Aim/Purpose: This study investigates whether partitioning generative data augmentation by recorded failure mechanism improves industrial equipment failure detection, both overall and for each failure mechanism, compared with single-generator augmentation, conventional resampling, and a cost-sensitive baseline. Background: Data-driven maintenance systems learn from operational histories in which failure is rare. Established remedies for this scarcity treat the minority class as one population, yet failures arise from distinct physical mechanisms with distinct sensor signatures. The homogeneity assumption is seldom examined, and its organizational consequence, decision support that systematically underrepresents infrequent failure modes, is seldom measured. Methodology: A leakage-safe comparison of eight strategies on the AI4I 2020 benchmark of 10,000 records, with a failure prevalence of 3.4% and four labeled failure mechanisms. The strategies were a cost-sensitive baseline, random undersampling, SMOTE, SMOTENC, Borderline-SMOTE, ADASYN, single-generator WGAN-GP augmentation, and a failure-type-aware design with one generator per failure mechanism. A Random Forest classifier received the same tuning under every strategy across 30 repeated stratified data splits. PR-AUC is the primary criterion; per-mechanism recall and comparisons at matched operating points are secondary criteria. Contribution: The study treats failure-mechanism labels as codified organizational knowledge and tests whether analytics can use that knowledge to improve failure detection. It demonstrates, through a fair, leakage-safe comparison, that partitioning augmentation by mechanism is no better than a tuned cost-sensitive baseline, and that the value of codified mechanism knowledge lies in revealing the failure modes that decision support misses. Findings: Across 30 repeated splits, the cost-sensitive baseline achieved the highest mean PR-AUC (0.818). The failure-type-aware strategy (0.803) was not significantly different from the baseline or the interpolation-based methods; its advantage over single-generator augmentation (0.770) was consistent but not significant after accounting for dependence between splits. At matched operating points, augmentation offered no benefit over changing the baseline decision threshold, and neither generative strategy improved detection of the rarest mechanism, tool wear. With generator settings fixed in advance instead of tuned, both generative strategies performed worse. Once its settings were fixed, the failure-type-aware strategy required approximately 200 times the computation of the baseline per split, in addition to a one-time search of about four hours. Recommendations for Practitioners: Before investing in generative augmentation, tune a cost-sensitive model and set its decision threshold according to the local cost of a missed failure relative to an unnecessary inspection; in this study, that combination matched every augmentation strategy at a small fraction of the computational cost (around 3 seconds per model build versus around 9 minutes for the failure-type-aware strategy, after a one-time search of about four hours). If failure mechanisms are documented, use them to evaluate detection for each mechanism, as overall scores may mask poorly detected failure modes. This study did not estimate the economic return of recording mechanisms. Recommendation for Researchers: Comparisons of imbalance strategies should include a tuned cost-sensitive baseline with an adjusted decision threshold, and all strategies should receive the same tuning. Studies should compare strategies at matched operating points and across repeated data splits, with tests that account for dependence between splits. They should report the composition of the minority class and evaluate results for each subtype. Impact on Society: Unplanned industrial downtime carries costs in energy, materials, and worker safety. Detection systems that miss infrequent failure mechanisms concentrate those costs on events organizations are least equipped to handle; evaluating detection for each failure mechanism makes these blind spots apparent. Future Research: Evaluation on operational maintenance records with partial or noisy mechanism labels; comparison of partitioned generation with a label-conditioned generator of matched capacity and with tabular diffusion models; assessment of the fidelity and memorization of synthetic records; and evaluation against explicit maintenance cost models.
