infection detection | 4 |
manual tracking | 4 |
statistical data | 4 |
user population | 4 |
major challenge | 4 |
northern italy | 4 |
recursive algorithm | 4 |
essential role | 4 |
individuals need | 4 |
next question | 4 |
service assigned | 4 |
examine whether | 4 |
time step | 4 |
mental well | 4 |
screenshot testing | 4 |
fast person | 4 |
week end | 4 |
may contain | 4 |
art recommendation | 4 |
investigate whether | 4 |
public transit | 4 |
older adults | 4 |
specific condition | 4 |
distance travelled | 4 |
case studies | 4 |
authors declare | 4 |
best results | 4 |
unique identifier | 4 |
auxiliary loss | 4 |
medical test | 4 |
healthcare context | 4 |
game based | 4 |
digital health | 4 |
dual queries | 4 |
time points | 4 |
mobile users | 4 |
final selection | 4 |
space model | 4 |
decentralized privacy | 4 |
also use | 4 |
likelihood ratio | 4 |
explicit feedback | 4 |
storage limitation | 4 |
first one | 4 |
may result | 4 |
verification key | 4 |
western europe | 4 |
malicious user | 4 |
users towards | 4 |
july th | 4 |
source codes | 4 |
boundary conditions | 4 |
generation algorithm | 4 |
quickly identify | 4 |
johns hopkins | 4 |
fast spreading | 4 |
collection study | 4 |
keeping track | 4 |
another scenario | 4 |
send push | 4 |
correlation coefficients | 4 |
label embedding | 4 |
also performed | 4 |
word vector | 4 |
last years | 4 |
exogenous signal | 4 |
research council | 4 |
user centred | 4 |
coding scheme | 4 |
weight constraints | 4 |
infected tcns | 4 |
positions information | 4 |
sensor networks | 4 |
projection procedure | 4 |
desired results | 4 |
retrieval doi | 4 |
potential health | 4 |
usage data | 4 |
major components | 4 |
filtering facepiece | 4 |
discussion forum | 4 |
assessing disease | 4 |
handheld controllers | 4 |
creative therapy | 4 |
medical professionals | 4 |
fake accounts | 4 |
healthcare service | 4 |
wifi access | 4 |
promising future | 4 |
network address | 4 |
will decrease | 4 |
user approval | 4 |
virus transmission | 4 |
different designs | 4 |
time required | 4 |
increasing attention | 4 |
city code | 4 |
important role | 4 |
product recommendation | 4 |
feature importance | 4 |
loss exponent | 4 |
processing techniques | 4 |
various questions | 4 |
exploratory analysis | 4 |
health systems | 4 |
galaxy zoo | 4 |
provides evidence | 4 |
may create | 4 |
italian prime | 4 |
identifiable information | 4 |
behavior categorization | 4 |
two groups | 4 |
unidad ciudadana | 4 |
proposed mobile | 4 |
classification methods | 4 |
two aspects | 4 |
dot product | 4 |
qualitative study | 4 |
simple linear | 4 |
pm location | 4 |
interactive visualization | 4 |
incidental contacts | 4 |
perform well | 4 |
current solutions | 4 |
analyzing user | 4 |
contract will | 4 |
person contact | 4 |
users following | 4 |
significance levels | 4 |
enterprise wifi | 4 |
th tutorial | 4 |
past days | 4 |
syndrome categories | 4 |
prediction problem | 4 |
safely lifted | 4 |
tracing across | 4 |
written documents | 4 |
recommendation social | 4 |
supervised classification | 4 |
inverse document | 4 |
dim denotes | 4 |
supply chains | 4 |
heat maps | 4 |
predefined uerc | 4 |
online communities | 4 |
twitter data | 4 |
takes advantage | 4 |
hateful tweet | 4 |
also pointed | 4 |
presidential election | 4 |
main contributions | 4 |
candy crush | 4 |
usability related | 4 |
rotational uerc | 4 |
