Purpose To detect academic misconduct in students' assessment score trajectories under severe class imbalance. The paper compares tabular learners, gradient-boosting models, and sequence-aware deep networks, and proposes a precision–recall–centric evaluation and deployment protocol (calibration, threshold selection and Recall@Top-k%) tailored to rare-event screening in educational settings. Design/methodology/approach A cohort of 1,527 students (2021–2024) is modeled using ten algorithms: LR, DT, RF, SVM, MLP, XGBoost, CatBoost, LightGBM, GRU-RNN and 1D-CNN. Features encode sequential score dynamics and metadata. Models are tuned via cross-validation; probabilities are calibrated (Platt/Isotonic); operating thresholds are chosen on validation to maximize minority-class F1 or a cost-sensitive utility. Performance is assessed on a hold-out test set with PR-AUC (headline), F1(+), Recall@Top-k%, ROC-AUC, calibration curves, Brier, and bootstrap CIs. Findings Sequence-aware models dominate: GRU-RNN and 1D-CNN achieve ROC-AUC ˜0.97–0.98 and the highest F1(+) and Recall@Top-5%. Tabular/boosting baselines show ˜0.90 accuracy yet miss most positives at the default 0.5 threshold, highlighting the necessity of calibration and threshold optimization. With PR-centric selection and tuned operating points, deep temporal models yield strong screening utility for limited human review budgets. Research limitations/implications Labels reflect suspected–not adjudicated–cheating, introducing noise. The single-institution cohort may limit external validity; temporal shift across semesters can degrade performance. Future work should include multi-site evaluation, collusion/graph modeling, semi-/weak-supervision for noisy labels and governance topics (fairness audits, drift monitoring and uncertainty reporting). Practical implications This study highlights how educational institutions can leverage machine learning for early detection of academic dishonesty based on historical performance data. CNN and RNN models are promising tools for identifying anomalous learning patterns. However, practical deployment requires preprocessing techniques to manage class imbalance and threshold optimization to reduce false negatives. The findings provide a roadmap for building automated cheating detection systems in both online and traditional assessment environments. Social implications By improving the ability to detect cheating, this research contributes to fairer academic environments, upholding educational integrity and credibility of credentials. However, ethical considerations must be taken into account to avoid false accusations and ensure student rights. Human-in-the-loop systems are crucial for verifying algorithmic predictions before disciplinary action, thereby fostering transparency and accountability in automated decision-making processes. Originality/value The study unifies a minority-focused evaluation protocol with a comprehensive comparison of tabular, boosting, and sequence-aware models for cheating detection from score trajectories. It demonstrates the decisive value of temporal representation learning and provides a reproducible pipeline and operational metrics that align model performance with real investigative workflows.

Purpose This study aimed to analyze the impact of the Cattleya Llanera artificial intelligence model on strengthening empathy and recognition. The objective was to determine the extent to which interaction with the tool helped participants to reflect on the social context, historical memory and human rights. Furthermore, the study explored its accessibility and effectiveness across various age and gender groups to assess its potential as an innovative educational resource in reconciliation and peacebuilding processes. Design/methodology/approach This study employed a quantitative approach, utilizing a Likert-scale questionnaire, to assess the impact of the Cattleya Llanera artificial intelligence model on the development of empathy and recognition. The instrument was administered to 66 participants and descriptive, correlational and comparative analyses were conducted, stratified by gender, age and prior experience with artificial intelligence (AI). A Cronbach’s alpha of 0.839 validated the instrument’s reliability, ensuring internal consistency. Participant proficiency classification levels enabled the identification of response patterns and evaluation of the tool’s effectiveness in developing socioemotional skills. Findings The results showed that the majority of participants positively evaluated their interaction with Cattleya Llanera, with skill scores concentrated in the upper-intermediate and advanced levels. No statistically significant gender differences were found or were there any between those with and without prior experience with AI. A high correlation was observed between the understanding of the social context and sensitivity to human rights, suggesting that the tool promotes critical thinking. However, a weaker relationship was identified between reflection and the generation of constructive solutions. Research limitations/implications The study’s limited sample size restricts the generalizability of the findings to broader populations. Furthermore, the evaluation was conducted at a single point in time, with no long-term follow-up. These limitations present opportunities for future research to expand the sample, incorporate longitudinal methodologies and investigate how AI-promoted reflection can translate into tangible actions in the social sphere. It is also necessary to examine its applicability in various sectors, including education, transitional justice and communities involved in reconciliation processes. Practical implications The findings suggest that Cattleya Llanera can be integrated into educational and community programs to foster empathy and recognition. Its accessibility and ease of use make it viable for diverse audiences, regardless of prior experience with AI. Furthermore, its application in academic settings could strengthen university social responsibility, promoting the development of citizens more committed to social justice. However, complementing the tool with participatory methodologies would enable the reflection facilitated by the tool to connect with practical experiences in everyday life. Social implications The study demonstrates that artificial intelligence can be leveraged as a resource for peacebuilding and promoting mutual understanding and recognition. By generating spaces for dialogue and critical reflection, Cattleya Llanera helps raise awareness about social issues and strengthen the social fabric. Its potential impact on peace education and historical memory makes it a valuable tool for post-conflict contexts, where reconciliation and understanding of others are fundamental to developing more equitable and inclusive societies. Originality/value This study offers an innovative perspective on the application of artificial intelligence in developing socioemotional competencies. Unlike other technological applications, Cattleya Llanera not only provides information but also generates narrative interactions that foster empathy and recognition. It is unique because its interdisciplinary approach combines pedagogy, artificial intelligence and peace studies. Furthermore, its results suggest new avenues of research on the role of AI in social transformation and dialogue-based learning.

