From the top 248 YouTube videos on direct-to-consumer genetic testing, we collected 84,082 comments and feedback. Topic modeling revealed six prominent themes: (1) general genetic testing, (2) ancestry testing, (3) relationship testing, (4) health and trait testing, (5) ethical considerations, and (6) YouTube video reactions. Our sentiment analysis, further, indicates a powerful surge of positive emotions – anticipation, joy, surprise, and trust – alongside a neutral to positive perspective toward direct-to-consumer genetic testing-related video content.
This research showcases the technique for evaluating user stances on DTC genetic testing through an examination of comments posted on YouTube videos, focusing on prominent themes and expressed opinions. Findings from an analysis of social media user conversations suggest that users display considerable interest in direct-to-consumer genetic testing and related online content. However, given the continual evolution of this innovative market, service providers, content providers, or regulatory bodies may still need to adjust their services in response to the needs and wants of users.
Our investigation into YouTube video comments provides a means of identifying user attitudes toward direct-to-consumer genetic testing, through the exploration of the discussed themes and expressions of opinion. User conversations on social media platforms highlight a keen interest in direct-to-consumer genetic testing and related social media posts, according to our study. Despite this, the dynamic nature of this new market compels service providers, content creators, and regulatory bodies to proactively tailor their services to the evolving tastes and aspirations of their user base.

Social listening, the act of tracking and evaluating public discourse, is fundamental to addressing infodemic issues. Context-specific communication strategies, culturally acceptable and appropriate for diverse subpopulations, are informed by this approach. Social listening relies on the insight that the most pertinent information and communication styles for target audiences are best identified by the target audience itself.
In response to the COVID-19 pandemic, this study illustrates the creation of a structured social listening training program for crisis communication and community outreach, facilitated by a series of web-based workshops, and reports on the experiences of workshop participants implementing derived projects.
For individuals managing community outreach or communication among populations with differing linguistic backgrounds, a series of online training sessions were created by a multidisciplinary team of specialists. The participants held no prior training or experience in the methodologies of systematic data collection and surveillance. The training's purpose was to furnish participants with the necessary knowledge and skills to develop a social listening system that was pertinent to their unique demands and accessible resources. PFI-6 With the pandemic as a backdrop, the workshop was structured to prioritize the gathering of qualitative data. Participant feedback, assignments, and in-depth interviews with each team yielded insights into the training experiences of all participants.
Web-based workshops, numbering six, took place between May and September 2021. Social listening workshops adhered to a structured approach, incorporating web-based and offline source material, followed by rapid qualitative analysis and synthesis, yielding communication recommendations, customized messages, and the creation of new products. Workshops scheduled follow-up meetings to allow participants to share their accomplishments and obstacles. Four out of six (67%) of the participating teams had operational social listening systems in place by the end of the training. The teams modified the training's knowledge to better suit their distinct necessities. In consequence, the social systems built by the different teams displayed nuanced differences in their layouts, intended users, and underlying motivations. Behavioral toxicology The newly developed social listening systems meticulously followed the taught principles of systematic social listening to gather, analyze data, and leverage the ensuing insights for a more effective development of communication strategies.
This paper explores an infodemic management system and workflow, informed by qualitative inquiry and responsive to local priorities and resource availability. The implementation of these projects directly contributed to the creation of content for targeted risk communication, while addressing the needs of linguistically diverse populations. These systems' adaptability ensures their continued applicability during future outbreaks of epidemics and pandemics.
This paper details a locally-adapted infodemic management system and workflow, informed by qualitative research and prioritized to local needs and resources. These project implementations led to the creation of risk communication content, adapted to reach linguistically diverse groups. These systems can be molded to face future occurrences of epidemics and pandemics.

Electronic nicotine delivery systems, commonly recognized as e-cigarettes, elevate the risk of detrimental health consequences for inexperienced tobacco users, especially adolescents and young adults. This vulnerable population is particularly susceptible to e-cigarette marketing and advertising campaigns visible on social media. Public health initiatives designed to mitigate e-cigarette use can potentially benefit from a comprehension of the predictive factors associated with e-cigarette manufacturers' social media advertising and marketing tactics.
Using time series modeling, this study explores the factors that forecast the daily rate of commercial tweets promoting electronic cigarettes.
Data pertaining to the daily cadence of commercial tweets concerning e-cigarettes was scrutinized, encompassing the period from January 1, 2017, to December 31, 2020. systems genetics In order to model the data, we implemented an autoregressive integrated moving average (ARIMA) model and an unobserved components model (UCM). Four techniques were used to measure how well the model predicted outcomes. Days within the UCM are characterized by events associated with the U.S. Food and Drug Administration (FDA), significant non-FDA events (such as substantial news or academic announcements), the difference between weekdays and weekends, and the period when JUUL's corporate Twitter account was active (compared to periods of inactivity).
After applying the two statistical models to the data, the findings revealed that the UCM method yielded the most effective modeling solution for our dataset. In the UCM model, each of the four predictors displayed a statistically significant impact on the daily frequency of e-cigarette commercial tweets. Brand advertising and marketing for e-cigarettes on Twitter demonstrated an increase of over 150 advertisements, on average, during days involving FDA activity, when compared to days without such FDA events. In a similar vein, days that included significant non-FDA events had, on average, more than forty commercial tweets regarding e-cigarettes, in contrast to days without these events. Weekdays exhibited a greater volume of commercial e-cigarette tweets than weekends, according to our data, with this trend coinciding with JUUL's active Twitter engagement.
On the social media platform Twitter, e-cigarette companies promote their products. Days featuring significant FDA pronouncements were notably correlated with a surge in commercial tweets, potentially reshaping the discourse around FDA-disseminated information. E-cigarette digital marketing in the US requires further regulation.
The promotion of e-cigarettes by companies frequently involves Twitter as a marketing channel. FDA-related pronouncements appeared to correlate with a higher volume of commercial tweets, potentially influencing the discourse surrounding the agency's communications. E-cigarette product digital marketing in the United States necessitates further regulation.

The sheer volume of COVID-19 misinformation has consistently overwhelmed the capacity of fact-checkers to adequately counteract its harmful consequences. Effective deterrents to online misinformation are found in automated and web-based strategies. Machine learning approaches have proven effective in achieving robust performance for text classification, encompassing the evaluation of credibility for potentially unreliable news. Despite progress observed from initial, rapid interventions, the colossal amount of COVID-19 misinformation keeps overwhelming fact checkers. For this reason, an enhancement of automated and machine-learned approaches for managing infodemics is critically needed.
The study intended to optimize automated and machine-learning techniques for a more effective approach to managing the spread of information during an infodemic.
We assessed three training approaches for a machine learning model to identify the superior performance: (1) solely COVID-19 fact-checked data, (2) exclusively general fact-checked data, and (3) a combination of COVID-19 and general fact-checked data. Two COVID-19 misinformation datasets were formulated from a combination of fact-checked false content and programmatically acquired verified information. The first set, consisting of entries from July through August of 2020, contained roughly 7000 items. The second dataset, including entries from January 2020 through June 2022, numbered approximately 31000 entries. To label the inaugural dataset, we received 31,441 votes via a crowdsourcing platform.
The models' accuracy on the first external validation dataset reached 96.55%, and 94.56% on the second dataset. COVID-19-related material was crucial in the development of our high-performing model. We successfully created integrated models exceeding the accuracy of human assessments regarding misinformation. Our model's predictions, enhanced by human input, achieved a peak accuracy of 991% when tested on the first external validation dataset. In instances where the machine-learning model's predictions matched human voting results, the accuracy reached 98.59% on the primary validation data set.