Publication Search

Recommender systems play a critical role in shaping user decisions across digital platforms; however, the increasing complexity of recommendation algorithms has raised serious concerns regarding transparency, trust, and accountability. This study focuses on enhancing the transparency of recommender systems by integrating Explainable Artificial Intelligence (XAI) techniques within a MovieLens-based recommendation framework. The primary problem addressed is the opacity of conventional recommendation models, which limits user understanding of why certain items are recommended and may reduce trust, perceived fairness, and system acceptance. Accordingly, the main objective of this research is to design and evaluate a hybrid explainable recommender system that balances predictive accuracy with human-understandable explanations. The proposed approach combines Matrix Factorization, feature-importance-aware neural networks, and knowledge graph embeddings to construct a robust recommendation model. To enhance explainability, multiple XAI strategies are integrated, including model-agnostic methods (LIME, SHAP, and CLIME), argumentation-based explanations, and context-aware personalized explanations. A comprehensive evaluation framework is employed, incorporating algorithmic metrics (accuracy, fidelity, robustness, counterfactual consistency, and fairness) alongside human-centered evaluations measuring trust, transparency, cognitive load, and perceived usefulness. Experimental results demonstrate that the knowledge graph–enhanced hybrid model achieves superior recommendation accuracy compared to baseline approaches. Moreover, context-aware explanations consistently outperform other methods in terms of fidelity, robustness, and user-perceived transparency, while argumentation-based explanations are found to be the most persuasive. CLIME offers a strong balance between technical stability and interpretability. The findings indicate that no single explainability technique is universally optimal; instead, hybrid and adaptive explanation strategies are most effective. In conclusion, this study confirms that human-centered, context-adaptive XAI significantly improves transparency and user trust in recommender systems, highlighting explainability as a fundamental component rather than an optional enhancement.

Diseases in primary health services exhibit complex spatial-temporal dynamics due to urbanization and population mobility. Conventional surveillance approaches are difficult to capture these patterns adaptively. Machine learning (ML) based on spatio-temporal modeling offers a solution with the ability to detect disease clusters automatically and with high precision. Research Objectives: This research aims to develop a machine learning model to detect disease hotspots from primary service data in Indonesia, with a focus on improving prediction accuracy, interpretability, and relevance of health policies. Methodology: The primary service dataset for 2024 (5,343 entries) was analyzed using three ML models Gradient Boosting Machine (GBM), Temporal Random Forest (TRF), and Multi-EigenSpot with spatial (village) and temporal (week, month) features. Performance evaluation includes predictive (AUC, F1-score) and spatial (Moran's I, Spatio-Temporal Correlation Index) metrics. Results: The results showed that Multi-EigenSpot achieved the best performance (AUC=0.91; F1=0.86), with the detection of dominant hotspots in Sungai Asam and Beringin Villages. Moran's I value of 0.63 indicates a strong spatial autocorrelation, while STCI=0.57 indicates moderate temporal stability. Conclusions: ML-based spatio-temporal models are effective in identifying hidden disease patterns and have the potential to be integrated into national digital surveillance systems. This approach supports precision public health by providing a scientific basis for real-time location- and time-based intervention policies.

End-to-end autonomous driving has emerged as a promising paradigm in which deep neural networks directly map raw visual inputs to continuous control actions. Despite its effectiveness, this approach suffers from limited transparency, posing significant challenges for deployment in safety-critical driving scenarios. This study addresses the lack of interpretability in vision-based end-to-end autonomous driving systems and aims to analyze model decision-making behavior under critical conditions such as sharp steering maneuvers and abrupt control transitions. To this end, an explainable end-to-end autonomous driving framework is proposed, combining a convolutional neural network trained via imitation learning with gradient-based visual attribution techniques, including Grad-CAM. The model predicts continuous steering, throttle, and braking commands directly from front-facing camera images, while explainability mechanisms are applied to reveal input regions influencing each control decision. Model performance is evaluated using both prediction accuracy and safety-oriented behavioral metrics. Experimental results show that the proposed explainable model achieves lower control prediction errors compared to a baseline end-to-end CNN, reducing steering mean squared error from 0.034 to 0.031, throttle error from 0.021 to 0.019, and brake error from 0.018 to 0.016. Moreover, safety-oriented analysis indicates improved driving stability, with steering variance reduced from 0.087 to 0.072 and abrupt control changes decreased from 14.6 to 10.3 events. Visual explanations consistently highlight road surfaces and lane-related structures during complex maneuvers, indicating reliance on semantically meaningful cues. In conclusion, the results demonstrate that integrating explainability into end-to-end autonomous driving not only preserves predictive performance but also correlates with smoother and more stable driving behavior. This framework contributes to the development of transparent and trustworthy autonomous driving systems suitable for safety-critical applications

