Aim/Purpose: This study aims to identify the key factors influencing the adoption of integrated enterprise resource planning and business intelligence systems (ERPBI) in small and medium-sized enterprises (SMEs). Using the technology-organization-environment (TOE) framework, the study develops a conceptual framework explaining how technological, organizational, and environmental determinants shape ERPBI adoption. Background: ERP and BI systems are increasingly interdependent: ERP systems integrate operational data, while BI systems convert that data into decision-support insights. In SMEs, adopting integrated ERPBI systems is especially challenging because of limited resources, technical expertise, and managerial capacity. Since existing studies often examine ERP and BI separately, an integrated, SME-focused framework is needed to better explain the combined adoption of operational and analytical capabilities. Methodology: A two-phase research design was employed. First, a systematic literature review of peer-reviewed studies published between 2017 and 2025 was conducted to extract ERPBI adoption determinants. Second, ten domain specialists were selected through purposive sampling based on their experience in ERP, BI, SME digitalization, or information systems adoption. They evaluated the relevance and importance of the identified determinants, which were then ranked using aggregated mean expert scores. Contribution: This study consolidates fragmented ERP and BI adoption research into an integrated ERPBI perspective and proposes a validated TOE-based conceptual framework specifically tailored to SMEs. Findings: The findings suggest that ERPBI adoption in SMEs is influenced by twelve technological, organizational, and environmental determinants: top management support, training, competitive pressure, communication, firm size, compatibility, relative advantage, perceived usefulness, artificial intelligence tools, big data analytics ability, cloud computing facility, and pandemic recovery planning. Rather than presenting these factors as definitive predictors of adoption success, the study synthesizes prior evidence and expert feedback to propose a structured framework for further empirical investigation. Recommendations for Practitioners: For practitioners, the proposed framework should be viewed as a decision-support guide rather than a prescriptive implementation model. SME managers may use the framework to assess key readiness areas, including technological compatibility, organizational resources, managerial support, employee capability, vendor support, and external pressures. However, the relevance and priority of these factors may vary across SME size, sector, digital maturity, and resource availability. Recommendation for Researchers: Future research should empirically test the proposed framework across different SME sectors and regions and investigate post-adoption outcomes using longitudinal approaches. Impact on Society: Effective ERPBI adoption can strengthen SME resilience, promote sustainable business practices, and contribute to economic stability through enhanced digital transformation. Future Research: Further studies are encouraged to explore emerging factors such as cybersecurity readiness, data governance, and responsible AI practices in ERPBI adoption.
Aim/Purpose: The primary objective is to address the structural operational cost crisis in modern SOCs by designing and formally specifying a three-layer agentic AI framework that integrates semantic alert triage, adaptive reinforcement-learning response, and episodic knowledge synthesis into a unified architecture. Background: Modern SOCs are experiencing an acute operational crisis. Exponential growth in alert volume, high false-positive rates (>40%), and chronic analyst attrition have created a perfect storm. Existing rule-based SIEM and single-agent SOAR approaches only achieve 20–55% alert automation and fail to address the full operational lifecycle. Methodology: The framework evaluation is based on a structured comparison with seven benchmark systems across four dimensions (threat coverage breadth, integration completeness, cost quantification, and adversarial safeguards), each rated on a five-level ordinal scale using replicable criteria. Contribution: The paper makes four contributions: (1) a formal algorithmic specification of a three-layer agentic AI architecture including three pseudocode procedures and a PPO state-action-reward formalism; (2) a quantitative operational cost projection framework explicitly distinguishing designed targets from measured performance, with a maximum designed workload reduction of 86%; (3) a systematic four-dimensional comparative analysis against seven benchmark frameworks demonstrating that CyberAgent is the only framework achieving full architectural completeness (integrating all three of semantic triage, adaptive RL response, and episodic knowledge synthesis simultaneously), an architectural claim requiring empirical confirmation; and (4) dual adversarial safeguards (prompt injection mitigation and reasoning consistency verification) absent from all seven benchmark frameworks. Findings: CyberAgent is a theoretical design-science artefact that has neither been implemented nor empirically evaluated. All quantitative projections are designed to achieve targets grounded in prior work, not verified outcomes: an alert automation rate of 85–90%, an analyst workload reduction of 56–86% (design target 86% under the product-rule independence assumption), an MTTR reduction of 65–75%, and a false-positive reduction of 60–70%. These projections require empirical validation using CybORG and the DARPA OpTC dataset, with this as the primary future work priority. Recommendations for Practitioners: The PTL’s Chain-of-Thought (CoT) reasoning traces provide human-readable decision narratives that enhance transparency and may support auditability workflows relevant to GDPR Article 33, HIPAA, PCI-DSS, and SOX. However, CoT traces do not automatically satisfy regulatory auditability or compliance requirements; they are one architectural input to a broader compliance process. Formal legal and compliance assessment by qualified professionals is required before deployment in regulated environments. Practitioners should treat CoT output as decision-support documentation, not as regulatory certification. Recommendation for Researchers: Future work should also develop federated DRL training protocols to ensure policy convergence under data-scarce conditions and rigorously test the adversarial robustness of the PTL’s consistency-checking mechanism against novel prompt-injection strategies. Impact on Society: If empirically validated, CyberAgent could make enterprise-grade cyber defence more accessible to mid-market organisations that cannot afford 24/7 SOC analyst staffing, by substantially reducing the alert-triage workload. All such impact claims are conditional on validation results. Future Research: Priority directions include: (1) empirical implementation and red-team validation across diverse enterprise environments; (2) federated DRL training to address the data sharing constraints that limit policy learning in regulated sectors; (3) extension of the KSL to support cross-organizational threat intelligence sharing; and (4) longitudinal studies measuring analyst skill development and human-AI trust calibration under progressively increasing levels of CyberAgent autonomy.
