Interactive Feedback Research Articles

Simple Recurrent Networks are Interactive.

There is disagreement among cognitive scientists as to whether a key computational framework - the Simple Recurrent Network (SRN; Elman, Machine Learning, 7(2), 195-225, 1991; Elman, Cognitive Science, 14(2), 179-211, 1990) - is a feedforward system. SRNs have been essential tools in advancing theories of learning, development, and processing in cognitive science for more than three decades. If SRNs were feedforward systems, there would be pervasive theoretical implications: Anything an SRN can do would therefore be explainable without interaction (feedback). However, despite claims that SRNs (and by extension recurrent neural networks more generally) are feedforward (Norris, 1993), this is not the case. Feedforward networks by definition are acyclic graphs - they contain no loops. SRNs contain loops - from hidden units back to hidden units with a time delay - and are therefore cyclic graphs. As we demonstrate, they are interactive in the sense normally implied for networks with feedback connections between layers: In an SRN, bottom-up inputs are inextricably mixed with previous model-internal computations. Inputs are transmitted to hidden units by multiplying them by input-to-hidden weights. However, hidden units simultaneously receive their own previous activations as input via hidden-to-hidden connections with a one-step time delay (typically via context units). These are added to the input-to-hidden values, and the sums are transformed by an activation function. Thus, bottom-up inputs are mixed with the products of potentially many preceding transformations of inputs and model-internal states. We discuss theoretical implications through a key example from psycholinguistics where the status of SRNs as feedforward or interactive has crucial ramifications.

Facilitating Students' Cognitive Engagement in Online Asynchronous Discussion Within a Remote English Foreign Language Learning Environment

This study examined the cognitive presence of students in an asynchronous online discussion in the Second Language Acquisition (SLA) course. The course combined synchronous meetings through Zoom sessions to support student participation in asynchronous discussions. The study involved a cohort of 36 participants from the two remote extended campuses of Pattimura University in Maluku. Through content analysis, two key aspects were examined: (1) student participation rates, and (2) the extent of students’ cognitive presence within the discussions. The content analysis findings revealed that although each student made a minimum of two contributions per topic during online asynchronous discussions, they exhibited a moderately high level of cognition, incorporating problem recognition, exploration, integration, and solution, not only in individual messages but also in the overall exchange of information within the discussion thread. These findings suggest that a combination of synchronous meetings through Zoom sessions, tailored prompts, feedback, and social interactions enhances students' active engagement and utilization of cognitive skills in online asynchronous discussions. Keywords: online asynchronous discussion, English foreign language learning, cognitive presence

The Role of Self-efficacy in Motivating Middle School Students' Learning

Self-efficacy is a pivotal psychological factor that shapes an individual's actions and motivations, significantly influencing the learning journey of middle school students. By examining the current state of self-efficacy and learning motivation among adolescents, this paper, drawing on practical teaching insights, explores their interplay. Evidence suggests that students with robust self-efficacy tend to exhibit stronger learning motivation and resilience, whereas those with lower self-efficacy are more likely to shy away from academic challenges. Hence, bolstering students' self-efficacy is critical for enhancing their learning drive. The paper proposes strategies such as achievement feedback, teacher support, and peer interaction to improve self-efficacy among middle school students.

Unveiling the Dynamics: A Mixed-Methods Exploration of the Interplay Between Foreign Language Enjoyment, Risk-Taking, and Oral Corrective Feedback Preferences in English as a Foreign Language Classrooms

This exploratory mixed-methods study examined the relationships between foreign language enjoyment (FLE), risk-taking (RT), and oral corrective feedback (OCF) preferences among learners of English as a foreign language (EFL). Employing a triangulated research design, the study integrated quantitative data from a structured online questionnaire with qualitative insights from semi-structured interviews and reflective journals. The sample consisted of 523 Saudi students enrolled in a one-year preparatory program at a major public university in Saudi Arabia. The findings indicated a significant positive correlation between FLE and RT, which suggested that greater enjoyment in language learning was associated with increased willingness to engage in linguistic RT. The results also showed that the learners had moderate preferences for all types of OCF, with no single predominant method. Additionally, the study revealed that the learners’ preferences for specific types of OCF significantly influenced both their enjoyment and RT behavior. Gender differences were observed not only in FLE and RT but also in the OCF preferences, with the female learners exhibiting a stronger inclination toward interactive and participatory feedback forms. Furthermore, the study underscored the significant impact of FLE on English language proficiency, thereby affirming that greater enjoyment correlated with higher exam scores. The study offers pedagogical recommendations derived from its findings aimed at improving both the experience and outcomes of language learning. Received: 30 May 2024 / Accepted: 31 August 2024 / Published: 05 November 2024