Abstract: The rapid diffusion of Generative Artificial Intelligence (AI) has intensified public debate regarding its benefits, risks, and societal implications. This study investigates public sentiment and thematic structures surrounding Generative AI by analyzing Twitter discourse as a representation of large-scale, real-time public perception. The research addresses two main problems: how public sentiment toward Generative AI is distributed and what dominant themes shape this perception. Accordingly, the objective is to map both emotional polarity and thematic narratives embedded in social media conversations. A computational mixed-methods approach was employed using a dataset of 12,470 tweets collected on 17 December 2024. Sentiment classification was conducted using a transformer-based DistilBERT model, while semantic representations were generated with Sentence-BERT. Topic modeling was performed using BERTopic, integrating HDBSCAN clustering and class-based TF-IDF to extract coherent and interpretable topics. Human-in-the-loop validation supported the interpretive robustness of topic labeling. The findings reveal that public sentiment toward Generative AI is predominantly positive (41.8%), particularly in relation to productivity enhancement, education, and creative applications. Neutral sentiment (31.4%) reflects informational discourse, while negative sentiment (26.8%) centers on ethical concerns, privacy risks, misinformation, and AI hallucinations. Seven dominant topics were identified, with clear topic–sentiment alignment showing optimism in utility-driven themes and skepticism in ethics- and risk-related discussions. In conclusion, public perception of Generative AI is dualistic—characterized by strong enthusiasm alongside persistent caution. These results provide empirical insights for AI governance, responsible innovation, and future research on socio-technical impacts of Generative AI. *    

: The rapid expansion of cybersecurity standards and threat intelligence frameworks has led to significant semantic fragmentation among security terminologies, hindering effective information retrieval and interoperability across systems. Traditional keyword-based search approaches are inadequate for capturing the contextual meaning of security terms, particularly within formal frameworks such as NIST, MITRE ATT&CK, and CWE. This study addresses this challenge by proposing CyberBERT, a transformer-based semantic search framework designed to align cybersecurity terminologies through deep contextual representation and ontology-driven reasoning. Research Objectives: The primary objective of this research is to develop a semantic retrieval model capable of understanding conceptual relationships between security terms beyond lexical similarity. Methodology: The proposed methodology fine-tunes a BERT-based model on the NIST Glossary corpus using a combination of masked language modeling and triplet loss objectives to generate discriminative semantic embeddings. These embeddings are further aligned with cybersecurity ontologies, including MITRE ATT&CK and CWE, to enhance semantic consistency and explainability. Semantic retrieval is performed using cosine similarity within a 768-dimensional embedding space and evaluated using Mean Reciprocal Rank (MRR) and Precision@K metrics. Results: Experimental results demonstrate that CyberBERT achieves an MRR of 0.832, outperforming domain-adapted baselines such as SecureBERT and CyBERT. The integration of ontology alignment improves semantic accuracy by over 6%, while robustness evaluations confirm resilience against adversarial linguistic perturbations. Visualization using t-SNE reveals coherent semantic clustering aligned with the five core NIST Cybersecurity Framework functions. Conclusions: In conclusion, CyberBERT effectively bridges semantic gaps across cybersecurity terminologies by combining transformer-based contextual learning with ontological reasoning. The framework offers a robust, interpretable, and scalable solution for semantic search, supporting improved interoperability and knowledge discovery in cybersecurity operations and standards harmonization.

Low Birth Weight (LBW) remains a critical global health issue that significantly contributes to neonatal morbidity and mortality, particularly in developing countries such as Indonesia. The main challenge in addressing LBW lies in its complex and multifactorial risk profile, which involves biological, social, environmental, and healthcare-related determinants. This study aims to analyze and synthesize the risk factors associated with LBW based on recent scientific literature. A literature review method was applied by searching articles from Portal Garuda, DOAJ, PubMed, and Google Scholar published between 2020 and 2025 using relevant keywords. The findings indicate that maternal age, interpregnancy interval, nutritional status, anemia, preeclampsia, infections, socioeconomic conditions, environmental exposure, and the quality of antenatal care are significant determinants of LBW. The synthesis of evidence confirms that LBW is influenced by the interaction of multiple individual and healthcare system factors rather than a single cause. In conclusion, this study highlights the urgent need to strengthen antenatal care services, improve maternal nutritional status, control maternal diseases during pregnancy, and implement community-based promotive and preventive strategies as key efforts to reduce the incidence of LBW.