Aim/Purpose: Individual differences in signers’ speed and amplitude cause variations in keypoint sequences, leading to redundant features that degrade the classification performance of sign language recognition models. Background: To reduce the impact of individual differences among signers, this paper proposes a Dynamic Adaptive Representation Calibration (DARC) module that helps the model focus on the most informative features. Methodology: The study utilizes component-based modeling of high-dimensional semantic features and introduces sample-adaptive learnable weights. The method was validated using large-scale sign language datasets, specifically WLASL2000 and MSASL1000. Contribution: The proposed DARC module dynamically adjusts the importance of different features for each input, allowing the model to focus more on informative patterns and reducing the influence of individual differences among signers. Findings: The proposed method achieved a Top-1 accuracy of 56.86% on the WLASL2000 dataset (a 3.2% relative improvement over the state-of-the-art DSTA-SLR) and 65.88% on the MSASL1000 dataset. Visualizations confirm that the proposed module significantly improves feature discriminability and clustering clarity. Additionally, multi-stream training validations demonstrate consistent performance improvements across spatial and temporal dynamic streams, effectively raising the model’s overall representation ceiling. Recommendations for Practitioners: Developers of practical sign language recognition systems should consider integrating dynamic adaptive calibration to better handle natural variations among different signers in real-world environments. Recommendation for Researchers: Researchers should further explore dynamic feature recalibration techniques to improve model robustness against individual variations in sequence-based recognition tasks. Impact on Society: By improving the accuracy of keypoint-based computer vision models, this research helps develop more accessible and scalable tools to bridge the communication gap between the deaf/hard-of-hearing community and hearing individuals. Future Research: Future studies should explore the application of the DARC module to other video-based action recognition tasks or investigate its performance in real-time continuous sign language translation.
Aim/Purpose: The use of machine learning models in graduate employability prediction is constrained by limited transparency. This limitation weakens their value for organizational decision-making in higher education. Background: An Explainable Artificial Intelligence (XAI) framework is proposed to fill this void. Using this framework, the predictive output generated will be translated into insights that are interpretable and useful for sensemaking and evidence-based management. Methodology: The experiments were conducted on a database containing 225,384 graduate records. The best accuracy results were obtained using the CatBoost algorithm, and global and local explanations were generated using SHAP and ICE. Contribution: Predictive accuracy is integrated with interpretability in this study. A framework is produced as a result, designed to support accountable, data-driven decision-making processes within higher education institutions. Findings: Education level and language proficiency are identified as dominant predictors of employability outcomes. Substantial influence is also exerted by GPA, university ranking, and internship experience, while demographic attributes such as gender make a negligible contribution. Both aggregate feature importance and heterogeneous individual effects are exposed through the explainability analysis. Recommendations for Practitioners: Institutions should prioritize language development, targeted academic support, and expanded internship pathways. Interpretable analytics should also be embedded in curriculum planning and policymaking. Recommendation for Researchers: Explainable AI should be examined within broader educational landscapes in future research. Additional variables should be incorporated, with particular attention directed toward fairness, bias, and model robustness. Impact on Society: The results indicate potential for more equitable and effective policy making. They also align with broader objectives related to workforce readiness and Sustainable Development Goals on education and employment. Future Research: Future work should rely on longitudinal and multi-institutional data. The practical impact of explainable AI in real decision-support environments also requires systematic evaluation.
Aim/Purpose: This study examines how students perceive the impact of Learning Management Systems (LMS) on teachers’ performance at Kuwait’s higher education institutions. Background: Learning institutions integrate LMS into their teaching methods to unlock numerous benefits. A performance-based approach is crucial for understanding the complex, multidisciplinary nature of teaching performance in an LMS-based blended learning environment. Methodology: Cross-sectional data were collected from 473 LMS users at Kuwait’s higher education institutions via questionnaires. Partial Least Squares Structural Equation Modelling (PLS-SEM) using SmartPLS was employed to test the hypotheses presented in the research model. Contribution: This study extends the DeLone and McLean Information Systems Success Model by incorporating social influence, along with LMS quality factors (information quality, system quality, and service quality), to explain students’ LMS usage and their perceptions of teaching performance. Additionally, the influence of technology on teaching performance is overlooked compared to student academic performance. Findings: This study’s findings suggest that, to improve teaching performance through LMS, higher education institutions should actively encourage students to increase their use of the LMS. In addition, the findings support the conclusion that the administration should ensure that students have access to a high-quality LMS with updated, easy-to-use features that align with technological advancements, thereby creating a user-friendly experience. Recommendations for Practitioners: Kuwait’s higher education system should implement LMS features that: facilitate faculty experience and encourage student use; improve communication with technical support to customise plugins and tailor the LMS to specific needs; and invest in networks and infrastructure to ensure reliability, ease of use, and speed. Recommendation for Researchers: Researchers must apply models and theories across different contexts with caution. Specifically, socio-economic and socio-cultural contexts are key to framing questions or justifying the choice of a theoretical angle. Impact on Society: Because implementing systems in instructional design requires a considerable investment, research like the current study enables learning institutions to move beyond assumptions and focus on what truly matters. Future Research: Future researchers should test and evaluate the model across different universities and LMS platforms, as this study focuses solely on Moodle. Researchers interested in LMS usage and teacher performance should broaden their scope to include other educational institutions, helping to overcome the current limitations of teacher performance studies in Kuwait.
Aim/Purpose: This paper investigates how to enhance Gen Z’s purchase intention on e-commerce platforms via gamification. Background: Most studies focus on user perceptions, which capture surface-level impressions but fail to uncover the underlying psychological needs that drive user engagement. This study addresses that gap by examining how users’ psychological needs (competence, autonomy, relatedness) and perceptions of gamification (usefulness, ease of use, enjoyment) influence gamified customer interaction and online purchase intention, particularly among Gen Z in e-commerce retailing. Methodology: An extended PLS-SEM method based on the Technology Acceptance Model and Self-Determination Theory was applied, with survey data collected from 416 Gen Z users of e-commerce platforms in Vietnam. Contribution: This paper is the first to investigate how e-commerce gamification enhances Vietnamese Gen Z purchase intentions. It further integrates the Technology Acceptance Model and Self-Determination Theory to reveal their underlying connections and bridge the perception-action gap. Findings: The findings reveal that gaming continuance intention, the strongest driver of online purchase intention, is shaped by perceived usefulness, ease of use, and enjoyment, with usefulness exerting the greatest influence. Autonomy, competence, and relatedness enhance these perceptions, as Gen Z values meaningful control, personalized choices, and clear, structured challenges with tangible retail benefits. While enjoyment plays a secondary role, it remains vital to prevent disengagement. Notably, social interaction – despite Gen Z’s connectedness – has significant influence only when it is integrated meaningfully. Recommendations for Practitioners: E-commerce gamification should go beyond superficial features by embedding user needs and value-driven experiences that resonate with Gen Z’s practical, emotional, and social retail behaviors, turning their passion for gaming into a drive to purchase. Recommendation for Researchers: The study examined social influence as a moderator only; future research should explore other factors, such as culture, preferences, habits, and demographic variables, to enhance the model’s generalizability. Impact on Society: This research has a notable societal impact by offering insights into how e-commerce platforms can better engage Gen Z consumers through meaningful and psychologically driven gamification. By highlighting the importance of usefulness, enjoyment, and autonomy in shaping purchase behavior, this approach helps businesses design more effective digital experiences, potentially leading to improved consumer satisfaction, greater online retail efficiency, and more personalized, user-centric commerce ecosystems. Future Research: The use of snowball sampling in this study may have introduced bias by producing a homogenous sample, limiting the representativeness of Gen Z. Future studies could combine methods – such as cluster sampling to ensure population diversity, followed by snowball sampling within clusters – and use purposive sampling for in-depth interviews with individuals of specific characteristics.