note taking | 4 |
gleamviz computational | 4 |
population layer | 4 |
slate blue | 4 |
visited area | 4 |
recently proposed | 4 |
video game | 4 |
cascade prediction | 4 |
six types | 4 |
common method | 4 |
interface will | 4 |
word vectors | 4 |
impact assessment | 4 |
intentional sabotage | 4 |
diverse healthcare | 4 |
may likely | 4 |
system life | 4 |
participants stated | 4 |
batch size | 4 |
use mobile | 4 |
smart metric | 4 |
modeling approach | 4 |
without considering | 4 |
hypothesis tests | 4 |
enough data | 4 |
fake transitions | 4 |
two attributes | 4 |
register device | 4 |
many applications | 4 |
contradictory findings | 4 |
generation model | 4 |
graph algorithms | 4 |
two services | 4 |
denver area | 4 |
open street | 4 |
per week | 4 |
benefits may | 4 |
four layers | 4 |
psychological distress | 4 |
label classification | 4 |
network effect | 4 |
latent representations | 4 |
motivates us | 4 |
various features | 4 |
aware recommendation | 4 |
much like | 4 |
ca users | 4 |
disagree strongly | 4 |
heterogeneous information | 4 |
governance logic | 4 |
desktop computer | 4 |
contact networks | 4 |
discussed topics | 4 |
quantitative data | 4 |
unexpected number | 4 |
motorized scooter | 4 |
partial least | 4 |
person transmission | 4 |
bluetooth device | 4 |
centroid position | 4 |
choice alternatives | 4 |
scale information | 4 |
mobile services | 4 |
bluetooth scans | 4 |
future use | 4 |
appropriate action | 4 |
providing users | 4 |
persuasive arguments | 4 |
generation procedure | 4 |
sensitive locations | 4 |
error process | 4 |
passing rate | 4 |
covariance matrix | 4 |
th century | 4 |
user feedback | 4 |
empirical investigation | 4 |
like quantum | 4 |
extensive experiments | 4 |
social relationships | 4 |
will return | 4 |
care professional | 4 |
ble beacon | 4 |
healthcare preferences | 4 |
ehr system | 4 |
environmental features | 4 |
physical activities | 4 |
automated conversational | 4 |
second step | 4 |
current location | 4 |
initial seed | 4 |
joint learning | 4 |
will calculate | 4 |
predictive performance | 4 |
new cases | 4 |
dependent variables | 4 |
topic modeling | 4 |
recommendation problem | 4 |
breast cancer | 4 |
effective vaccine | 4 |
quantum optimization | 4 |
understanding user | 4 |
absolute error | 4 |
profile based | 4 |
metapopulation approach | 4 |
alert users | 4 |
contract state | 4 |
cultural values | 4 |
gcg user | 4 |
public authorities | 4 |
consent must | 4 |
scooter related | 4 |
open data | 4 |
help identify | 4 |
users appropriate | 4 |
unique device | 4 |
voice user | 4 |
online political | 4 |
signing key | 4 |
aspect distribution | 4 |
keep using | 4 |
physical distance | 4 |
filtering algorithm | 4 |
exploratory nature | 4 |
information embedded | 4 |
stress increased | 4 |
will never | 4 |
discussed previously | 4 |
authors also | 4 |
factor model | 4 |
using wifi | 4 |
social contextual | 4 |
obtained via | 4 |
large university | 4 |
patient care | 4 |
stress level | 4 |
news detection | 4 |
unauthorized entities | 4 |
several methods | 4 |
verified accounts | 4 |
widely adopted | 4 |
notifying contacts | 4 |
product reviews | 4 |
geographic area | 4 |
common words | 4 |
get infected | 4 |
user knows | 4 |
may require | 4 |
vector representation | 4 |
persuasive topics | 4 |
acceptance model | 4 |
apps like | 4 |
negatively affect | 4 |
two real | 4 |
