Fake or not? Automated detection of COVID-19 misinformation and disinformation in social networks and digital media

Precognition of Known And Unknown Biothreats: A Risk-Based Approach

Data mining and artificial intelligence algorithms can estimate the probability of future occurrences with defined precision. Yet, the prediction of infectious disease outbreaks remains a complex and difficult task. This is demonstrated by the limited accuracy and sensitivity of current models in predicting the emergence of previously unknown pathogens such as Zika, Chikungunya, and SARS-CoV-2, and the resurgence of Mpox, along with their impacts on global health, trade, and security. Comprehensive analysis of infectious disease risk profiles, vulnerabilities, and mitigation capacities, along with their spatiotemporal dynamics at the international level, is essential for preventing their transnational propagation. However, annual indexes about the impact of infectious diseases provide a low level of granularity to allow stakeholders to craft better mitigation strategies. A quantitative risk assessment by analytical platforms requires billions of near real-time data points from heterogeneous sources, integrating and analyzing univariable or multivariable data with different levels of complexity and latency that, in most cases, overwhelm human cognitive capabilities. Autonomous biosurveillance can open the possibility for near real-time, risk- and evidence-based policymaking and operational decision support.

Recruitment for Voluntary Video and Mobile HIV Testing on Social Media Platforms During the COVID-19 Pandemic: Cross-Sectional Study

BACKGROUND

The COVID-19 pandemic prompted social distancing policies and caused misinformation that hindered in-person HIV screening for high-risk groups. Social media platforms provide additional options for voluntary counseling and testing (VCT) for HIV, overcoming these limitations. However, there is a lack of data on HIV testing recruitment through social media platforms and its outcomes during the pandemic.

OBJECTIVE

This study aimed to measure the rate of face-to-face mobile and video VCT conducted after recruitment through social media platforms and friend referrals during the pandemic and compare the geographic distribution, risk feature targeting, testing outcome, and cost between the 2 models.

METHODS

Data were collected from March 3 to December 31, 2021, during the COVID-19 outbreak in Taiwan. Participants engaging in unprotected sex were recruited. After one-on-one message discussions through the platforms, the well-trained research assistants provided mobile or video VCT based on the participants' availability. Primary outcomes were completion rate, testing results, and CD4 count. Secondary outcomes included demographic and HIV risk-taking and protective features from a questionnaire. Selection bias was controlled by adjusting for the testing site (Taipei vs non-Taipei) using univariable multinomial logistic regression.

RESULTS

This study gathered 5142 responses on the social media platforms, recruiting 1187 participants. Video VCT had a completion rate of 31.8% (207/651), higher than mobile VCT's 21.8% (980/4491). Both rates were higher than those before the COVID-19 pandemic. Recruitment through friend referrals, instant messaging apps (eg, Line [LY Corporation]), and geosocial dating apps (eg, Hornet [Queer Networks Inc], Grindr [Grindr LLC], and Gsland [Tien-Hao Tsai]) resulted in higher acceptance and completion rates than social networks (eg, Facebook [Meta], X [formerly Twitter], and Instagram [Meta]). Mobile VCT had higher recruitment among urban residents and screening density, while video VCT reached a broader geographic area. The mobile group was more likely to have had more than 10 sexual partners (odds ratio [OR] 1.92, 95% CI 1.05-3.50; P=.03), history of sex work (OR 4.19, 95% CI 1.68-10.43; P=.002), and sexually transmitted diseases (OR 2.23, 95% CI 1.18-4.23; P=.01) within the past 3 months. The video group was more likely to meet sexual partners through social media. The HIV-positive rate in the mobile group was 0.7% (7/973) with an average CD4 count of 460/μL, while in the video group, it was 1% (2/205) with an average CD4 count of 347/μL, indicating a later diagnosis. Both positivity rates were higher than those before the COVID-19 pandemic, with no significant difference between the groups. The video group cost US $54.68 per participant, slightly higher than the US $50.36 for the mobile group.

CONCLUSIONS

Recruiting through social media platforms that facilitate one-on-one message discussions can effectively target high-risk groups for mobile and video VCT. This approach should be integrated into the current screening model to enhance HIV case finding.