Social Sensors Early Detection of Contagious Outbreaks in Social Media

2018 ◽  
pp. 400-407 ◽  
Author(s):  
Arunkumar Bagavathi ◽  
Siddharth Krishnan
Keyword(s):  
Social Media ◽  
Early Detection ◽  
Social Sensors

scholarly journals Early detection of cyberbullying on social media networks

2021 ◽  
Vol 118 ◽  
pp. 219-229
Author(s):  
Manuel F. López-Vizcaíno ◽  
Francisco J. Nóvoa ◽  
Victor Carneiro ◽  
Fidel Cacheda
Keyword(s):  
Social Media ◽  
Early Detection ◽  
Social Media Networks

scholarly journals Neural User Response Generator: Fake News Detection with Collective User Intelligence

2018 ◽  
Author(s):  
Feng Qian ◽  
Chengyue Gong ◽  
Karishma Sharma ◽  
Yan Liu
Keyword(s):  
Neural Network ◽  
Social Media ◽  
Early Detection ◽  
Convolutional Neural Network ◽  
Semantic Information ◽  
Experimental Results ◽  
News Article ◽  
Fake News ◽  
Additional Information ◽  
Word Level

Fake news on social media is a major challenge and studies have shown that fake news can propagate exponentially quickly in early stages. Therefore, we focus on early detection of fake news, and consider that only news article text is available at the time of detection, since additional information such as user responses and propagation patterns can be obtained only after the news spreads. However, we find historical user responses to previous articles are available and can be treated as soft semantic labels, that enrich the binary label of an article, by providing insights into why the article must be labeled as fake. We propose a novel Two-Level Convolutional Neural Network with User Response Generator (TCNN-URG) where TCNN captures semantic information from article text by representing it at the sentence and word level, and URG learns a generative model of user response to article text from historical user responses which it can use to generate responses to new articles in order to assist fake news detection. We conduct experiments on one available dataset and a larger dataset collected by ourselves. Experimental results show that TCNN-URG outperforms the baselines based on prior approaches that detect fake news from article text alone.

scholarly journals Using WeChat, a Chinese Social Media App, for Early Detection of the COVID-19 Outbreak in December 2019: Retrospective Study

10.2196/19589 ◽  
2020 ◽  
Vol 8 (10) ◽  
pp. e19589
Author(s):  
Wenjun Wang ◽  
Yikai Wang ◽  
Xin Zhang ◽  
Xiaoli Jia ◽  
Yaping Li ◽  
...  
Keyword(s):  
Social Media ◽  
Early Detection ◽  
New Technologies ◽  
Disease Outbreaks ◽  
Early Warning Systems ◽  
Warning Systems ◽  
Early Detection Of Disease ◽  
New Approach ◽  
Novel Coronavirus ◽  
Chinese Social Media

Background A novel coronavirus, SARS-CoV-2, was identified in December 2019, when the first cases were reported in Wuhan, China. The once-localized outbreak has since been declared a pandemic. As of April 24, 2020, there have been 2.7 million confirmed cases and nearly 200,000 deaths. Early warning systems using new technologies should be established to prevent or mitigate such events in the future. Objective This study aimed to explore the possibility of detecting the SARS-CoV-2 outbreak in 2019 using social media. Methods WeChat Index is a data service that shows how frequently a specific keyword appears in posts, subscriptions, and search over the last 90 days on WeChat, the most popular Chinese social media app. We plotted daily WeChat Index results for keywords related to SARS-CoV-2 from November 17, 2019, to February 14, 2020. Results WeChat Index hits for “Feidian” (which means severe acute respiratory syndrome in Chinese) stayed at low levels until 16 days ahead of the local authority’s outbreak announcement on December 31, 2019, when the index increased significantly. The WeChat Index values persisted at relatively high levels from December 15 to 29, 2019, and rose rapidly on December 30, 2019, the day before the announcement. The WeChat Index hits also spiked for the keywords “SARS,” “coronavirus,” “novel coronavirus,” “shortness of breath,” “dyspnea,” and “diarrhea,” but these terms were not as meaningful for the early detection of the outbreak as the term “Feidian”. Conclusions By using retrospective infoveillance data from the WeChat Index, the SARS-CoV-2 outbreak in December 2019 could have been detected about two weeks before the outbreak announcement. WeChat may offer a new approach for the early detection of disease outbreaks.

scholarly journals Early Detection of Depression Indication from Social Media Analysis

2021 ◽  
Vol 40 ◽  
pp. 03029
Author(s):  
Maharukh Syed ◽  
Meera Narvekar
Keyword(s):  
Social Media ◽  
Early Detection ◽  
Media Analysis ◽  
Social Media Analysis ◽  
The Past ◽  
Course Of Action ◽  
Negative Thoughts ◽  
Depression Detection ◽  
Suicidal Thoughts And Behaviors ◽  
Detection Of Depression