automatic risk | 4 |
entire population | 4 |
prevent replay | 4 |
experienced users | 4 |
work will | 4 |
longitudinal study | 4 |
actual case | 4 |
political orientation | 4 |
accuracy score | 4 |
pandemic situation | 4 |
unique users | 4 |
req checkin | 4 |
users spent | 4 |
emergency room | 4 |
duration spent | 4 |
software engineering | 4 |
tv programs | 4 |
high concentration | 4 |
similarity function | 4 |
visual features | 4 |
overcome negative | 4 |
public opinion | 4 |
multiple challenges | 4 |
user mobile | 4 |
become one | 4 |
ill patients | 4 |
infected patients | 4 |
content platform | 4 |
system components | 4 |
trusted third | 4 |
coronavirus cases | 4 |
trustworthy comments | 4 |
app development | 4 |
computer systems | 4 |
carrier might | 4 |
significant improvement | 4 |
implementation overview | 4 |
dynamic settings | 4 |
online health | 4 |
comparative evaluation | 4 |
multiple types | 4 |
many cases | 4 |
may influence | 4 |
open innovation | 4 |
data shall | 4 |
statutory regulation | 4 |
word representation | 4 |
fuzzy sets | 4 |
semantic representations | 4 |
sample data | 4 |
electronic compass | 4 |
topological properties | 4 |
gesture recognition | 4 |
distributed across | 4 |
embedding models | 4 |
bipartite graph | 4 |
temporal graph | 4 |
extract features | 4 |
past two | 4 |
security monitoring | 4 |
gradient descent | 4 |
based recommendation | 4 |
significant margin | 4 |
tracing interviews | 4 |
embedding jointly | 4 |
tracing graph | 4 |
truth label | 4 |
current node | 4 |
analysis method | 4 |
relevant data | 4 |
ad hoc | 4 |
weighted average | 4 |
influential factors | 4 |
stress decreased | 4 |
reference code | 4 |
real life | 4 |
research gaps | 4 |
riding behavior | 4 |
open coding | 4 |
intensive task | 4 |
many apps | 4 |
root tweet | 4 |
contact patterns | 4 |
main italian | 4 |
every id | 4 |
directly access | 4 |
following contributions | 4 |
silent period | 4 |
mean absolute | 4 |
network value | 4 |
user feels | 4 |
invitation codes | 4 |
upper body | 4 |
internal services | 4 |
second version | 4 |
different algorithms | 4 |
online weight | 4 |
driven models | 4 |
voluntary use | 4 |
healthcare systems | 4 |
user posts | 4 |
search behavior | 4 |
knowledge graphs | 4 |
value co | 4 |
negative matrix | 4 |
strong integrity | 4 |
feature representation | 4 |
haptic devices | 4 |
health goals | 4 |
hate tweets | 4 |
disease spread | 4 |
openness strategy | 4 |
encryption algorithms | 4 |
software system | 4 |
high variation | 4 |
different values | 4 |
personal contact | 4 |
interactive systems | 4 |
novel social | 4 |
relatively high | 4 |
approach may | 4 |
technical requirements | 4 |
online news | 4 |
evolving graph | 4 |
brief overview | 4 |
qr codes | 4 |
model building | 4 |
focal platform | 4 |
bm model | 4 |
smart devices | 4 |
louvain method | 4 |
web page | 4 |
smartphone users | 4 |
effectively capture | 4 |
secure data | 4 |
selective broadcasting | 4 |
preferential attachment | 4 |
trace covid | 4 |
management method | 4 |
ios platform | 4 |
numerous studies | 4 |
visual cues | 4 |
seed labels | 4 |
national institute | 4 |
highest degree | 4 |
user improvement | 4 |
two methods | 4 |
social interactions | 4 |
xi xj | 4 |
valid queries | 4 |
information uploaded | 4 |
suspicious posts | 4 |
answer questions | 4 |
factory environment | 4 |
language model | 4 |