Cytosolic alkalinization in guard cells: an intriguing but interesting event during stomatal closure that merits further validation of its importance

Stomatal closure is essential to conserve water and prevent microbial entry into leaves. Alkalinization of guard cells is common during closure by factors such as abscisic acid, methyl jasmonate, and even darkness. Despite reports pointing at the role of cytosolic pH, there have been doubts about whether the guard cell pH change is a cause for stomatal closure or an associated event, as changes in membrane potential or ion flux can modulate the pH. However, the importance of cytosolic alkalinization is strongly supported by the ability of externally added weak acids to restrict stomatal closure. Using genetically encoded pH sensors has confirmed the rise in pH to precede the elevation of Ca2+ levels. Yet some reports claim that the rise in pH follows the increase in ROS or Ca2+. We propose a feedback interaction among the rise in pH or ROS or Ca2+ to explain the contrasting opinions on the positioning of pH rise. Stomatal closure and guard cell pH changes are compromised in mutants deficient in vacuolar H+-ATPase (V-ATPase), indicating the importance of V-ATPase in promoting stomatal closure. Thus, cytosolic pH change in guard cells can be related to the rise in ROS and Ca2+, leading to stomatal closure. We emphasize that cytosolic pH in stomatal guard cells deserves further attention and evaluation.

Climate‐driven shifts in plant–soil feedback of a perennial grass species

Abstract Plant–soil feedback (PSF) plays a key role in determining the composition of plant communities, and understanding the impact of the ongoing climate change on PSF is thus crucial for predicting the consequences of climate change for ecosystems. Here, we conducted a growth‐chamber experiment to examine possible climate‐driven shifts in PSF of a perennial grass, Festuca rubra, originating from two climatically distinct sites, by using all factorial combinations of soil biota origin, plant origin, and cultivation climate. Soil biota generated more negative PSF effects when grown under the climatic conditions of their origin. This observation suggests that soil biota, especially soil pathogens, are well adapted to their local climate, exhibiting greater efficiency in suppressing plant growth within their climatic conditions. All plants, regardless of their origin, exhibited less negative PSF (expressed as relative performance in live vs. sterilized soil) when grown under warmer climate than under colder climate, likely due to positive effects of increased activity of soil decomposers and enhanced nutrient cycling. Plants showed negative PSF when grown with local soil biota under home climate, and the negative PSF disappeared when plants were grown with foreign biota or in away climates. This suggests that any disruption of the established plant‐soil‐climate interactions may lead to the release of plants from negative PSF, potentially destabilizing plant communities. Synthesis. Our results highlight the adaptions of soil biota to their native climate as key drivers of plant–soil feedback interactions and suggest that climate change could significantly alter these interactions, potentially leading to new plant community dynamics. These findings emphasize the need for further investigations to unravel the mechanisms driving these responses and evaluate their consequences for ecosystem resilience in the face of climate change.

Retrieve water quality parameters of urban rivers from hyperspectral images through feature interaction based two-stage method fused with spectral unmixing and spatial relatedness

Monitoring water quality through efficient quantification of water quality parameters (WQPs) is of paramount importance to environmental management of urban rivers. Unmanned aerial vehicle (UAV) remote sensing techniques posed a great opportunity for visualizing spatial distributions of WQPs concentrations with higher flexibility and monitoring frequency compared to satellite remote sensing techniques, assisting to trace potential contamination sources and prevent water quality from degradation. However, current methods of water quality monitoring usually involved large masses of water samples as training data to keep calculation accuracy every time their study area changed, increasing financial cost and incurring time delay in monitoring and evaluating water quality. This study proposed a UAV-based two-stage multidirectional fusion with probabilistic matrix factorization (TSMF-PMF) method in unified framework, to effectively quantify WQPs including chemical oxygen demand (COD), biochemical oxygen demand (BOD), and turbidity from UAV hyperspectral images. TSMF-PMF established feature interaction and outlier feedback module, ensuring relatively high calculation stability with less training samples. The experimental results showed that TSMF-PMF achieved good performance on predicting concentrations of WQPs with coefficient of determination (R2) and mean absolute percentage error (MAPE) ranging from 0.82 to 0.91 and from 5.35 % to 10.23 %. This study established theoretical and technical foundation to optimize environmental management scheme of urban rivers and provided an application demonstration.