Aim/Purpose: The purpose of this study is to develop an adaptive real-time flower classification framework that maximizes accuracy, speed, and resource efficiency by integrating Transfer Learning, Extreme Learning Machines, and Reinforcement Learning. Background: Accurate and efficient flower species identification is essential for applications in smart city planning, agriculture, and floriculture. Traditional static classification models lack adaptability to diverse environments and resource constraints, necessitating dynamic approaches that can optimize performance in real-time settings. Methodology: The proposed framework employs a Reinforcement Learning (RL) agent to dynamically select between lightweight classifiers (ELM + MobileNetV2) and high-accuracy classifiers (CNN + EfficientNetB0). The system is trained and evaluated on a public Kaggle dataset and real-time images captured via IoT-enabled cameras, ensuring robustness in both controlled and real-world scenarios. Contribution: This study introduces a novel adaptive classification system that balances accuracy, inference latency, and resource usage through RL-based decision-making. It advances the field by demonstrating superior adaptability and efficiency compared to static ensembles and state-of-the-art methods. Findings: The framework achieves 95.8% accuracy while reducing training and inference latency. The RL-driven approach outperforms traditional static models, showing enhanced scalability, resource-awareness, and real-time performance in diverse environments. Recommendations for Practitioners: Practitioners should consider implementing RL-based adaptive classification systems to improve real-time accuracy and resource management, especially in IoT-driven environments, such as smart cities and precision agriculture. Recommendation for Researchers: Further research is encouraged to explore additional classifier combinations, extend the framework to other classification tasks, and investigate long-term adaptive strategies for dynamic environments. Impact on Society: This framework has the potential to significantly improve real-time monitoring and management in urban greenery, crop monitoring, and flower industry automation, contributing to sustainable practices and enhanced urban aesthetics. Future Research: Future studies may focus on integrating more diverse classifiers, optimizing RL policies for even faster adaptation, and deploying the system in large-scale, real-world deployments to evaluate long-term robustness and utility.
Aim/Purpose: The present paper focuses on the necessity of systematically incorporating knowledge produced within e-Communities of Practice (eCoPs) into formal organizational decision-making mechanisms, especially in environments of complexity, uncertainty, and accelerated digital evolution. Background: Even though eCoPs have been acknowledged as formidable tools for collaborative learning and knowledge sharing, their systematic integration into executive-level Decision Support Systems (DSS) has yet to be achieved. A coherent theoretical integration has not yet been developed. Methodology: The study takes a conceptual and design-based research approach in which the authors synthesize the modern literature on digital collaboration, knowledge management, leadership, and intelligent decision-support systems. Based on this, a knowledge-based, leadership-focused decision model is created. Contribution: The paper also proposes a reference architecture that serves as a layer of knowledge formation between eCoPs collaboration platforms and Intelligent Decision Support Systems (IDSS), facilitating two-way integration of tacit community insights and formal analytical models. In contrast to conventional data-based DSS models, the proposed model integrates socially constructed, practice-based knowledge into the decision-making process. Findings: The discussion shows that the systematic integration of knowledge generated by eCoPs makes decision-making more rational, helps address semi-structured and unstructured issues more effectively, and improves organizational learning and adaptive capacity. Recommendations for Practitioners: The eCoPs should be strategically institutionalized within organizations, supported by collaboration-enabling infrastructures coupled with decision systems, and embedded in leadership practices that encourage trust, openness, and the co-creation of knowledge. The model is especially relevant in SMEs and organizations undergoing digital transformation, where tacit knowledge is essential in strategic responsiveness. Recommendation for Researchers: In future research, the framework should be empirically tested in organizational settings, the governance and trust mechanisms of eCoPs-based decision systems should be studied, and the ways AI could be used to improve collaborative knowledge extraction and structuring should be identified. Impact on Society: The framework helps to make organizational decision-making more transparent, inclusive, and knowledge-based by formally integrating collective expertise into organizational decision systems. Future Research: Future research must use longitudinal and mixed-method designs to identify the quantifiable effects of eCoPs-created knowledge on decision quality and organizational performance, and to conduct cross-sector and cross-cultural comparisons.
Aim/Purpose: This study aims to evaluate the trend in the adoption and implementation of integrated reporting (IR) by selected Indian companies in line with the Integrated Reporting Framework ( Framework) over the past five years, from 2019-20 to 2023-24. Background: Although the growing movement towards voluntary adoption of integrated reporting by Indian firms is evident through the expanding figures, it remains at a budding stage in India, stressing the need to analyze reporting practices in terms of the extent of the Framework’s compliance by Indian firms as well as the rate of adoption. Methodology: The study analyzed the quality of integrated reports from 32 firms over five years using content analysis with the Integrated Reporting Disclosure Index. In addition, descriptive charts and the chi-square test were employed to support the empirical analysis. Contribution: The study integrates legitimacy, stakeholder, and institutional theories to explain the observed patterns. The findings suggest that improvements in integrated reporting practices are driven by a combination of legitimacy-seeking behavior, stakeholder pressures, and institutional influences, including regulatory encouragement by SEBI and normative guidance from professional bodies. Findings: The findings reveal that while the Framework’s adoption has increased over time, only 53% of the sampled firms published integrated reports by 2023–24, indicating partial diffusion of the Framework. In contrast, disclosure quality shows a consistent upward trend, with nearly 50% of firms achieving IRQ scores in the range of 0.80–0.85, reflecting substantial improvements in reporting practices. Significant variation in disclosure was reported in the study, such as in the disclosure of governance, strategy, and resource allocation by Indian companies, restraining stakeholders’ intellectual capacity to value created over time. Recommendations for Practitioners: To promote more rigorous implementation of the Framework with value-added disclosure quality, there is an evident need for a robust, focused regulatory framework. From a regulatory standpoint, the data support the creation of stronger, more focused policy frameworks to promote broader adoption and enhance disclosure uniformity. Recommendation for Researchers: The researchers may focus on analyzing the association between integrated reporting disclosures and firm value or performance. Researchers can focus on analyzing the key determinants influencing the Framework’s adoption and the IRQ. Impact on Society: The study offers a benchmark for enhancing reporting quality for practitioners and other stakeholders, such as investors and the general public, strengthening transparency, competitiveness, and well-informed decision-making. Future Research: Future studies could be conducted, aimed at cross-country comparative analyses based on India and other emerging economies, incorporating both financial and non-financial sectors, to provide a more inclusive representation of integrated reporting practices and their consequences.
