Detection of suicide risk is a highly prioritized, yet complicated task. Five decades of research have produced predictions slightly better than chance (AUCs = 0.56–0.58). In this study, Artificial Neural Network (ANN) models were constructed to predict suicide risk from everyday language of social media users. The dataset included 83,292 postings authored by 1002 authenticated Facebook users, alongside valid psychosocial information about the users. Using Deep Contextualized Word Embeddings for text representation, two models were constructed: A Single Task Model (STM), to predict suicide risk from Facebook postings directly (Facebook texts → suicide) and a Multi-Task Model (MTM), which included hierarchical, multilayered sets of theory-driven risk factors (Facebook texts → personality traits → psychosocial risks → psychiatric disorders → suicide). Compared with the STM predictions (0.621 ≤ AUC ≤ 0.629), the MTM produced significantly improved prediction accuracy (0.697 ≤ AUC ≤ 0.746), with substantially larger effect sizes (0.729 ≤ d ≤ 0.936). Subsequent content analyses suggested that predictions did not rely on explicit suicide-related themes, but on a range of text features. The findings suggest that machine learning based analyses of everyday social media activity can improve suicide risk predictions and contribute to the development of practical detection tools.

Data collection from online platforms, such as Amazon’s Mechanical Turk (MTurk), has become popular in clinical research. However, there are also concerns about the representativeness and the quality of these data for clinical studies. The present work explores these issues in the specific case of major depression. Analyses of two large data sets gathered from MTurk (Sample 1: N = 2,692; Sample 2: N = 2,354) revealed two major findings: First, failing to screen for inattentive and fake respondents inflates the rates of major depression artificially and significantly (by 18.5%–27.5%). Second, after cleaning the data sets, depression in MTurk is still 1.6 to 3.6 times higher than general population estimates. Approximately half of this difference can be attributed to differences in the composition of MTurk samples and the general population (i.e., sociodemographics, health, and physical activity lifestyle). Several explanations for the other half are proposed, and practical data-quality tools are provided.

Importance: Contemporary studies raise concerns regarding the implications of excessive screen time on the development of autism spectrum disorder (ASD). However, the existing literature consists of mixed and unquantified findings.Objective: To conduct a systematic review and meta-analyis of the association between screen time and ASD.Data Sources: A search was conducted in the PubMed, PsycNET, and ProQuest Dissertation & Theses Global databases for studies published up to May 1, 2023.Study Selection: The search was conducted independently by 2 authors. Included studies comprised empirical, peer-reviewed articles or dissertations published in English with statistics from which relevant effect sizes could be calculated. Discrepancies were resolved by consensus.Data Extraction and Synthesis: This study followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) reporting guideline. Two authors independently coded all titles and abstracts, reviewed full-text articles against the inclusion and exclusion criteria, and resolved all discrepancies by consensus. Effect sizes were transformed into log odds ratios (ORs) and analyzed using a random-effects meta-analysis and mixed-effects meta-regression. Study quality was assessed using the Grading of Recommendations, Assessment, Development, and Evaluations (GRADE) approach. Publication bias was tested via the Eggerztest for funnel plot asymmetry. Data analysis was performed in June 2023.Main Outcomes and Measures: The 2 main variables of interest in this study were screen time and ASD. Screen time was defined as hours of screen use per day or per week, and ASD was defined as an ASD clinical diagnosis (yes or no) or ASD symptoms. The meta-regression considered screen type (ie, general use of screens, television, video games, computers, smartphones, and social media), age group (children vs adults or heterogenous age groups), and type of ASD measure (clinical diagnosis vs ASD symptoms).Results: Of the 4682 records identified, 46 studies with a total of 562 131 participants met the inclusion criteria. The studies were observational (5 were longitudinal and 41 were cross-sectional) and included 66 relevant effect sizes. The meta-analysis resulted in a positive summary effect size (log OR, 0.54 [95% CI, 0.34 to 0.74]). A trim-and-fill correction for a significant publication bias (Eggerz = 2.15;P = .03) resulted in a substantially decreased and nonsignificant effect size (log OR, 0.22 [95% CI, −0.004 to 0.44]). The meta-regression results suggested that the positive summary effect size was only significant in studies targeting general screen use (β [SE] = 0.73 [0.34];t₅₈ = 2.10;P = .03). This effect size was most dominant in studies of children (log OR, 0.98 [95% CI, 0.66 to 1.29]). Interestingly, a negative summary effect size was observed in studies investigating associations between social media and ASD (log OR, −1.24 [95% CI, −1.51 to −0.96]).Conclusions and Relevance: The findings of this systematic review and meta-analysis suggest that the proclaimed association between screen use and ASD is not sufficiently supported in the existing literature. Although excessive screen use may pose developmental risks, the mixed findings, the small effect sizes (especially when considering the observed publication bias), and the correlational nature of the available research require further scientific investigation. These findings also do not rule out the complementary hypothesis that children with ASD may prioritize screen activities to avoid social challenges.

In this commentary, we raise seven methodological concerns regarding Twenge, Joiner, Rogers, and Martin (2018), among which are inaccurate research measurements, negligible correlations between the main variables, insufficient and inadequate statistical analyses, and problematic interpretation of the results. In fact, the negligible associations between screen activities and depression, their decrease when demographic variables are controlled, and their fading away to nil among boys challenge the article’s title and conclusions, according to which increases in depressive symptoms are attributed to increases in new-media screen use. This conclusion cannot be deduced from the reported results and could be misleading to the general public.