Mark de Reuver

BACKGROUND Online youth forums offer valuable insights into how cultural identities, relationships, and social contexts shape young people’s mental health. Analyzing these data at scale requires a hybrid approach that combines computational methods with youth’s contextual experiences. Hybrid intelligence brings computational analysis together with researchers’ and youth’s perspectives, while intersectionality theory helps explain how identities and systems of power intersect in these contexts. OBJECTIVE This study aimed to identify youth mental health needs and challenges in a Dutch online peer support forum through an intersectionality-guided analysis that combined researchers, large language models (LLMs), and youth co-analysis, and to examine the practical contributions and limitations of this hybrid workflow. METHODS We collected and analyzed a corpus of 37,691 posts (including replies) from 16 sub-forums on De Kindertelefoon.nl, the largest and only publicly available Dutch youth forum. BERTopic produced 200 topic clusters; screening removed 36 low-signal clusters, leaving 164 for analysis. Researchers annotated 40 clusters across four dimensions: overarching topic, emotional stages, system touchpoints, and identity characteristics. Two non-overlapping sets of 20 clusters supported few-shot prompting and prompt testing with Microsoft Copilot (GPT-4o model). Two co-analysis workshops involved 22 youth aged 12–23 years from diverse backgrounds. Participants analyzed selected forum posts and compared their interpretations with LLM annotations. Researchers synthesized workshop recordings, facilitator notes, group artifacts, and LLM outputs to refine final annotations. RESULTS The screened 164 clusters with 22,314 posts were organized into 10 thematic groups, with 31 sub-themes. “Romantic relationships” was the most prevalent theme, accounting for 9,873 posts (44.2%), followed by “Identity, expression, and belonging” (3,626 posts; 16.2%) and “Feelings, coping, and care” (2,852 posts; 12.8%). Across themes, we identified intersectional themes of mental health challenges linked to youth’s cultural identities, the people around them, and the institutions and services. Youth contributions connected emotional experiences to specific actors and situations and revised overly formal and difficult language. Practical limitations of LLM annotation included row misalignment, failed large-batch processing, and relatively low alignment with the researcher’s annotation on emotional stages. Workshop observations supported the value of relationship building, use of accessible materials, and facilitated pair work. CONCLUSIONS Youth mental health needs in this forum extended across identity, relationships, and institutional contexts. Combining computational analysis with youth participation supported contextual interpretation and identified opportunities for more inclusive digital support. The workflow provides exploratory methodological evidence, and further evaluation is needed to assess its accuracy and transferability in other datasets and populations.

The European Digital Identity (EUDI) Wallet is widely framed as a regulatory and technical implementation project under eIDAS 2.0. Despite substantive political commitment and technical effort, the wallet ecosystem develops slowly, exhibits fragmentation, and raises concerns about public control and market dominance. This paper advances the argument that these difficulties are structural rather than incidental. With this insight, we developed an analytical framework to identify key sources of complexity. Using an intrinsic case study approach and drawing on Turner et al. synthesis of Complex Adaptive System (CAS) characteristics, we distinguish between substantive complexity (inherent in the governance object) and process complexity (arising from governance arrangements). The analysis indicates that the EUDI Wallet manifests the defining characteristics of a CAS, wherein systemic complexity emerges from the dynamic interactions among substantive, process-oriented, and hybrid mechanisms. The paper's main contribution is a theoretically grounded framework of CAS indicators for digital identity ecosystems, illustrated with empirical examples from the EUDI Wallet context. This framework provides the conceptual foundation for subsequent empirical research on governance tensions and adaptive strategies and offers a diagnostic tool for policymakers and practitioners.

An intersectional feminist lens offers a promising approach to increase power sharing in participatory projects, helping to transform tokenistic inclusion into meaningful collaboration. However, little work has been done to understand how to apply intersectionality in practice. Here, we investigate a participatory project that involves young people in developing design requirements for a preventive, AI-based mental health app. We collect meeting notes, reflection documents, relationship-building and decision-making accounts to understand where complexities arise. Then we conduct a focus group with the research team to discuss these complexities. A thematic analysis of the focus group uncovers 5 concepts. We find that power imbalances are inherent and concessions need to be made selectively. Giving power to relationship mediators (in our case, youth workers), focusing on the quantity as well as the quality of the content, adjusting to individual differences through exercise adaptations, and practicing flexibility and compromise. Finally, we call researchers to move beyond positionality statements to disclose how biases manifested or were mitigated. This paper contributes to design scholarship by providing solutions to complexities that appear when applying an intersectional feminist perspective to participatory projects with young people for meaningful power sharing.