Aim/Purpose: This study addresses the challenge of understanding and predicting tourist decision-making in the AI era by integrating sentiment, credibility, and contextual signals from social media into a unified and actionable framework. It seeks to move beyond raw user-generated content toward trustworthy, decision-ready insights that can guide destinations, platforms, and travelers. Background: Tourism analytics often treat online sentiment at a surface level, overlooking emotional nuance, content credibility, and real-world context. To bridge this gap, the Affective Understanding, Reliability, and Outcome-driven Recommendation Architecture (AURORA) offers a sentiment-driven, context-aware system that captures emotions, filters unreliable information, and models how travelers make choices across different decision stages. Methodology: AURORA processes multimodal public data such as reviews, social posts, and event feeds. It combines aspect-based sentiment and emotion analysis with credibility assessment and contextual modeling. A Bayesian state-space model tracks traveler decision stages, while uplift modeling identifies when and where interventions are most effective. The analysis tested AURORA on a large-scale Booking.com dataset spanning 18–24 months, which captured seasonal variation. Contribution: AURORA introduces a next-generation, sentiment-based decision framework that unites emotional understanding, trust evaluation, and context sensitivity in tourism analytics. The paper demonstrates how combining textual and behavioral data yields measurable insights that are both theoretically grounded and practically deployable for decision support. Findings: Aspect‑level sentiment on core attributes – particularly safety, cleanliness, and value – emerges as the strongest predictor of traveler attitudes and booking propensity, with emotional intensity amplifying these effects and social proof showing diminishing marginal returns at high volumes. Credibility and provenance filters materially reduce noise from low‑quality or manipulated content, and hybrid models that combine textual embeddings with structured metadata outperform polarity‑only baselines for predicting high‑intent behaviors. Practitioners should therefore prioritize real‑time monitoring of high‑elasticity aspects, elevate aspect‑rich, high‑credibility content in ranking and messaging, and time interventions to the traveler’s decision stage to maximize incremental lift rather than mere engagement. Recommendations for Practitioners: Prioritize real-time monitoring of high-elasticity aspects (e.g., safety, crowding) to inform campaigns. Elevate high-quality, aspect-rich user content in ranking algorithms. Time interventions to decision-journey stages when cues are most impactful. Recommendation for Researchers: Extend the framework to non-English, multilingual contexts with localized aspect taxonomies. Investigate causal pathways between exposure to specific sentiment cues and actual booking behavior. Explore the integration of multimedia sentiment (image/video emotion) in tourism decision models. Impact on Society: Enables more transparent and trustworthy tourism information ecosystems, empowering travelers to make better decisions and helping destinations manage perception during crises. Fosters healthier digital tourism discourse by amplifying authentic, credible voices. Future Research: Building on AURORA, the next phase should validate and extend the architecture across languages, cultures, and media. This includes developing localized aspect taxonomies and multilingual encoders, running causal field experiments that link exposure to specific sentiment cues with booking behavior, and integrating multimedia emotion signals (images and video) alongside privacy‑preserving, on‑device analytics. Together, these steps will make AURORA more robust to cross‑cultural expression, resilient under distribution shifts, and practical for real‑time, privacy‑aware deployment in diverse tourism ecosystems.
Aim/Purpose: This study aims to analyze and predict the employability outcomes of higher education students in the Philippines using data-driven predictive modeling. It aims to identify the student attributes that most strongly influence employability, thereby supporting evidence-based curriculum development and workforce alignment initiatives. Background: Graduate employability remains a challenge in the Philippines due to persistent gaps between higher education outcomes and labor market expectations. While prior studies emphasize technical competencies, there is limited evidence on the role of non-academic student attributes in predicting employability, particularly through interpretable predictive approaches. This study addresses this gap by examining employability-related traits using machine learning techniques. Methodology: A publicly available dataset of 2,982 anonymized student records from mock interviews conducted across Philippine higher education institutions was analyzed. Employability was treated as a binary outcome variable. Predictive models were developed with Random Forest selected as the primary model based on overall performance. Model interpretation was conducted using Shapley Additive Explanations (SHAP) analysis to identify the most influential student attributes. Contribution: The study demonstrates how interpretable machine learning can be used to evaluate graduate employability and identify key attributes shaping workforce readiness. The findings offer practical value for higher education institutions and policymakers seeking data-driven approaches to curriculum design and student development. Findings: The Random Forest model showed strong predictive performance in classifying employability outcomes. SHAP analysis revealed that mental alertness, general appearance, and the ability to present ideas were the most influential factors affecting employability, indicating the importance of cognitive and professional presentation skills. Recommendations for Practitioners: Higher education institutions should strengthen instructional strategies and student development programs that enhance cognitive readiness, professional presentation, and communication-related competencies. Career services and industry partners are encouraged to collaborate in aligning training initiatives with employability needs. Recommendation for Researchers: Future studies should explore additional predictive models and incorporate broader datasets to further validate the determinants of employability. Including demographic and academic variables may deepen understanding of employability dynamics. Impact on Society: By identifying critical employability attributes, this study supports more responsive and inclusive higher education practices. Data-driven employability strategies can contribute to improved workforce readiness and reduced graduate unemployment in the Philippines. Future Research: Future research may examine longitudinal employability outcomes and assess the application of predictive analytics in institutional decision-making contexts. Attention to ethical considerations, including transparency and fairness, is also recommended.