Co-Designing Dynamic Mixed Reality Drill Positioning Widgets: A Collaborative Approach with Dentists in a Realistic Setup.

Mixed Reality (MR) is proven in the literature to support precise spatial dental drill positioning by superimposing 3D widgets. Despite this, the related knowledge about widget's visual design and interactive user feedback is still limited. Therefore, this study is contributed to by co-designed MR drill tool positioning widgets with two expert dentists and three MR experts. The results of co-design are two static widgets (SWs): a simple entry point, a target axis, and two dynamic widgets (DWs), variants of dynamic error visualization with and without a target axis (DWTA and DWEP). We evaluated the co-designed widgets in a virtual reality simulation supported by a realistic setup with a tracked phantom patient, a virtual magnifying loupe, and a dentist's foot pedal. The user study involved 35 dentists with various backgrounds and years of experience. The findings demonstrated significant results; DWs outperform SWs in positional and rotational precision, especially with younger generations and subjects with gaming experiences. The user preference remains for DWs (19) instead of SWs (16). However, findings indicated that the precision positively correlates with the time trade-off. The post-experience questionnaire (NASA-TLX) showed that DWs increase mental and physical demand, effort, and frustration more than SWs. Comparisons between DWEP and DWTA show that the DW's complexity level influences time, physical and mental demands. The DWs are extensible to diverse medical and industrial scenarios that demand precision.

Finding Fulfillment: Leveraging Meaningful Feedback to Boost Worker Engagement

This article explores how organizations can design more meaningful feedback practices to boost employee engagement. Drawing on academic literature linking feedback and engagement, key drivers of the connection are identified, such as fulfilling psychological needs for competence and purpose. The brief then advocates shifting feedback focus from retrospective evaluations to forward-looking development centered on learning, growth opportunities, and stronger role alignment. Practical application examples across industries including healthcare, education, technology, and manufacturing demonstrate embedding feedback within organizational purpose and contextual priorities. Additional implementation strategies are offered, such as framing managers as coaches, emphasizing continual check-ins over annual reviews, rewarding continuous learning, and soliciting worker feedback. The conclusion asserts that by reframing routine feedback interactions to stimulate motivation, skills, and purpose-driven work, companies can transform this tool into a key lever for fostering enduring employee commitment, dedication, and fulfillment.

MyFeedback: an online writing feedback service with students as partners

MyFeedback is an online feedback service run by the academic tutoring team at the University of East London (UEL). The service provides a formative type of feedback on the academic writing of students based on drafts they upload to a digital inbox. The service is a differentiating support mechanism that complements the one-to-one guidance provided by the academic writing tutors. This is possible by training and supervising students (online feedback initiators) to provide reviews of assignment drafts. In this ALDCon24 workshop, we discussed how the development and operation of the service has thrived through a partnership between learning developers and students, and thus establishing a community of practice (Wenger, 1998) of shared learning and vision. We provided insights into the working model and the ways in which students become partners and occasionally co-creators. We highlighted the opportunities and benefits that are shared among all those involved and the roles they assume. Student users of the service engage in a self-regulated learning experience (Nicol and Macfarlane-Dick, 2006) enacted by their repeated exposure to peer feedback interactions that is underpinned by pedagogical principles, such as the zone of proximal development (Vygotsky, 1978) and differentiation, for example in Tomlinson (2001). Tutors and student partners collaborate to consolidate their feedback mechanisms by bringing together teaching expertise, fresh enthusiasm, first-hand student experiences, and a sense of belonging, inclusivity and collaboration. At the same time, tutors direct their capacity efficiently to students who can benefit more from a live dialogue based on their assessment at hand.