PurposeThis paper uses computer vision to develop a method for collecting football players’ positions during a match. It also compares the differences between various solutions of the existing object detection models to determine discerning differences. Then, an illustration of the obtained information is created as a heatmap.Design/methodology/approachThe proposed method utilizes a dataset of side-view football broadcast footage to detect the players’ positions on the football at any given moment of the football match. Using YOLO object detection, the players of each team are identified and recorded to create valuable illustrations that the coaches can further analyze, training staff, etc. Using three different implementations of YOLO (YOLOv5m6, YOLOv5l-tph and YOLOv5l-tph-plus) the results will be compared to find out the best implementation for this specific task.FindingsAfter each YOLO implementation was trained using the same dataset, the results showed that YOLOv5l-tph performed best, achieving a precision of 0.9868. Meanwhile, YOLOv5l-tph-plus placed second, with a precision of 0.9786. Finally, YOLOv5m6 performed worst, with a precision of 0.8214.Originality/valueIn sports, various analytical information can be extracted from games, whether from statistical records or recorded footage. For “sports analytics,” the goal is to provide valuable insights that are otherwise not obtainable through traditional means, such as merely rewatching past footage. In both the past and the present, there have been multiple attempts at using statistical records to predict or quantify various aspects of the games.

Purpose Despite the fact that chatbots have been largely adopted for the last few years, a comprehensive literature review research focusing on the intention of individuals to adopt chatbots is rather scarce. In this respect, the present paper attempts a literature review investigation of empirical studies focused on the specific issue in nine scientific databases during 2017-2021. Specifically, it aims to classify extant empirical studies which focus on the context of individuals' adoption intention toward chatbots. Design/methodology/approach The research is based on PRISMA methodology, which revealed a total of 39 empirical studies examining users' intention to adopt and utilize chatbots. Findings After a thorough investigation, distinct categorization criteria emerged, such as research field, applied theoretical models, research types, methods and statistical measures, factors affecting intention to adopt and further use chatbots, the countries/continents where these surveys took place as well as relevant research citations and year of publication. In addition, the paper highlights research gaps in the examined issue and proposes future research directions in such a promising information technology solution. Originality/value As far as the authors are concerned, there has not been any other comprehensive literature review research to focus on examining previous empirical studies of users' intentions to adopt and use chatbots on the aforementioned period. According to the authors' knowledge, the present paper is the first attempt in the field which demonstrates broad literature review data of relevant empirical studies.

Purpose This paper purposed a multi-facet sentiment analysis system. Design/methodology/approach Hence, This paper uses multidomain resources to build a sentiment analysis system. The manual lexicon based features that are extracted from the resources are fed into a machine learning classifier to compare their performance afterward. The manual lexicon is replaced with a custom BOW to deal with its time consuming construction. To help the system run faster and make the model interpretable, this will be performed by employing different existing and custom approaches such as term occurrence, information gain, principal component analysis, semantic clustering, and POS tagging filters. Findings The proposed system featured by lexicon extraction automation and characteristics size optimization proved its efficiency when applied to multidomain and benchmark datasets by reaching 93.59% accuracy which makes it competitive to the state-of-the-art systems. Originality/value The construction of a custom BOW. Optimizing features based on existing and custom feature selection and clustering approaches.

Purpose Automatic anatomical therapeutic chemical (ATC) classification is progressing at a rapid pace because of its potential in drug development. Predicting an unknown compound's therapeutic and chemical characteristics in terms of how it affects multiple organs and physiological systems makes automatic ATC classification a vital yet challenging multilabel problem. The aim of this paper is to experimentally derive an ensemble of different feature descriptors and classifiers for ATC classification that outperforms the state-of-the-art. Design/methodology/approach The proposed method is an ensemble generated by the fusion of neural networks (i.e. a tabular model and long short-term memory networks (LSTM)) and multilabel classifiers based on multiple linear regression (hMuLab). All classifiers are trained on three sets of descriptors. Features extracted from the trained LSTMs are also fed into hMuLab. Evaluations of ensembles are compared on a benchmark data set of 3883 ATC-coded pharmaceuticals taken from KEGG, a publicly available drug databank. Findings Experiments demonstrate the power of the authors’ best ensemble, EnsATC, which is shown to outperform the best methods reported in the literature, including the state-of-the-art developed by the fast.ai research group. The MATLAB source code of the authors’ system is freely available to the public at https://github.com/LorisNanni/Neural-networks-for-anatomical-therapeutic-chemical-ATC-classification. Originality/value This study demonstrates the power of extracting LSTM features and combining them with ATC descriptors in ensembles for ATC classification.