Aim/Purpose: This study aims to address the issue of partial preference, which causes incomplete criteria-level ratings and limits the accuracy of recommendations in multi-criteria recommender systems (MCRS). The primary focus of this study is to develop an imputation method that treats the imputation process as a sequential prediction task in which each missing criterion is predicted based not only on the known ratings but also on the previously imputed values. These preceding ratings serve as contextual input for the next prediction step, enabling the model to dynamically capture inter-criteria dependencies and thereby improve the overall imputation quality. Background: A key challenge faced by MCRS is the issue of partial preference, which arises when users fail to provide ratings for all criteria. This results in incomplete criteria-level data, ultimately undermining the accuracy and effectiveness of MCRS in generating relevant recommendations. While most studies have primarily focused on improving the recommendation algorithms themselves, the pre-recommendation phase, which involves preparing high-quality and comprehensive input data, has often been overlooked. Yet, ensuring that multi-criteria data is as complete and accurate as possible is crucial for producing high-quality recommendations. This highlights the importance of a preprocessing step, particularly the imputation process to handle incomplete criteria ratings, applied prior to the recommendation generation process. Rating-based imputation offers efficiency, while machine learning-based imputation offers accuracy. To leverage those advantages, this study employed rating-based imputation using a simple yet effective machine learning technique, Naive Bayes (NB). NB operates under the assumption of conditional independence among features, which may lead to suboptimal performance in contexts where semantic or perceptual correlations exist among criteria. In response to this limitation, this study introduces a sequential imputation approach, where each prediction of a missing criterion is informed by previously known or imputed ratings that are used as contextual input for the next prediction. Methodology: This study introduces a new imputation method called Recurrent Naive Bayes (RNB), designed to estimate missing criteria ratings. Unlike traditional approaches, RNB models the imputation as a sequential prediction process, where each known or already imputed criterion Rc serves as contextual information for predicting the subsequent missing criterion Rc+1. The core of RNB involves a recurrent process that includes prediction using NB, conditional imputation for the missing values, and updating the set of completed criteria. At each step, the model uses more features, starting with the overall rating and adding each newly predicted criterion one by one until all criteria are completed. In the recommendation process, RNB is used beforehand as part of the Multi-Criteria Collaborative Filtering (MCCF) pipeline. The performance of RNB is then evaluated by examining its impact on recommendation accuracy, specifically in terms of predicted criteria ratings, overall ratings, and recommended items, using three real-world datasets: TripAdvisor (TA), Yahoo! Movies (YM), and BeerAdvocate (BA). Contribution: This study addresses the issue of partial preference in MCRS by highlighting the underexplored potential of NB for imputing missing criteria ratings. To this end, we propose RNB, a novel method that enhances traditional NB by adopting a sequential imputation strategy. Unlike conventional approaches that treat each criterion independently, RNB captures inter-criteria correlations, thereby improving imputation quality while preserving computational efficiency. Findings: RNB consistently outperformed baseline methods significantly, including no imputation, mean imputation, and NB imputation, in enhancing MCRS performance across all datasets. This is demonstrated by its performance in predicting criteria ratings, overall ratings, and recommended items. The improvements were most notable in datasets with a larger number of criteria, stronger inter-criteria correlations, and larger size. Additionally, RNB enhanced recommendation accuracy for both moderately and highly recommended items. Recommendations for Practitioners: By implementing MCRS, practitioners are encouraged to incorporate imputation techniques, such as RNB, during the preprocessing stage to improve data completeness and overall recommendation quality. RNB offers a practical balance between accuracy and efficiency, making it suitable for real-world applications where computational resources and data quality vary. It is especially recommended in scenarios involving sparse multi-criteria data with high inter-criteria correlation, such as in tourism, e-commerce, or entertainment domains. Recommendation for Researchers: Adopting RNB can be beneficial for researchers as a practical and effective imputation method in MCRS, particularly when dealing with sparse and partially filled datasets. Its ability to capture inter-criteria dependencies through a sequential process makes it a valuable alternative to traditional imputation methods that assume feature independence. RNB’s simplicity, efficiency, and ease of integration into existing MCRS frameworks make it suitable for empirical studies that require scalable and interpretable preprocessing techniques. Impact on Society: Recommender systems play a vital role in supporting decision-making across various domains such as tourism, entertainment, e-commerce, and education. By addressing the issue of partial preferences, RNB improves the completeness of user data, leading to more relevant and personalized recommendations. This impacts enhanced user satisfaction, better overall experiences, increased trust in digital platforms, and more informed consumer decisions. Moreover, the efficiency and simplicity of RNB support broader accessibility by enabling effective recommendations even in data-sparse environments. Future Research: The performance of RNB depends on the assumption that inter-criteria dependencies can be captured in a sequential manner. However, the optimal ordering of criteria may differ between datasets, requiring dataset-specific analysis. Future research may explore dynamic or hybrid ordering strategies that simultaneously consider both sparsity and correlation to improve imputation quality. In addition, incorporating more advanced machine learning techniques could help model complex or nonlinear relationships among criteria. Furthermore, enhancing the robustness and adaptability of the imputation process.