Upaya Meningkatkan Kesadaran Orang Tua tentang Hak dan Perlindungan Anak di Lembaga Pusat Pengembangan Anak (PPA) Linggang Mapan Kabupaten Kutai Barat

Child protection aims to guarantee the fulfillment of children's rights so that they can live, grow, develop and participate optimally in accordance with human dignity, as well as receive protection from violence and discrimination, for the sake of realizing Indonesian children who are of good quality, have noble character and prosperous. The aim of this activity is to increase parents' awareness about children's rights and protection at the Linggang Mapan Child Development Center (CDC), Linggang Bingung District, West Kutai Regency. To help partners improve parents' ability to understand and be aware of the increasing impact of violence against children, education is carried out regarding children's rights and protection. The reason for using the group counseling method or group approach is because the concept of extension is related to group counseling targets. This method is more profitable because it allows for feedback and group interaction which provides the opportunity to exchange experiences and influence the behavior and norms of its members. After carrying out activities for two weeks with two meetings with the parents of the Linggang Mapan Child Development Center (CDC) children, the author can conclude that during the process, parents can understand and comprehend what is meant by children's rights and protection by paying attention to each other's environment. a place for children to play and develop and explain to children what should be avoided while playing and socializing with other people, because violence or abuse can happen anywhere and be done by anyone, including family members.

Micro-Process of Open Innovation in Megaprojects Under Sense-Making Perspective

Compared with traditional closed innovation, open innovation brings more new ideas, technologies, and resources to megaprojects, which is becoming increasingly important in the face of growing complexity and sustainability. Drawing on the application of sense-making theory in organizational change, this study conducts an empirical case study to explore how open innovation is carried out in megaprojects, as well as how to explain the processes at the micro level. The Changchun Metropolitan Circle Ring Expressway phase II project was selected as the analytical case and grounded coding technology was adopted to analyze the realization process of open innovation. The results revealed that managers as organizers first completed their own sense making and then influenced others’ sense making via sense giving to unify understanding and complete innovation mode transformation. Moreover, managers need to adjust sense making for themselves and sense giving for others according to interactive feedback. This study illustrated that open innovation strategies need to enact some new relevant routines in order for a cognitive reorientation to take place. A multi-level and multi-dimensional micro-mechanism and process was proposed to guide open innovation behavior in megaprojects.

Arctic freshwater outflow suppressed Nordic Seas overturning and oceanic heat transport during the Last Interglacial

The Last Interglacial period (LIG) was characterized by a long-term Arctic atmospheric warming above the preindustrial level. The LIG thus provides a case study of Arctic feedback mechanisms of the cryosphere-ocean circulation-climate system under warm climatic conditions. Previous studies suggested a delay in the LIG peak warming in the North Atlantic compared to the Southern Ocean and evoked the possibility of southward extension of Arctic sea ice to the southern Norwegian Sea during the early LIG. Here we compile new and published proxy data on past changes in sea ice distribution, sea surface temperature and salinity, deep ocean convection, and meltwater sources based on well-dated records from the Norwegian Sea. Our data suggest that southward outflow of Arctic freshwater supressed Nordic Seas deep-water formation and northward oceanic heat transport during the early LIG. These findings showcase the complex feedback interactions between a warming climate, sea ice, ocean circulation and regional climate.

Applying Systems Thinking to Sustainable Beef Production Management: Modeling-Based Evidence for Enhancing Ecosystem Services

We used systems thinking (ST) to identify the critical components of beef cattle production through the lens of ecosystem services (ES), offering a holistic approach to address its adverse externalities. We identified eight critical feedback loops in beef production systems: (i) grazing and soil health, (ii) manure management and soil fertility, (iii) feed efficiency and meat production, (iv) water use and soil moisture, (v) cultural services and community engagement, (vi) energy use, (vii) carbon sequestration and climate regulation, and (viii) environmental impact. Our analysis reveals how these interconnected loops influence each other, demonstrating the complex nature of beef production systems. The dynamic hypothesis identified through the loops indicated that improved grazing and manure management practices enhance soil health, leading to better vegetation growth and cattle nutrition, which, in turn, have a positive impact on economic returns to producers and society, all of which encourage the continuation of interlinked beef and ecosystem stewardship practices. The management of beef production ES using ST might help cattle systems across the globe to contribute to 9 of the 17 different United Nations’ Sustainable Development Goals, including the “zero hunger” and “climate action” goals. We discussed the evaluation framework for agrifood systems developed by the economics of ecosystems and biodiversity to illustrate how ST in beef cattle systems could be harnessed to simultaneously achieve the intended environmental, economic, social, and health impacts of beef cattle systems. Our analysis of the literature for modeling and empirical case studies indicates that ST can reveal hidden feedback loops and interactions overlooked by traditional practices, leading to more sustainable beef cattle production outcomes. ST offers a robust framework for enhancing ES in beef cattle production by recognizing the interconnectedness of ecological and agricultural systems, enabling policymakers and managers to develop more effective and sustainable strategies that ensure the long-term health and resilience of humans and ES.