Depression that stems through social media has been steadily growing since the past few years but with the current inclination towards social media reliance it is highly imperative to detect the early signs. Continuous observation of a user's social media interests and activities may highlight suspicious and negative thoughts. This observation can help in understanding their future course of action and also indicate any suicidal thoughts and behaviors. By using the machine learning models, early indications of depression detection can be addressed. This work studies different word embedding techniques for early detection of depression from social media posts. Further, this work develops a model using various NLP processes in order to address the issue of early detection. The recommendations can be useful as a Decision Support System for counselors, psychologist and also can be of good use by the cyber-crime cell department for criminal investigations.

scholarly journals A call for governments to pause Twitter censorship: a cross-sectional study using Twitter data as social-spatial sensors of COVID-19/SARS-CoV-2 research diffusion

2020 ◽  
Author(s):  
Vanash M. Patel ◽  
Robin Haunschild ◽  
Lutz Bornmann ◽  
George Garas
Keyword(s):  
Social Media ◽  
Crucial Role ◽  
Media Analysis ◽  
List Type ◽  
Cross Sectional ◽  
Twitter Data ◽  
Global Pandemic ◽  
Number Of Publications ◽  
Twitter Activity ◽  
Social Sensors

ABSTRACTObjectivesTo determine whether Twitter data can be used as social-spatial sensors to show how research on COVID-19/SARS-CoV-2 diffuses through the population to reach the people that are especially affected by the disease.DesignCross-sectional bibliometric analysis conducted between 23rd March and 14th April 2020.SettingThree sources of data were used in the analysis: (1) deaths per number of population for COVID-19/SARS-CoV-2 retrieved from Coronavirus Resource Center at John Hopkins University and Worldometer, (2) publications related to COVID-19/SARS-CoV-2 retrieved from WHO COVID-19 database of global publications, and (3) tweets of these publications retrieved from Altmetric.com and Twitter.Main Outcome(s) and Measure(s)To map Twitter activity against number of publications and deaths per number of population worldwide and in the USA states. To determine the relationship between number of tweets as dependent variable and deaths per number of population and number of publications as independent variables.ResultsDeaths per one hundred thousand population for countries ranged from 0 to 104, and deaths per one million population for USA states ranged from 2 to 513. Total number of publications used in the analysis was 1761, and total number of tweets used in the analysis was 751,068. Mapping of worldwide data illustrated that high Twitter activity was related to high numbers of COVID-19/SARS-CoV-2 deaths, with tweets inversely weighted with number of publications. Poisson regression models of worldwide data showed a positive correlation between the national deaths per number of population and tweets when holding the country’s number of publications constant (coefficient 0.0285, S.E. 0.0003, p<0.001). Conversely, this relationship was negatively correlated in USA states (coefficient –0.0013, S.E. 0.0001, p<0.001).ConclusionsThis study shows that Twitter can play a crucial role in the rapid research response during the COVID-19/SARS-CoV-2 global pandemic, especially to spread research with prompt public scrutiny. Governments are urged to pause censorship of social media platforms during these unprecedented times to support the scientific community’s fight against COVID-19/SARS-CoV-2.SUMMARY BOXWhat is already known on this topicTwitter is progressively being used by researchers to share information and knowledge transfer.Tweets can be used as ‘social sensors’, which is the concept of transforming a physical sensor in the real world through social media analysis.Previous studies have shown that social sensors can provide insight into major social and physical events.What this study addsUsing Twitter data used as social-spatial sensors, we demonstrated that Twitter activity was significantly positively correlated to the numbers of COVID-19/SARS-CoV-2 deaths, when holding the country’s number of publications constant.Twitter can play a crucial role in the rapid research response during the COVID-19/SARS-CoV-2 global pandemic.

scholarly journals Celebrity Cancer on Twitter: Mapping a Novel Opportunity for Cancer Prevention

2019 ◽  
Vol 26 (1) ◽  
pp. 107327481982582 ◽  
Author(s):  
Sarah C. Vos ◽  
Jeannette Sutton ◽  
C. Ben Gibson ◽  
Carter T. Butts
Keyword(s):  
Prostate Cancer ◽  
Social Media ◽  
Early Detection ◽  
Cancer Prevention ◽  
Cancer Site ◽  
Message Content ◽  
Chi Square ◽  
Media Messages ◽  
Before And After ◽  
Social Media Platforms

Social media platforms have the potential to facilitate the dissemination of cancer prevention and control messages following celebrity cancer diagnoses. However, cancer communicators have yet to systematically leverage these naturally occurring interventions on social media as these events are difficult to identify as they are unfolding and little research has analyzed their effect on social media conversations. In this study, we add to the research by analyzing how a celebrity cancer announcement influenced Twitter conversations in terms of the volume of social media messages and the type of content. Over a 9-day period, during which actor Ben Stiller announced that he had been treated for prostate cancer, we collected 1.2 million Twitter messages about cancer. We conducted automated content analyses to identify how often common cancer sites (prostate, breast, colon, or lung) were discussed. Then, we used manual content analysis on a sample of messages to identify cancer continuum content (awareness, prevention, early detection, diagnosis, treatment, survivorship, and end of life). Chi-square analyses were implemented to evaluate changes in cancer site and cancer continuum content before and after the announcement. We found that messages related to prostate cancer increased significantly more than expected for 2 days following Stiller’s announcement. However, the number of cancer messages that described other cancer locations either did not increase or did not increase by the same magnitude. In terms of message content, results showed larger than expected increases in diagnosis messages. These results suggest opportunities to shape social media conversations following celebrity cancer announcements and increase prevention and early detection messages.