1. Businesses that own transaction platforms continuously have to adjust the conditions for buyers and sellers to join the platform (Broekhuizen et al., 2019; Tilson et al., 2010; Wareham et al., 2...

Artificial intelligence (AI) based mental health apps, especially chatbots, are increasingly being developed for youth, but rarely with their input, especially that of marginalised groups. This results in the development of apps that have low engagement and pose safety concerns. We use participatory methods to explore the preferences and design requirements of youth who face social exclusion, come from migrant backgrounds, or have low socioeconomic positions. We recruited 64 youths from youth work programs around the Netherlands and carried out 6 workshops. The first three explored the use of apps and large language models (LLMs) for well-being, while the last explored youth’s preferences for an LLM chatbot. Data was analysed thematically. Our results showed participants were open to using apps, preferring multifunctional apps, and identified human connection, self-development, and education as potential functions. However, they were reluctant to use chatbots, perceiving them as fake and lacking emotional intelligence. Instead, participants saw chatbots as providers of information, favouring shorter outputs with simple language, although they disagreed on how human-like chatbots should sound. Finally, the need for personalisation was emphasised, showing a desire for control with extensive customisation settings and clear privacy policies. Further work must be done to explore other relevant stakeholders’ views.

Background: The transition from adolescence to young adulthood (age 10‐25 years) constitutes a sensitive developmental period marked by rapid biological, psychological, and social change, during which preventive health interventions can shape long-term outcomes. Mobile health tools offer accessible opportunities for tailored support for this population, but often adapt poorly to dynamic contexts, resulting in inconsistent engagement and effects. Just-in-time adaptive interventions (JITAIs), which tailor support in real time using ongoing data, are increasingly explored as precision health strategies. However, how these mechanisms are designed, implemented, and evaluated for adolescents and young adults (AYAs) has not been systematically reviewed. Objective: This review aimed to synthesize the evidence on JITAIs developed for AYAs, examine how their adaptive mechanisms have been designed to support specific health goals and changing AYA contexts, and assess methodological reporting quality to inform future precision health intervention development. Methods: We conducted a systematic review in accordance with PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) and SWiM (Synthesis Without Meta-Analysis) reporting guidelines. Twelve databases were searched for peer-reviewed studies published from 2013 to 2025. Eligible studies focused on participants aged 10 to 25 years and reported real-time adaptive mobile health interventions consistent with JITAI design principles. Two reviewers independently conducted screening, data extraction, and methodological quality appraisal using the Joanna Briggs Institute checklists. AYA coauthors contributed to all phases. Due to substantial heterogeneity in study populations, intervention content, adaptive mechanisms, comparators, and outcome measurements, findings were synthesized narratively, and no meta-analysis was conducted. Results: A total of 61 unique interventions were included. JITAIs for AYAs addressed substance use (n=24, 39.3%), mental health (n=23, 37.7%), and physical health or chronic conditions (n=14, 23%). JITAI tailoring mechanisms relied predominantly on self-reported behavioral data. Decision rules were typically symptom threshold–based, and decision points were commonly daily or event-triggered. Methodological concerns with reporting on intervention administration, participant selection, and outcome measurement reliability were pervasive across all studies, limiting the interpretability of observed effects and cross-study comparisons. Ethical considerations, including researcher positioning and reflexivity, alongside the depth of reporting around participatory AYA engagement in design and implementation, were also inconsistent. Conclusions: This review contributes a novel perspective to AYA digital health by moving beyond intervention outcomes to examine how core adaptive mechanisms are operationalized for AYAs across multiple health domains, while also integrating AYA perspectives into the interpretation of findings and recommendations. Unlike prior reviews focused primarily on adults or specific conditions, it identifies broader contextual, methodological, and ethical considerations relevant to AYA precision health. These findings highlight the need for more transparent, contextually responsive, and youth-centered adaptive interventions, alongside more rigorous designs for evaluating adaptive intervention components in daily life contexts.