Aim/Purpose: This study aims to identify and prioritize the determinants of Healthcare Service Robotics (HSR) adoption that are most relevant to Saudi public healthcare. A PRISMA-guided review is used as preparatory evidence mapping, followed by expert-based contextual prioritization, thereby moving beyond the re-identification of generic IT adoption factors. Background: Modern healthcare systems have been using Healthcare Service Robotics (HSR) as a significant enabler of operational efficiency, safer service delivery, and improved quality of care. Despite extensive research on information technology and innovation adoption, evidence on determinants of HSR adoption remains fragmented across healthcare, robotics, artificial intelligence-enabled services, and information systems. This issue is particularly relevant to Saudi public healthcare, where digital health transformation under Vision 2030 increases the need for context-sensitive evidence on organizational readiness, workforce acceptance, and secure technology integration. Methodology: This study adopted a systematic literature review (SLR) based on PRISMA guidelines in the initial stage, which involved preparatory evidence mapping. The study synthesized 75 peer-reviewed publications from 2019 to 2024, yielding 59 potential determinants and adoption-related outcomes. The factors were then assessed by 19 panel experts using a structured single-round rating protocol. Each factor’s contextual importance was rated by the experts on a five-point Likert scale, with those obtaining mean scores of 3.50 or higher retained. This eventually resulted in 14 critical factors. Contribution: The study contributes by distinguishing preparatory evidence synthesis from expert-based contextual prioritization, refining UTAUT, TOE, and DOI constructs into a Technology-Organization-People (TOP) taxonomy, separating adoption determinants from outcomes, and offering a decision-oriented framework for HSR implementation in Saudi public healthcare. Findings: Performance expectancy, facilitating conditions, effort expectancy, and privacy and security emerged as the highest-priority antecedents, while job security concerns ranked comparatively lower. Recommendations for Practitioners: The framework supports policymakers and hospital leaders in prioritizing infrastructure readiness, demonstrable performance benefits, usability, and data-governance safeguards before wider HSR deployment. Recommendation for Researchers: Future empirical studies should therefore test the proposed framework using quantitative methods such as structural equation modeling and should distinguish antecedents from adoption outcomes when specifying the model. Impact on Society: By identifying the factors that experts consider most important for HSR implementation, the study provides a basis for more structured planning of robotic technologies in public healthcare. Attention to performance benefits, infrastructure readiness, usability, privacy and security, and staff preparedness may help healthcare institutions introduce HSR in ways that are better aligned with service quality, operational requirements, and patient-related safeguards. Future Research: Future studies can address these limitations and advance the field of study by focusing on three major directions, the first of which is the use of the identified 14 critical factors as independent variables in a large-scale study of a quantitative nature for the statistical measurement of the factors’ influence on behavioral intention towards HSR adoption and use. Another way to address the limitations of this study in future research is to conduct comparative analyses of public and private healthcare institutions to examine how organizational contexts, such as hospital size and top management support, vary across sectors. Lastly, future studies may use longitudinal designs to examine how these factors change over time as nurses become accustomed to using robotic systems in their day-to-day work.
Aim/Purpose: This study develops and empirically validates an integrative multi-theoretical model of Metaverse adoption among retail SMEs by combining Institutional Theory, the Technology-Organization-Environment (TOE) framework, and the Knowledge-Based View (KBV). It further distinguishes the moderating roles of potential and realized absorptive capacities in explaining how institutional, technological, organizational, and environmental drivers translate into intentions to adopt the Metaverse and perceived enhanced performance. Background: Existing Metaverse adoption research remains fragmented, with most studies examining isolated technological, organizational, or behavioral determinants and giving limited attention to SMEs and emerging-market contexts. Such single-theory approaches provide only a partial explanation of a complex organizational adoption process. Addressing this limitation, this study integrates complementary theoretical perspectives to capture external institutional pressures, technological and organizational conditions, environmental influences, and firms’ knowledge-based capabilities within a unified framework to explain retail SMEs’ adoption of the Metaverse. Methodology: A quantitative cross-sectional survey was conducted between March and May 2025 among employees of retail SMEs operating across different retail subsectors and geographic regions in Jordan. Using convenience sampling, 523 valid responses were obtained and analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). Contribution: The study demonstrates that Metaverse adoption among retail SMEs is best understood as a multidimensional process shaped jointly by institutional pressures, technological and organizational conditions, environmental influences, and knowledge-based capabilities. By integrating Institutional Theory, the TOE framework, and the Knowledge-Based View, and by distinguishing the moderating roles of potential and realized absorptive capacities, the study provides a more comprehensive explanation of how adoption drivers translate into adoption intention and, subsequently, perceived performance gains. The findings extend existing technology-adoption research by showing that SMEs’ ability to acquire, assimilate, transform, and exploit knowledge is critical to converting Metaverse opportunities and external pressures into meaningful organizational outcomes. Findings: The findings show that coercive, normative, and mimetic pressures, relative advantage, digital leadership, Metaverse vendors’ support, and consumer Metaverse literacy significantly increase SMEs’ intention to adopt the Metaverse. In contrast, compatibility and organizational readiness exert significant negative effects. Metaverse adoption intention strongly enhances perceived performance. Potential absorptive capacity strengthens most institutional, technological, organizational, and environmental adoption relationships, except those involving coercive isomorphism and compatibility, while realized absorptive capacity strengthens the relationship between adoption intention and perceived enhanced performance. Recommendations for Practitioners: Retail SMEs should approach Metaverse adoption as a strategic organizational initiative rather than a purely technological investment. Managers should strengthen digital leadership, organizational readiness, vendor collaboration, and customer-oriented digital capabilities while developing both potential and realized absorptive capacities. This will enable firms to recognize better and assimilate relevant Metaverse knowledge, translate it into effective implementation practices, and convert adoption intentions into improved organizational performance. Recommendation for Researchers: Researchers are encouraged to further examine Metaverse adoption across industries, countries, and organizational contexts using longitudinal and mixed-methods approaches. Impact on Society: The study highlights the potential of Metaverse technologies to enhance digital transformation, innovation, competitiveness, and sustainable economic growth among SMEs. Future Research: Future studies should investigate additional moderating variables, sector-specific applications, and the long-term organizational and societal implications of Metaverse adoption.