Home-based guidance training system with interactive visual feedback using kinect on stroke survivors with moderate to severe motor impairment

The home-based training approach benefits stroke survivors by providing them with an increased amount of training time and greater feasibility in terms of their training schedule, particularly for those with severe motor impairment. Computer-guided training systems provide visual feedback with correct movement patterns during home-based training. This study aimed to investigate the improvement in motor performance among stroke survivors with moderate to severe motor impairment after 800 min of training using a home-based guidance training system with interactive visual feedback. Twelve patients with moderate to severe stroke underwent home-based training, totaling 800 min (20–40 min per session, with a frequency of 3 sessions per week). The home-based guidance training system uses Kinect to reconstruct the 3D human body skeletal model and provides real-time motor feedback during training. The training exercises consisted of six core exercises and eleven optional exercises, including joint exercises, balance control, and coordination. Pre-training and post-training assessments were conducted using the Fugl-Meyer Assessment-Upper Limb (FMA-UE), Fugl-Meyer Assessment-Lower Limb (FMA-LE), Functional Ambulation Categories (FAC), Berg Balance Scale (BBS), Barthel Index (BI), Modified Ashworth Scale (MAS), as well as kinematic data of joint angles and center of mass (COM). The results indicated that motor training led to the attainment of the upper limit of functional range of motion (FROM) in hip abduction, shoulder flexion, and shoulder abduction. However, there was no improvement in the active range of motion (AROM) in the upper extremity (U/E) and lower extremity (L/E) joints, reaching the level of the older healthy population. Significant improvements were observed in both left/right and superior/inferior displacements, as well as body sway in the mediolateral axis of the COM, after 800 min of training. In conclusion, the home-based guidance system using Kinect aids in improving joint kinematics performance at the level of FROM and balance control, accompanied by increased mediolateral body sway of the COM for stroke survivors with moderate to severe stroke. Additionally, spasticity was reduced in both the upper and lower extremities after 800 min of home-based training.

Academic Opportunities of Gamification at University

Gamification is a powerful tool of modern education, but its successful implementation requires careful planning that takes into account the academic context and the individual needs of students. The authors tested a new narrative model of gamification, which integrated game elements and storylines to create a more interactive and motivating learning environment. The model involved stories and scenarios that linked various tasks and activities to immerse students in professionally relevant situations. The model was based on gamification principles, game mechanics, interactive tasks, social interaction, and adaptive feedback. The narrative contextualized learning, thus enhancing students’ engagement, motivation, and professional identity. The experiment (September-December 2023) gamified a course of Professional Ethics and involved first-year students of Clinical Psychology (n = 31), Voino-Yasenetsky Krasnoyarsk State Medical University. The narrative model of gamification fostered a more positive attitude towards the future profession, increased students’ engagement, and enhanced their interest in the academic process. Storylines, roles, personages, problematic situations, and unpredictability ensured students’ deep immersion in professional situations and contributed to the development of important ethical and professional qualities. Gamification has a great potential for improving the quality of higher education, making the learning routine more exciting and effective.

Multimodal Feedback to Improve Performance of Order Picker Truck Drivers Using a Virtual Reality Simulator

VR technology presents exciting prospects for immersive forklift training environments. VR facilitates hands-on learning without the risks of real world errors. Real-time multimodal feedback (such as visual and haptic) is an effective way to enhance learning outcomes and skill acquisition. However, the efficacy and usability of real-time multimodal feedback provided for VR-based forklift driving needs to be investigated, as its impact on training outcomes remains unexplored. We aim to understand how various feedback modalities influence task performance, perceived workload, and user preferences. Fifteen (3 female, 12 male) individuals participated and completed VR-based forklift driving tasks with four feedback conditions (No feedback, visual, haptic, combined visual and haptic). A significant main effect of Feedback was found for completion time. Mental demand and frustration were affected by the Sex and Feedback interaction. These differences in the perception of feedback modalities underscore the importance of considering diverse user demographics when designing feedback systems.

