The LiT.RL News Verification Browser is a research tool for news readers, journalists, editors or information professionals. The tool analyzes the language used in digital news web pages to determine if they are clickbait, satirical news, or falsified news, and visualizes the results by highlighting content in color-coded categories. Although the clickbait, satire, and falsification detectors perform to certain accuracy levels on test data, during real-world internet use accuracy may vary. The browser is not a replacement for digital literacy and is not always correct. All processing is completed on the local machine-results are not sent to or from a remote server. Results may be saved locally to a standard SQLite database for further analysis.

Background Undergraduate studies are challenging, and mental health issues can frequently occur in undergraduate students, straining campus resources that are already in demand for somatic problems. Cost-effective measures with ubiquitous devices, such as smartphones, offer the potential to deliver targeted interventions to monitor and affect lifestyle, which may result in improvements to student mental health. However, the avenues by which this can be done are not particularly well understood, especially in the Canadian context. Objective The aim of this study is to deploy an initial version of the Smart Healthy Campus app at Western University, Canada, and to analyze corresponding data for associations between psychosocial factors (measured by a questionnaire) and behaviors associated with lifestyle (measured by smartphone sensors). Methods This preliminary study was conducted as an observational app-based ecological momentary assessment. Undergraduate students were recruited over email, and sampling using a custom 7-item questionnaire occurred on a weekly basis. Results First, the 7-item Smart Healthy Campus questionnaire, derived from fully validated questionnaires—such as the Brief Resilience Scale; General Anxiety Disorder-7; and Depression, Anxiety, and Stress Scale–21—was shown to significantly correlate with the mental health domains of these validated questionnaires, illustrating that it is a viable tool for a momentary assessment of an overview of undergraduate mental health. Second, data collected through the app were analyzed. There were 312 weekly responses and 813 sensor samples from 139 participants from March 2019 to March 2020; data collection concluded when COVID-19 was declared a pandemic. Demographic information was not collected in this preliminary study because of technical limitations. Approximately 69.8% (97/139) of participants only completed one survey, possibly because of the absence of any incentive. Given the limited amount of data, analysis was not conducted with respect to time, so all data were analyzed as a single collection. On the basis of mean rank, students showing more positive mental health through higher questionnaire scores tended to spend more time completing questionnaires, showed more signs of physical activity based on pedometers, and had their devices running less and plugged in charging less when sampled. In addition, based on mean rank, students on campus tended to report more positive mental health through higher questionnaire scores compared with those who were sampled off campus. Some data from students found in or near residences were also briefly examined. Conclusions Given these limited data, participants tended to report a more positive overview of mental health when on campus and when showing signs of higher levels of physical activity. These early findings suggest that device sensors related to physical activity and location are useful for monitoring undergraduate students and designing interventions. However, much more sensor data are needed going forward, especially given the sweeping changes in undergraduate studies due to COVID-19.

Background The COVID-19 pandemic is a public health emergency that poses challenges to the mental health of approximately 1.4 million university students in Canada. Preliminary evidence has shown that the COVID-19 pandemic had a detrimental impact on undergraduate student mental health and well-being; however, existing data are predominantly limited to cross-sectional survey-based studies. Owing to the evolving nature of the pandemic, longer-term prospective surveillance efforts are needed to better anticipate risk and protective factors during a pandemic. Objective The overarching aim of this study is to use a mobile (primarily smartphone-based) surveillance system to identify risk and protective factors for undergraduate students’ mental health. Factors will be identified from weekly self-report data (eg, affect and living accommodation) and device sensor data (eg, physical activity and device usage) to prospectively predict self-reported mental health and service utilization. Methods Undergraduate students at Western University (London, Ontario, Canada), will be recruited via email to complete an internet-based baseline questionnaire with the option to participate in the study on a weekly basis, using the Student Pandemic Experience (SPE) mobile app for Android/iOS. The app collects sensor samples (eg, GPS coordinates and steps) and self-reported weekly mental health and wellness surveys. Student participants can opt in to link their mobile data with campus-based administrative data capturing health service utilization. Risk and protective factors that predict mental health outcomes are expected to be estimated from (1) cross-sectional associations among students’ characteristics (eg, demographics) and key psychosocial factors (eg, affect, stress, and social connection), and behaviors (eg, physical activity and device usage) and (2) longitudinal associations between psychosocial and behavioral factors and campus-based health service utilization. Results Data collection began November 9, 2020, and will be ongoing through to at least October 31, 2021. Retention from the baseline survey (N=427) to app sign-up was 74% (315/427), with 175-215 (55%-68%) app participants actively responding to weekly surveys. From November 9, 2020, to August 8, 2021, a total of 4851 responses to the app surveys and 25,985 sensor samples (consisting of up to 68 individual data items each; eg, GPS coordinates and steps) were collected from the 315 participants who signed up for the app. Conclusions The results of this real-world longitudinal cohort study of undergraduate students’ mental health based on questionnaires and mobile sensor metrics is expected to show psychosocial and behavioral patterns associated with both positive and negative mental health–related states during pandemic conditions at a relatively large, public, and residential Canadian university campus. The results can be used to support decision-makers and students during the ongoing COVID-19 pandemic and similar future events. For comparable settings, new interventions (digital or otherwise) might be designed using these findings as an evidence base. International Registered Report Identifier (IRRID) DERR1-10.2196/30504

No abstract

Les décisions fondées sur des données probantes reposent sur le principe selon lequel tous les renseignements sur un sujet sont recueillis et analysés. Les examens systématiques permettent l’évaluation rigoureuse de différentes études selon les principes de PICO (population, intervention, contrôle, résultats). Toutefois, le fait de réaliser une révision est un processus généralement lent qui impose un fardeau important sur les ressources. Le problème fondamental est qu’il est impossible d’élargir l’approche actuelle à la réalisation d’un examen systématique pour faire face aux difficultés découlant d’un corpus important de données non structurées. Pour cette raison, l’Agence de la santé publique du Canada envisage l’automatisation de différentes étapes de synthèse des données visant à accroître les gains d’efficacité. Dans le présent article, les auteurs présentent le résumé d’une version préliminaire d’un nouveau système d’apprentissage automatique fondé sur des avancements récents quant au traitement du langage naturel (TLN), comme BioBERT, où d’autres optimisations seront réalisées par l’entremise d’une nouvelle base de données de documents portant sur la vaccination. Le modèle de TLN optimisé obtenu et qui est au cœur de ce système peut déceler et extraire les champs relatifs aux principes de PICO des publications sur la vaccination avec une exactitude moyenne s’élevant à 88 % dans cinq classes de texte. La fonctionnalité est rendue possible par une interface Web directe.