Aim/Purpose: The research aimed to design, develop, and test a system that enabled reciprocal knowledge flows between government, academia, business, media, and community stakeholders. Background: The research problem addressed in this study concerned the absence of an integrated, digital knowledge management (KM) system that could operationalize the Pentahelix framework to strengthen the management and governance of VOEs. Despite policy frameworks such as Government Regulation No. 11/2021, which formalized the operational mechanisms of Village-Owned Enterprises (VOEs) and emphasized entrepreneurship and community empowerment, challenges persisted in translating these frameworks into practice. Methodology: Employing a research and development (R&D) approach with Agile Scrum, the study engaged eight VOE managers from four villages in the Tomini Bay region of Gorontalo Province to elicit requirements through interviews, observations, and questionnaires. The system was developed iteratively over four sprints and implemented functionalities such as user authentication, collaborative forums, a knowledge repository, and analytics dashboards. The platform design utilized Unified Modeling Language (UML) diagrams to model workflows, actor roles, and class structures. System testing applied black-box and white-box approaches, complemented by sprint reviews and user acceptance testing. Contribution: This research contributed to the body of knowledge by offering both a conceptual framework and a tested prototype for digitally mediated multi-stakeholder collaboration in rural enterprise development. Findings: The findings underscored that digital KM platforms, when anchored in multi-stakeholder frameworks, served as strategic enablers of rural development. Evaluation demonstrated high system reliability with 100% functional test pass rate and optimized query response times (reduced by 60-75%). User acceptance testing revealed strong adoption potential, with Perceived Usefulness (M = 6.2/7.0), Intention to Use (M = 6.0/7.0), and Overall Satisfaction (M = 5.9/7.0) scores indicating high levels of satisfaction. Task completion rates improved from 72% in Sprint 1 to 95% in Sprint 4. The integration of the platform with potential e-government and e-commerce systems suggested significant implications for participatory governance, market democratization, and rural economic empowerment. Recommendations for Practitioners: Practically, by presenting a tested prototype developed using Agile Scrum methodology that served as a model for similar initiatives in developing countries. Recommendation for Researchers: Theoretically, by extending the application of KM and Pentahelix frameworks to rural enterprise contexts. Impact on Society: The platform’s adaptability to diverse digital readiness contexts signaled its transferability to other rural regions, provided that localized adjustments were made. Future Research: Future studies could explore the integration of automation, advanced analytics, and recommender systems while further evaluating the longitudinal impacts on business performance, collaboration intensity, and community well-being.
Aim/Purpose: Strategic decision-making in Sustainable Bio-Based Supply Chains (SBSCs) is increasingly hindered by semantic ambiguity, expert inconsistency, and the inability of conventional models to handle uncertainty. These challenges compromise the alignment of AI integration with sustainability goals, especially in complex, multi-criteria environments. This study develops an AI-based decision support framework that addresses uncertainty and complexity in evaluating SBSCs, leveraging hybrid fuzzy logic methodologies. Background: The shift toward AI-enabled SBSCs introduces multifaceted sustainability trade-offs and challenges rooted in linguistic ambiguity, subjective judgments, and expert inconsistency. Existing methods often lack the semantic resilience required for strategic supply chain planning under uncertainty. Methodology: This study proposes an integrated hybrid approach combining Circular Intuitionistic Fuzzy Sets (C-IFS) with a Type-2 Fuzzy MAIRCA method. The framework operates in two stages: (1) C-IFS aggregation and entropy-based filtering to derive robust criteria weights and manage low-consensus indicators; and (2) application of Type-2 Fuzzy MAIRCA to assess and prioritize AI-integrated SBSC alternatives against idealized performance targets using interval-valued fuzzy distances. Contribution: The proposed model introduces a novel fusion of advanced fuzzy logic techniques to enable transparent, interpretable, and information-centric evaluation of bio-based supply chain configurations in uncertain environments. Findings: Among the evaluated SBSC configurations, the fully integrated AI-driven model (A2) achieved the highest sustainability score (0.872) with the lowest performance gap (Ψ = 0.486), confirming its strategic alignment. Scenario testing under semantic shifts upheld the model’s robustness and highlighted digital infrastructure as a key sensitivity factor. Recommendations for Practitioners: Practitioners can adopt the proposed framework to improve the strategic alignment of AI implementations in SBSCs, enabling more resilient, data-driven decisions across operational and regulatory dimensions. Recommendation for Researchers: Researchers are encouraged to explore extensions of this hybrid approach to other high-uncertainty domains and to examine the integration of additional soft computing methods for enhanced decision fidelity. Impact on Society: By supporting sustainable and technologically adaptive supply chains, this framework contributes to greener production ecosystems and informed policymaking in bioeconomy sectors. Future Research: Future studies may incorporate dynamic feedback systems, real-time AI learning, or bibliometric modeling to enrich the methodological scope and cross-sector applicability of the framework.
Aim/Purpose: This paper focuses on app review analysis techniques, driven by the rapid advancement of the mobile app market and NLP techniques in optimizing mobile app user experiences. Background: Owing to technological advancements, app review analysis has rapidly evolved. This study examines both conventional and emerging techniques, including current advancements such as large language models (LLMs) in app review analysis. It provides an overview of the various methods used across different categories of app review analysis, comparing effective strategies for identifying user concerns and enhancing app functionality. Methodology: A systematic review was utilized based on two major standard guidelines, PRISMA and Kitchenham’s guidelines, for the period of 2014 to 2024. After defining the review protocol, papers were identified through keyword-based searches on six major online databases: Scopus, Web of Science, IEEE Xplore, ACM Digital Library, Science Direct, and Springer. Following screening and excluding papers based on defined quality criteria, 53 papers were considered for this study. The use of PRISMA ensures a transparent and reproducible review process, while Kitchenham’s guidelines provide a structured and rigorous approach for evaluating and synthesizing the literature. Contribution: This review study aims to evaluate the current state of knowledge on app review analysis techniques to improve mobile app user experiences. This study categorized the existing state-of-the-art papers into eight different categories, such as sentiment analysis, review classification, summarization, and prioritization, and examined challenges related to app review analysis. Furthermore, the study emphasizes the potential of LLMs for optimizing and automating app review analysis and provides future directions to address gaps in user-centric app development. Findings: Among the eight main categories defined in app review analysis, sentiment analysis is the most prevalent, followed by review classification and information extraction. Most studies use a combination of these categories to achieve a comprehensive goal. Prioritization techniques such as risk matrices, thumbs-up count-based approach, and anomaly detection are widely used to identify emerging issues. Extracting meaningful information and evaluating the proposed approach are the most common challenges identified. Novel LLMs, like Chat-GPT, significantly enhance review analysis by automating the process, improving feature extraction, and enabling context-aware review classification. Recommendations for Practitioners: The combination of conventional approaches and novel LLM-based methods can enhance both the efficiency and accuracy in identifying and addressing critical issues raised through mobile app user reviews. It effectively prioritizes user concerns by leveraging the strengths of both traditional preprocessing techniques and advanced LLMs. Recommendation for Researchers: Researchers are encouraged to explore the integration of emerging technologies like LLMs to enhance the of app review analysis, particularly in feature-specific sentiment analysis. Impact on Society: The results of this study contribute to enhancing the mobile app user experience through effective app review analysis, which improves user satisfaction and supports user-centered app development. This ultimately leads to a better mobile app ecosystem, benefiting both users and developers. Future Research: In the future, this research can be extended in multiple directions. Researchers can address the existing research gaps that LLMs have yet to address, particularly in prioritizing user concerns. Additionally, there is potential for further research on tool implementations focusing on identifying persistent issues through time series analysis by considering the app version and date of the app reviews. Moreover, there is a need to develop comprehensive frameworks that are more generalizable across different apps and categories, with a focus on identifying user concerns related to specific features.