Aim/Purpose: This study addresses the challenge of converting large volumes of unstructured online energy discussions into interpretable aspect-level knowledge without manual annotation. Background: Indonesian public energy discussions provide useful information about issue salience and evaluative judgments. However, they are often informal, noisy, code-mixed, and difficult to analyze manually. Existing label-free methods typically operate at the topic level and often lack aspect-level outputs that are sufficiently grounded in local evidence and faithful to the text. Methodology: This study proposes a two-stage label-free knowledge discovery pipeline. The first stage extracts aspect terms by combining LDA-based topic representation, multilingual sentence embeddings, autoencoder compression, clustering, evidence-based candidate selection, and contextual part-of-speech filtering. The second stage assigns aspect-level sentiment using opinion lexicons, dependency-distance scoring, negation and intensity handling, pragmatic adjustment, and segment–aspect term pairs. The evaluation includes ablation analysis, baseline comparison, human validation of aspect-term outputs, and evidence-based sentiment auditing. Contribution: This study presents a label-free pipeline for extracting aspect terms and mapping aspect-level sentiment from unstructured public discussion. It distinguishes between mere mentions and those supported by explicit evaluative evidence, thereby capturing both issue salience and evaluative sentiment. Findings: The findings show that effective aspect-term extraction requires a balance among cluster separation, representation quality, textual faithfulness, and linguistic validity. Human validation showed that most sampled aspect-term outputs were contextually valid. The pipeline produced 17,004 aspect-term occurrences, with non-evaluative aspect mentions forming the largest sentiment category at 35.40%. This result indicates that public attention to energy issues often appears without explicit evaluation. Recommendations for Practitioners: Practitioners in energy communication, policy analysis, and public opinion monitoring can use this pipeline to identify which energy issues are merely mentioned and which are explicitly evaluated. The outputs can also help identify aspects that receive support or opposition and monitor changes in public attention and sentiment over time. Recommendation for Researchers: Researchers should develop label-free text analytics that preserve local evidence, support evidence-based labeling, and distinguish mentioned aspect terms from evaluated aspect terms. Future work should strengthen text-grounded aspect-term representations for knowledge discovery. Impact on Society: This study supports the assessment of public energy discussions by transforming unstructured online conversations into evidence-based knowledge. It also enables a more informed interpretation of digital public discourse in the energy domain. Future Research: Future research could improve this framework by incorporating adaptive domain filtering, enhancing the handling of sarcasm and implicit sentiment, conducting multilingual or cross-domain validation, and integrating human-in-the-loop evaluation.
Aim/Purpose: This study proposes a hybrid learner profiling framework that combines behavioral data and semantic analysis based on Large Language Models (LLMs) to build interpretable and actionable learner representations. Background: Existing learning analytics approaches rely primarily on quantitative interaction logs or static self-reports, failing to capture the underlying cognitive and emotional reasons behind learner behaviors. Most existing profiling approaches describe what the learner does, but not why they behave in a certain way. Methodology: The framework relies on two complementary pillars. The first analyzes data from virtual learning environments (VLEs). The second uses an LLM as a semantic annotator to extract cognitive, self-regulatory, and emotional dimensions from learners’ textual outputs. The approach was validated using real-world offline datasets and synthetic pedagogical archetypes. Contribution: This work contributes a multidimensional learner representation that bridges the gap between observable interaction logs and unobservable internal states. Findings: The behavioral profiling module achieved a dropout prediction AUC of 0.871. Semantic annotation showed no correlation between cognitive complexity and emotional tone (r = 0.00). In controlled validation, planning cues were detected in 92.3% of valid Strategist messages, compared with 0-16.7% of messages from the other archetypes. Recommendations for Practitioners: Researchers should treat learner profiling as a multidimensional and partially latent construct requiring complementary data sources. Recommendation for Researchers: Researchers should consider learner profiling as a multidimensional and partially latent construct, combining multiple data sources rather than relying solely on easily accessible interaction logs. Impact on Society: This framework helps educational organizations reduce dropout rates and improve the overall quality and inclusivity of digital learning environments. Future Research: Future developments will focus on deploying the framework in real-world settings, such as integrating it into a real Learning Management System (LMS) and evaluating its impact on adaptive learning and personalized support.