Purpose Diabetic retinopathy (DR) is one of the dangerous complications of diabetes. Its grade level must be tracked to manage its progress and to start the appropriate decision for treatment in time. Effective automated methods for the detection of DR and the classification of its severity stage are necessary to reduce the burden on ophthalmologists and diagnostic contradictions among manual readers. Design/methodology/approach In this research, convolutional neural network (CNN) was used based on colored retinal fundus images for the detection of DR and classification of its stages. CNN can recognize sophisticated features on the retina and provides an automatic diagnosis. The pre-trained VGG-16 CNN model was applied using a transfer learning (TL) approach to utilize the already learned parameters in the detection. Findings By conducting different experiments set up with different severity groupings, the achieved results are promising. The best-achieved accuracies for 2-class, 3-class, 4-class and 5-class classifications are 86.5, 80.5, 63.5 and 73.7, respectively. Originality/value In this research, VGG-16 was used to detect and classify DR stages using the TL approach. Different combinations of classes were used in the classification of DR severity stages to illustrate the ability of the model to differentiate between the classes and verify the effect of these changes on the performance of the model.

Purpose The authors aim to develop a conceptual framework for longitudinal estimation of stress-related states in the wild (IW), based on the machine learning (ML) algorithms that use physiological and non-physiological bio-sensor data. Design/methodology/approach The authors propose a conceptual framework for longitudinal estimation of stress-related states consisting of four blocks: (1) identification; (2) validation; (3) measurement and (4) visualization. The authors implement each step of the proposed conceptual framework, using the example of Gaussian mixture model (GMM) and K-means algorithm. These ML algorithms are trained on the data of 18 workers from the public administration sector who wore biometric devices for about two months. Findings The authors confirm the convergent validity of a proposed conceptual framework IW. Empirical data analysis suggests that two-cluster models achieve five-fold cross-validation accuracy exceeding 70% in identifying stress. Coefficient of accuracy decreases for three-cluster models achieving around 45%. The authors conclude that identification models may serve to derive longitudinal stress-related measures. Research limitations/implications Proposed conceptual framework may guide researchers in creating validated stress-related indicators. At the same time, physiological sensing of stress through identification models is limited because of subject-specific reactions to stressors. Practical implications Longitudinal indicators on stress allow estimation of long-term impact coming from external environment on stress-related states. Such stress-related indicators can become an integral part of mobile/web/computer applications supporting stress management programs. Social implications Timely identification of excessive stress may improve individual well-being and prevent development stress-related diseases. Originality/value The study develops a novel conceptual framework for longitudinal estimation of stress-related states using physiological and non-physiological bio-sensor data, given that scientific knowledge on validated longitudinal indicators of stress is in emergent state.

PurposeThe practical purpose of this research is to propose a candidate for post-quantum signature standard that is free of significant drawback of the finalists of the NIST world competition, which consists in the large size of the signature and the public key. The practical purpose is to propose a fundamentally new method for development of algebraic digital signature algorithms.Design/methodology/approachThe proposed method is distinguished by the use of two different finite commutative associative algebras as a single algebraic support of the digital signature scheme and setting two different verification equation for a single signature. A single public key is computed as the first and the second public keys, elements of which are computed exponentiating two different generators of cyclic groups in each of the algebras.FindingsAdditionally, a scalar multiplication by a private integer is performed as final step of calculation of every element of the public key. The same powers and the same scalar values are used to compute the first and the second public keys by the same mathematic formulas. Due to such design, the said generators are kept in secret, providing resistance to quantum attacks. Two new finite commutative associative algebras, multiplicative group of which possesses four-dimensional cyclicity, have been proposed as a suitable algebraic support.Originality/valueThe introduced method is novel and includes new techniques for designing algebraic signature schemes that resist quantum attacks. On its base, a new practical post-quantum signature scheme with relatively small size of signature and public key is developed.

PurposeDiabetes is one of the life-threatening chronic diseases, which is already affecting 422m people globally based on (World Health Organization) WHO report as at 2018. This costs individuals, government and groups a whole lot; right from its diagnosis stage to the treatment stage. The reason for this cost, among others, is that it is a long-term treatment disease. This disease is likely to continue to affect more people because of its long asymptotic phase, which makes its early detection not feasible.Design/methodology/approachIn this study, the authors have presented machine learning models with feature selection, which can detect diabetes disease at its early stage. Also, the models presented are not costly and available to everyone, including those in the remote areas.FindingsThe study result shows that feature selection helps in getting better model, as it prevents overfitting and removes redundant data. Hence, the study result when compared with previous research shows the better result has been achieved, after it was evaluated based on metrics such as F-measure, Precision-Recall curve and Receiver Operating Characteristic Area Under Curve. This discovery has the potential to impact on clinical practice, when health workers aim at diagnosing diabetes disease at its early stage.Originality/valueThis study has not been published anywhere else.