Aim/Purpose: The purpose of this paper is to address the gap in the recognition of prior learning (RPL) by automating the classification of non-formal learning certificates using deep learning techniques. This study aims to evaluate the effectiveness of different text augmentation strategies—character-level, token-level, and semantic-level—in improving the classification accuracy of these certificates, which are crucial for bridging the skills gap in the digital economy. Background: Traditional education systems often overlook skills gained through non-formal learning, creating a gap between industry needs and academic qualifications. This paper addresses this by using BERT-based deep learning models to classify non-formal learning certificates, enhanced by text augmentation techniques to improve accuracy in mapping them to formal academic standards. Methodology: This study employs a deep learning approach using Bidirectional Encoder Representations from Transformers (BERT) to classify non-formal learning certificates into seven core computer science courses. The research utilizes text augmentation techniques at character, token, and semantic levels to improve classification accuracy. A dataset of 525 certificates, collected through data gathering, was preprocessed using Optical Character Recognition (OCR) to extract text from PDF documents, followed by cleaning and augmentation before training the BERT model. Contribution: This paper addresses the growing need for efficient Recognition of Prior Learning (RPL) in the context of rapidly advancing knowledge, particularly in the AI era, where non-formal learning is becoming increasingly important. We present a novel approach to automating the classification and validation of non-formal learning certificates using deep learning techniques. The study evaluates and compares character-level, token-level, and semantic-level text augmentation methods to improve the accuracy of certificate classification. What sets this research apart is the systematic assessment of which augmentation method best enhances model performance for RPL tasks, providing new insights into optimizing deep learning models for this purpose. The findings aim to reduce human error and improve the efficiency of RPL implementation, offering a scalable solution for better integrating or converting non-formal learning into formal educational systems. Findings: The study found that token-level augmentations, particularly word insertion and word deletion, significantly improved classification accuracy, with validation accuracies exceeding 88%. Character-level augmentations also contributed to model performance, but with slightly lower accuracy. Semantic-level augmentation via back translation showed the least impact. These results demonstrate that token-level text augmentations offer the most effective strategy for enhancing the classification of non-formal learning certificates in the context of Recognition of Prior Learning (RPL). Recommendations for Practitioners: Practitioners should focus on token-level text augmentation techniques, like word insertion and deletion, to improve the accuracy of machine learning models for classifying non-formal learning certificates, enabling better integration into formal education and employment pathways. Recommendation for Researchers: Researchers should explore combining multiple augmentation techniques (e.g., token-level and semantic-level) and investigate advanced models like BERT-large or multilingual variants for improved classification accuracy. Additionally, examining the impact of different OCR tools and preprocessing strategies could further enhance non-formal learning certificate recognition. Impact on Society: The findings of this study have significant implications for improving access to education and employment opportunities. By enhancing the recognition of prior learning through automated classification of non-formal learning certificates, this research supports a more inclusive and equitable education system. It can help individuals, particularly those with non-traditional educational backgrounds, gain recognition for their skills, ultimately bridging the skills gap in the workforce and promoting lifelong learning in the digital economy. Future Research: Future research should focus on expanding the dataset to include multilingual certificates, which would enhance the model’s ability to generalize across different languages and cultural contexts. Additionally, researchers could investigate the use of hybrid models that combine BERT with other machine learning techniques to further improve classification accuracy. Exploring the integration of real-world data sources, such as employer-verified work experience and additional non-formal learning formats, could also provide a more comprehensive approach to recognizing prior learning.
Aim/Purpose: This study aims to develop and assess a speed monitoring system that enforces continuous compliance with speed regulations on highways by calculating average vehicle speed between two fixed cameras. Background: Unlike traditional point-based enforcement methods, this approach ensures continuous speed monitoring over an extended distance, reducing the possibility of speed manipulation by drivers. Methodology: The proposed system employs mathematical models to calculate average vehicle speed by considering factors such as acceleration, air resistance, and environmental road conditions. To assess its performance, a computer-based simulation was conducted, simulating vehicle movements across a predefined highway segment. The simulation incorporated various driving behaviors and environmental conditions to evaluate the system's accuracy and reliability in detecting speed violations. Due to resource constraints and ethical considerations regarding real-world testing of enforcement systems, this study primarily relies on simulated data, with limitations clearly acknowledged throughout the methodology section. Contribution: This research contributes to the field of intelligent transportation systems by addressing limitations of conventional approaches and leveraging technological advancements to develop more effective interventions for reducing speed-related accidents. Findings: The simulation results demonstrate that the proposed system significantly outperforms traditional point-based enforcement across all key performance metrics, achieving higher measurement accuracy and violation detection rates. Recommendations for Practitioners: Transportation authorities should consider implementing average speed enforcement systems on highways with high accident rates, as they promote more consistent driving behavior and eliminate the "kangaroo effect" commonly observed with point-based enforcement. Recommendation for Researchers: Future research should focus on field implementation and validation, advanced vehicle identification methods, behavioral impact studies, and integration with emerging vehicle technologies. Impact on Society: By encouraging consistent compliance with speed limits, the system could significantly reduce speed-related accidents and fatalities, alleviate pressure on emergency medical services, decrease fuel consumption and emissions, and promote equitable enforcement. Future Research: Further investigation is needed into real-world implementation, enhanced vehicle identification techniques, long-term behavioral impacts, integration with connected vehicle technologies, and comprehensive cost-benefit analyses.
