ABSTRACT
BACKGROUND: During the COVID-19 pandemic, media sources dedicated significant time and resources to improve knowledge of COVID-19 precautionary behaviors (eg, wearing a mask). Many older adults report using the television, radio, print newspapers, or web-based sources to get information on political news, yet little is known about whether consuming news in the early phase of the pandemic led to behavior change, particularly in older adults. OBJECTIVE: The goals of this study were to determine (1) whether dosage of news consumption on the COVID-19 pandemic was associated with COVID-19 precautionary behaviors; (2) whether being an ever-user of social media was associated with engagement in COVID-19 precautionary behaviors; and (3) among social media users, whether change in social media use during the early stages of the pandemic was associated with engagement in COVID-19 precautionary behaviors. METHODS: Data were obtained from a University of Florida-administered study conducted in May and June of 2020. Linear regression models were used to assess the association between traditional news and social media use on COVID-19 precautionary behaviors (eg, mask wearing, hand washing, and social distancing behaviors). Analyses were adjusted for demographic characteristics, including age, sex, marital status, and education level. RESULTS: In a sample of 1082 older adults (mean age 73, IQR 68-78 years; 615/1082, 56.8% female), reporting 0 and <1 hour per day of media consumption, relative to >3 hours per day, was associated with lower engagement in COVID-19 precautionary behaviors in models adjusted for demographic characteristics (ß=-2.00; P<.001 and ß=-.41; P=.01, respectively). In addition, increasing social media use (relative to unchanged use) was associated with engagement in more COVID-19 precautionary behaviors (ß=.70, P<.001). No associations were found between being an ever-user of social media and engaging in COVID-19 precautionary behaviors. CONCLUSIONS: The results demonstrated an association between higher media consumption and greater engagement in COVID-19 precautionary behaviors in older adults. These findings suggest that media can be effectively used as a public health tool for communication of prevention strategies and best practices during future health threats, even among populations who are historically less engaged in certain types of media.
ABSTRACT
Frequent spontaneous facial self-touches, predominantly during outbreaks, have the theoretical potential to be a mechanism of contracting and transmitting diseases. Despite the recent advent of vaccines, behavioral approaches remain an integral part of reducing the spread of COVID-19 and other respiratory illnesses. The aim of this study was to utilize the functionality and the spread of smartwatches to develop a smartwatch application to identify motion signatures that are mapped accurately to face touching. Participants (n = 10, five women, aged 20-83) performed 10 physical activities classified into face touching (FT) and non-face touching (NFT) categories in a standardized laboratory setting. We developed a smartwatch application on Samsung Galaxy Watch to collect raw accelerometer data from participants. Data features were extracted from consecutive non-overlapping windows varying from 2 to 16 s. We examined the performance of state-of-the-art machine learning methods on face-touching movement recognition (FT vs. NFT) and individual activity recognition (IAR): logistic regression, support vector machine, decision trees, and random forest. While all machine learning models were accurate in recognizing FT categories, logistic regression achieved the best performance across all metrics (accuracy: 0.93 ± 0.08, recall: 0.89 ± 0.16, precision: 0.93 ± 0.08, F1-score: 0.90 ± 0.11, AUC: 0.95 ± 0.07) at the window size of 5 s. IAR models resulted in lower performance, where the random forest classifier achieved the best performance across all metrics (accuracy: 0.70 ± 0.14, recall: 0.70 ± 0.14, precision: 0.70 ± 0.16, F1-score: 0.67 ± 0.15) at the window size of 9 s. In conclusion, wearable devices, powered by machine learning, are effective in detecting facial touches. This is highly significant during respiratory infection outbreaks as it has the potential to limit face touching as a transmission vector.