scholarly journals Using WeChat, a Chinese Social Media App, for Early Detection of the COVID-19 Outbreak in December 2019: Retrospective Study (Preprint)

2020 ◽  
Author(s):  
Wenjun Wang ◽  
Yikai Wang ◽  
Xin Zhang ◽  
Xiaoli Jia ◽  
Yaping Li ◽  
...  
Keyword(s):  
Social Media ◽  
Early Detection ◽  
New Technologies ◽  
Disease Outbreaks ◽  
Early Warning Systems ◽  
Warning Systems ◽  
Early Detection Of Disease ◽  
New Approach ◽  
Novel Coronavirus ◽  
Chinese Social Media

BACKGROUND A novel coronavirus, SARS-CoV-2, was identified in December 2019, when the first cases were reported in Wuhan, China. The once-localized outbreak has since been declared a pandemic. As of April 24, 2020, there have been 2.7 million confirmed cases and nearly 200,000 deaths. Early warning systems using new technologies should be established to prevent or mitigate such events in the future. OBJECTIVE This study aimed to explore the possibility of detecting the SARS-CoV-2 outbreak in 2019 using social media. METHODS WeChat Index is a data service that shows how frequently a specific keyword appears in posts, subscriptions, and search over the last 90 days on WeChat, the most popular Chinese social media app. We plotted daily WeChat Index results for keywords related to SARS-CoV-2 from November 17, 2019, to February 14, 2020. RESULTS WeChat Index hits for “Feidian” (which means severe acute respiratory syndrome in Chinese) stayed at low levels until 16 days ahead of the local authority’s outbreak announcement on December 31, 2019, when the index increased significantly. The WeChat Index values persisted at relatively high levels from December 15 to 29, 2019, and rose rapidly on December 30, 2019, the day before the announcement. The WeChat Index hits also spiked for the keywords “SARS,” “coronavirus,” “novel coronavirus,” “shortness of breath,” “dyspnea,” and “diarrhea,” but these terms were not as meaningful for the early detection of the outbreak as the term “Feidian”. CONCLUSIONS By using retrospective infoveillance data from the WeChat Index, the SARS-CoV-2 outbreak in December 2019 could have been detected about two weeks before the outbreak announcement. WeChat may offer a new approach for the early detection of disease outbreaks.

#earlydetection: Leveraging social media to recruit individuals at increased-risk of pancreas cancer for an early detection study.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e14577-e14577
Author(s):  
Kelsey Klute ◽  
Christina Hoy ◽  
Luann Larson ◽  
Fang Yu ◽  
Michael A. Hollingsworth ◽  
...  
Keyword(s):  
Social Media ◽  
Early Detection ◽  
Pancreas Cancer ◽  
Familial Risk ◽  
News Story ◽  
Local News ◽  
Live Chat ◽  
Increased Risk ◽  
The Mean ◽  
Clinical Trial Information

e14577 Background: Social media (SM) could transform how individuals learn of clinical trials. In an ongoing, single-center cohort study to collect serial biospecimens and clinical data from high-risk individuals (HRIs) for pancreatic cancer (PC), we explored how HRIs learned of the study, surveyed relevant SM posts and compared those referred by SM vs. other means. Methods: Initial recruitment focused on HRIs with familial risk for PC. Referral method was self-reported. We identified relevant SM posts and compared those referred via SM vs. other means by ANOVA and t-test. Investigators did not create SM content but were featured in a relevant local news clip, institutional blog post and Project Purple podcast; study-related media was IRB-approved. Results: We enrolled 91 HRIs between Aug 2018 and Jan 2019. Over half self-referred; 55.0% of self-referrals came from SM. We identified 16 unique SM posts, all to Facebook. Authors were 2 administrators for local hereditary cancer organizations, Project Purple, UNMC and 2 study subjects (9,4, 3 and 2 posts). Content included links to a podcast, clinicaltrials.gov, local news story, blog post, live chat and anecdotes from subjects. Nine posts shared study contact information or clinicaltrials.gov link. The mean age of those referred via SM was younger than for other methods (mean 49.2 vs. 53.4y) but was not statistically significant (p = 0.19). SM was more likely to recruit HRIs with familial risk than other methods (100.0% vs. 76.3%; p < 0.01) Conclusions: SM effectively recruited HRIs with familial risk for PC; this group may be more likely to seek information online. Individuals may find studies via SM without investigator involvement. SM may be an effective tool to recruit HRIs to early detection research in PC and other conditions. Clinical trial information: NCT03568630. [Table: see text]

Sign in / Sign up

Export Citation Format

Share Document