Aim/Purpose: To design and validate a knowledge management model to improve business performance in knowledge-based enterprises (KBEs). Background: In recent years, KBEs have become essential drivers of economic development, particularly in Iran. These enterprises face unique challenges, such as intense competition and limited access to advanced knowledge management practices. Addressing these challenges through effective management models is critical for enhancing their performance. This study aims to design and validate a knowledge management model tailored to the specific needs of KBEs in Iran, fostering improved business performance and competitiveness. Methodology: This research adopts an exploratory mixed-methods approach, integrating both qualitative and quantitative techniques. The qualitative phase involved in-depth interviews with 21 managers from knowledge-based enterprises in Iran, selected through theoretical sampling. In the quantitative phase, data were collected from 140 experts from these enterprises, chosen using simple random sampling. Data collection was carried out via interviews and questionnaires. The qualitative data were analyzed using grounded theory methodology, while the quantitative data were analyzed using Partial Least Squares (PLS) analysis to validate the proposed knowledge management model. Contribution: This study is the first of its kind in Iran to develop a knowledge management model specifically designed for knowledge-based enterprises and to evaluate its impact on business performance. The results offer valuable insights for policymakers and managers, enabling them to refine competitive strategies and foster sustainable growth. Furthermore, the study introduces a validated paradigmatic model of knowledge management, underscoring its pivotal role in enhancing business performance across financial, marketing, innovation, and social domains. Findings: The findings indicate that the implementation of the knowledge management model can significantly improve the performance of knowledge-based enterprises in Iran. This model focuses on enhancing knowledge repositories, streamlining business processes, and strengthening competitive capabilities. Key factors influencing knowledge management include managerial leadership, knowledge workers, a knowledge-oriented culture, and organizational learning. The knowledge management infrastructure in these enterprises acts as a foundational element, while business support factors and environmental uncertainty serve as mediating variables. Recommendations for Practitioners: Organizations should prioritize the development of robust knowledge management infrastructures to enhance business performance. This includes fostering a knowledge-driven culture, investing in collaborative tools, and ensuring effective leadership to create sustainable competitive advantages. Recommendation for Researchers: Future research should investigate the integration of knowledge management strategies in diverse organizational contexts and evaluate their long-term effects on innovation. Exploring how these practices contribute to organizational agility and resilience is also recommended. Impact on Society: The findings highlight the pivotal role of knowledge management in driving societal and organizational progress, particularly in knowledge-driven economies. By optimizing knowledge flow, organizations can contribute to sustainable development and address complex societal challenges. Future Research: Further research should explore the impact of emerging technologies, such as artificial intelligence (AI) and machine learning, on the enhancement of knowledge management practices. Investigating their potential to automate knowledge processes, optimize decision-making, and facilitate real-time knowledge sharing will be crucial for advancing the field. Additionally, examining the ethical implications of integrating these technologies into knowledge management systems represents a critical area for future inquiry.
Aim/Purpose: Automation of information extraction from digitized complex documents that contain both printed and handwritten text (as well as non-textual information) is one of the actual problems in the digital transformation of public administration. This study proposes an ML-based approach to improve the quality of automated extraction and processing of numerical data from digitized documents with handwritten digits using optical character recognition technology. Background: Currently, in public institutions in Ukraine, manual intervention is a bottleneck in the process of extracting numerical data from digitized documents and subsequent processing. New approaches to automating these processes are needed. Methodology: The methodology includes preprocessing of the document image, segmentation and classification of handwritten digits, conversion of the extracted digits into a date format with the possibility of their validation, and performing necessary calculations based on the extracted numerical information. First, handwritten digits from scanned images of document pages are segmented, then they are preprocessed and sent for recognition with a module based on convolutional neural networks. The image preprocessing steps consisted of binarization, application of a Gaussian filter to remove noise, and use of the Hough transform to correct the document’s skew angle. A CNN model was used to perform character-by-character classification for the recognition of segmented digits. Contribution: The study addresses current limitations in the extraction of handwritten digits from complex document images. The segmentation technique utilizes morphological transformations such as erosion and dilation, as well as the connected components method. The study explored different architectures with convolutional neural networks to determine the optimal hyperparameter configuration. The research findings confirm the importance of integrating methods to ensure effective image preprocessing, segmentation, and recognition of extracted digits. Findings: Experimental results demonstrate that the proposed approach decreases the processing time by a factor of 7.7 and increases the accuracy of numerical data recognition on pages containing fragments of handwritten digits. This indicates that operational tasks are completed with higher accuracy and efficiency. Recommendations for Practitioners: Software may be developed based on this research and implemented in the Pension Fund of Ukraine to automate the processing of digitized documents to determine service lengths and calculate the amount of pension to be awarded. The solution makes it possible to eliminate manual intervention in the process of data extraction and processing. Recommendation for Researchers: The study showed high accuracy in recognizing individual handwritten digits – 99.68% with the training data and 99.55% with the test data. However, the accuracy of recognition is lower if complex documents contain both handwritten and printed text as well as non-textual information. This is due to the complexity of segmenting handwritten characters, which requires further research to identify more effective methods for preprocessing and segmentation. Impact on Society: The proposed methodology allows a significant reduction of human factors in the process of extracting data from digitized documents, accelerating their processing and increasing the efficiency of government institutions. Future Research: Further research may further explore the areas of automated processing of digitized documents, especially in other branches of the state administration, taking into account the specifics of data extracted for further processing.
Aim/Purpose: Despite the necessity of ensuring that reliable and recent information for economic development, particularly agriculture, is accessed and shared, the information found on websites related to agricultural topics requires assessment to ensure that only accurate information is shared with stakeholders within the maize industry in Tanzania. A rigorous tool for assessing the quality, accuracy, reproducibility, value, and use of agricultural information on the web is needed to ensure that web agriculture information can be meaningful to users. This study was undertaken to design a tool that can be used to assess the quality of agricultural information on the web. Methodology: This study employed an interpretive qualitative case study design. The qualitative data collection involved the design of the Web Agricultural Information Quality Evaluation Tool, in which data was collected through literature analysis and interviews. Thematic analysis was the main method of data analysis, where a literature review and data from interviews were used to identify themes that may be included in quality information evaluation tools for the maize industry in Tanzania. The Web Agricultural Information Quality Evaluation Tool has two main parts. Part A is the fundamental information quality criteria, which include authority and timeliness. Part B relates to the relevancy and completeness of the agricultural information on the web. Findings: The findings revealed that authority, timeliness, relevancy, and completeness are the key information quality criteria for assessing the quality of web agricultural information related to the maize industry. Impact on Society: The value of the Web Agricultural Information Quality Evaluation Tool is that it assists stakeholders involved in the agriculture value chain to assess the quality of information available on the web to ensure that timely, trustworthy, and accurate information is used to ensure the sustainability of the maize industry. Future Research: The research is based on the first three components of the analysis, design, development, and evaluation framework (ADDIE) model. Further research on the implementation and evaluation is needed to assess the relevance of the tool, specifically related to the maize industry and other agricultural sectors.