The Role of ChatGPT in Teaching Speaking Skills for English Majored Students: A Research Perspective

With the rapid advancement of artificial intelligence and its integration into education, the potential for enhancing English-speaking instruction has grown significantly. Traditional methods of teaching speaking to English-majored students often face challenges such as time constraints, limited access to native speakers, and varying levels of student proficiency. This study explores the auxiliary role of ChatGPT, a large language model, in assisting the development of speaking skills among English majors. By leveraging its natural language processing capabilities, the study aims to innovate teaching methods and provide learners with personalized, real-time practice opportunities. The article first outlines the technical features of ChatGPT and its applications in speaking instruction, including customized conversation practice, real-time interaction, and intelligent feedback. It also examines the current challenges of traditional speaking instruction, such as limited classroom time and the need for individualized feedback. Furthermore, the study discusses how ChatGPT can support teachers in providing scalable, interactive learning experiences. Finally, the article evaluates the effectiveness and feasibility of ChatGPT in enhancing speaking proficiency and highlights the potential future applications of AI tools in English language education. This research offers valuable insights into how AI can be integrated into language learning to address existing challenges and improve the overall teaching of speaking skills.

Benefits of Virtual Reality Training for Cardiopulmonary Resuscitation Skill Acquisition and Maintenance

Objectives To investigate the benefits of virtual reality (VR) first-aid training in acquiring cardiopulmonary resuscitation (CPR) skills. Methods A total of 100 non-medical professional volunteers from Nanchang were selected in March 2021 using the convenience sampling method. They were randomly divided into two groups: the VR training group (VR group) and the traditional simulation scenario training group (traditional group). The VR Group underwent immersive virtual reality CPR training with interactive feedback, while the Traditional Group received standard simulation-based CPR training using mannequins and instructor guidance. After training, relevant data were collected for comparative analysis. Results The study revealed that the VR group consistently outperforming the traditional group in theoretical knowledge test (cardiac arrest recognition, chest compressions, airway management, and artificial respiration) scores at 1, 3, 6, and 12 months post-training (p < 0.05). Similarly, the VR group showed superior performance in overall skills test scores and individual CPR quality metrics at all post-training assessments. The VR group scored higher in total skills, assessment, post-resuscitation assessment, chest compressions (at 1, 3, and 6 months), airway opening, and artificial respiration compared to the traditional group (p < 0.05). Despite these findings, both groups exhibited a gradual decrease in skills test scores over time. Conclusions Virtual reality training can significantly improve non-medical professional volunteers’ CPR knowledge and skill levels, helping them master and maintain these competencies. However, a decrease in CPR knowledge and skills among the participants over time was observed after VR training, suggesting the need for further retraining sessions.

Systems modelling and simulation to guide targeted investments to reduce youth suicide and mental health problems in a low–middle-income country

BackgroundDespite suicide’s public health significance and global mental health awareness, current suicide prevention efforts show limited impact, posing a challenge for low- and middle-income countries. This study aimed to develop a dynamic simulation model that could be used to examine the potential effectiveness of alternative interventions for reducing youth mental health problems and suicidal behavior in Bogotá, Colombia.MethodsA system dynamics model was designed using a participatory approach involving three workshops conducted in 2021 and 2022. These workshops engaged 78 stakeholders from various health and social sectors to map key mental health outcomes and influential factors affecting them. A model was subsequently developed, tested, and presented to the participants for interactive feedback, guided by a moderator. Simulation analyses were conducted to compare projected mental health outcomes for a range of intervention scenarios with projections for a reference scenario corresponding to business-as-usual.ResultsA total of 6670 suicide attempts and 347 suicides are projected among 7 − 17-year-olds from January 1, 2023, to early 2031 under the business-as-usual scenario. Mental health issues among 12 − 17-year-olds are projected to increase from 18.9% (2023) to 27.8% (2031), and substance use issues from 2.29 to 2.49% over the same period. School-based suicide prevention and gatekeeper training are the most effective strategies, reducing total numbers of suicide attempts and suicides by more than 20% (i.e., compared to business-as-usual). However, discontinuous funding significantly hinders these effective suicide prevention efforts.ConclusionsSystems modelling is an important tool for understanding where the best strategic financial and political investments lie for improving youth mental health in resource-constrained settings.