This study aims to improve the accuracy, speed, and safety of suicide risk assessment among adolescents in the digital ecosystems of smart cities. To achieve this goal, an integrated system architecture was developed that combines natural language processing methods, transformer models, and privacy-preserving computation. The methodological part includes large-scale textual data analysis, distributed processing in Apache Spark and Hadoop environments, and the use of federated learning, which allows models to be trained without transferring sensitive source information. The evaluation was conducted on open mental health datasets and supplemented by a series of experiments simulating the system's operation in real time, as well as surveys of specialists – psychologists, educators, and IT experts. The analysis showed that transformer models, particularly BERT, significantly outperform classical algorithms, achieving an AUC-ROC of 0.96 and an F1 score of 0.92 with an average response time of 2.4 seconds. Survey participants noted the importance of transparency and data protection, and the proposed architecture received high marks for reducing the risk of information leaks and providing robust audit mechanisms. The novelty of the work lies in the combination of predictive analytics, federated learning, differential privacy, and blockchain traceability in a single application-oriented system. The results show that ethically sound and rapid suicide risk detection can be implemented in schools, medical institutions, and municipal services, providing both practical benefits and contributing to methodological advancements.

This article presents a formal demonstration of a hybrid big data processing architecture that combines the fault tolerance and storage robustness of Hadoop with the speed and in-memory processing capabilities of Apache Spark. The proposed architecture is evaluated through test execution and performance benchmarking in real-world data centers across three regions in Kazakhstan. The model integrates distributed resource management components, Directed Acyclic Graph (DAG)-based scheduling mechanism, and Resilient Distributed Datasets (RDDs) to enable dynamic workload distribution and rapid failure recovery. The results demonstrate that the hybrid system consistently outperforms standalone Spark and Hadoop architectures under variable workloads, illustrating enhancements in execution time, task recovery, and resource utilization. Quantitative performance metrics allow for a structured comparison of architectures and help optimize deployments for diverse scenarios. The proposed hybrid architecture shows significant improvements, reducing average execution time by up to 38% and increasing resource efficiency by 25% compared to standalone Spark and Hadoop systems.

The timely detection of psycho-emotional risks has become increasingly important due to the rapid growth of social media platforms. This study examines user-generated text as a potential source of early indicators of psychological vulnerability. The proposed NLP-based framework incorporates behavioral features to improve the interpretation of users’ psycho-emotional states. In addition to text classification, the study considers structured behavioral indicators to support psycho-emotional risk analysis. Particular attention is given to interpretability. SHAP-based techniques are applied to reveal the contribution of individual features and to provide a clearer explanation of model predictions. The evaluation was conducted on publicly available datasets containing textual data and aggregated behavioral/physiological indicators. No raw physiological streams, wearable sensor data, or biometric recordings were used. The two datasets were employed in complementary experimental settings and were not aligned at the individual-sample level; accordingly, the broader analytical perspective explored in this study should not be interpreted as a single end-to-end or fully aligned multimodal learning framework. The proposed BERT-based model with SHAP interpretability achieved an accuracy of 96.3%, an F1-score of 0.96, and a ROC–AUC score of 0.98, showing consistent improvement over baseline models, including Random Forests and Support Vector Machines.

This study presents a methodology for cross-ranking analysis to evaluate the consistency of universities’ positions across the QS World University Rankings, Times Higher Education (THE) World University Rankings, and Academic Ranking of World Universities (ARWU). Data for 2022–2025 were harmonized by university names, countries, years, and ranking positions, resulting in a unified dataset of 316 observations. Ranking agreement was assessed using the overlap of ranked lists, a Spearman distance–based similarity measure, and a normalized inverse-rank metric. QS rankings were treated as the response variable, while THE and ARWU positions served as predictors. Model performance was evaluated using leave-one-year-out cross-validation for a median baseline, the average of THE and ARWU ranks, linear regression, Random Forest, and XGBoost. Random Forest achieved the lowest mean absolute error (MAE = 24.80 ± 3.26 ranking positions), whereas linear regression best preserved relative ordering (Spearman’s ρ = 0.794 ± 0.062). Additional analyses of the TOP-50, TOP-100, and TOP-200 subsets showed that prediction accuracy decreases as ranking depth increases. The findings demonstrate that QS, THE, and ARWU provide complementary rather than interchangeable assessments of university performance. The proposed framework is intended for comparative cross-ranking analysis rather than forecasting future university rankings.

The early detection of psycho-emotional risks remains challenging despite its growing importance. Most existing models rely on a single data type, mainly questionnaires or text, and operate as “black boxes”, limiting practical use. Psycho-emotional states are multidimensional, reflected in textual, structured, and temporal digital signals. Ignoring this complexity may result in information loss and lower prediction accuracy. This paper presents an explainable text-based computational framework for psycho-emotional risk classification using public datasets. Record-level structured information was used only when it was available within the same original observation and was not created by matching records across datasets. The study did not integrate observations across datasets or perform cross-dataset fusion; these aspects are considered potential directions for future research. Implemented in Python using PyTorch, the model was evaluated on two open-text datasets. The BERT-based configuration achieved accuracy of 0.593 ± 0.009 and an ROC-AUC of 0.860 ± 0.006, while RoBERTa-base improved the performance to 0.666 ± 0.005 accuracy and a 0.896 ± 0.004 ROC-AUC under five-fold cross-validation. The results demonstrate that classification quality depends on encoder selection, preprocessing, dataset characteristics, duplicate handling, calibration, and the way that available record-level information is represented. Therefore, the findings should be interpreted as record-level computational classification results rather than the clinical validation of psycho-emotional risk assessment.

Global university rankings differ in methodology, yet their published positions are frequently compared across systems and monitored over time. This study examines two dimensions of ranking stability: cross-sectional consistency across ranking systems and temporal persistence within QS, while assessing whether machine-learning models improve predictive accuracy beyond a persistence baseline. The analysis included 57 universities from 20 countries and seven regions. Cross-ranking consistency among QS-2026, THE-2026, and ARWU 2025 was evaluated using pairwise rank correlations, bootstrap confidence intervals, and normalized percentile positions. Temporal predictability was assessed on a balanced panel of 40 universities with QS positions for 2021–2024 and 2026 using an expanding-window design, a persistence baseline, linear regression, Random Forest, XGBoost, and LightGBM. Pairwise correlations were positive within observed overlaps, but the ranking systems were not interchangeable. The persistence baseline achieved the lowest development MAE. On the final two-year holdout, Random Forest (MAE 5.073) did not significantly outperform persistence (MAE 5.150; p = 0.902), and the latest QS position was the only predictor with consistently positive importance. Historical persistence errors bracketed the 2024–2026 result, indicating that predictability was driven mainly by ranking persistence, whereas additional machine-learning complexity provided limited benefits in this sample.