Abortion remains a complex reproductive health issue due to the interplay of multiple interrelated determinants. This study aimed to map the factors influencing the incidence of abortion based on recent scientific evidence. A literature review design was applied by analyzing ten selected articles published within the last five years and retrieved from major scientific databases. The selection process was conducted systematically through title, abstract, and full-text screening based on predefined inclusion criteria. The extracted data included study characteristics, type of abortion, examined determinants, and key conclusions. The synthesized findings indicate that abortion incidence is shaped by a combination of biological, social, and healthcare system related factors. Clinical determinants such as maternal age, endocrine disorders, uterine anatomical abnormalities, obstetric history, anemia, and hypertension play a substantial role in spontaneous and recurrent miscarriage. In contrast, structural factors including income level, contraceptive access, and legal regulations predominantly influence induced abortion. The discussion highlights that abortion should not be viewed as an isolated clinical event, but rather as the cumulative outcome of risks operating across multiple levels of influence. In conclusion, abortion represents a multifactorial phenomenon that requires comprehensive prevention strategies extending beyond medical interventions alone. These strategies should also address healthcare accessibility and broader social conditions. This review contributes to a deeper understanding of the complexity of abortion determinants and provides an evidence-based reference for developing more effective preventive approaches in the future.

Intellectual Property Rights (IPR) have the potential to be recognized as an object of Rahn Tasjily collateral because they meet the criteria of property that can be transferred in accordance with the principles of muamalah in Islamic banking. However, its implementation faces legal challenges, particularly related to the dualism between the provisions of Fiduciary Guarantee (UUJF), which contains potential riba and gharar, and the DSN-MUI Fatwa No. 68/2008, which rejects such non-Sharia elements. This study aims to analyze the position of IPR as marhun according to the principles of muamalah and to identify substantial barriers in its application in Islamic Financial Institutions (LKS), particularly in the aspects of valuation and execution. The method used is normative law with an approach to regulations and concepts, analyzed descriptively and qualitatively using secondary data. The study concludes that the conflict between UUJF and Rahn Tasjily, the high risk of gharar in valuation, and the delays in execution due to the Constitutional Court's decision, highlight the urgent need for OJK and DSN-MUI to issue technical regulations to harmonize and mitigate risks in accordance with Sharia principles.

This research examines the legal vulnerability of Foundation assets whose land title certificates (SHGB) are still registered under the name of the founder or management, which can lead to disputes after the founder's death. The case of Vihara Thien En Thang reflects this issue, where conflict arose when the founder's heirs claimed the land as part of the inheritance. Through false statements, they successfully issued a Replacement HGB Certificate, while the original certificate was still held by the Foundation. The main objective of this research is to analyze the legal status of the deed of gift made by the founder to the Foundation and the legal implications of issuing the Replacement HGB Certificate based on false data. This study uses a normative legal method (juridical normative), with a statute approach and conceptual approach. Secondary data, consisting of primary, secondary, and tertiary legal sources, was collected through literature study and analyzed descriptively and qualitatively. Thus, this research aims to provide an understanding of its vulnerabilities and offer recommendations for protecting the legitimate assets of the Foundation.

Global environmental challenges require active engagement from all sectors, including education. For Muslim youth, awareness of environmental sustainability aligns with Islamic ethical principles such as stewardship (khalifah), justice (ʿadl), and social welfare (maslahah). This study examines the influence of green economy education within Islamic higher education on students’ eco-literacy, ethical awareness, and sustainable economic behavior. A quantitative approach was employed using a structured questionnaire distributed to students from both Islamic economics and non-economics programs. Data were analyzed with descriptive statistics, independent t-tests, and one-way ANOVA to identify differences in environmental knowledge, attitudes, and behavior. Findings show that students with an Islamic economics background consistently achieve higher scores in knowledge, attitudes, and behavioral engagement related to sustainability compared to non-Islamic economics students. Integrating Islamic ethical values into the curriculum provides a holistic framework for internalizing sustainability principles, encouraging students to translate ethical knowledge into practical action. Pedagogical strategies such as project-based learning, reflective exercises, and experiential programs further enhance engagement and eco-conscious behavior. The study highlights the critical role of Islamic education in fostering a generation of ethically aware and environmentally responsible students. By embedding moral and ecological principles in academic programs, educational institutions can strengthen students’ capacity for sustainable decision-making and support broader goals of responsible economic and environmental stewardship.

This research investigates integrated maritime workforce resilience and mental health management frameworks addressing post-pandemic seafarer wellbeing challenges and organizational safety culture transformation. Through qualitative analysis involving 39 stakeholders including seafarers, ship operators, mental health professionals, maritime unions, training institutions, and maritime authorities, this study examines how COVID-19 pandemic intensified mental health crises through extended contracts, shore leave restrictions, and isolation while exposing systemic inadequacies in psychological support systems. Results demonstrate that comprehensive mental health frameworks can reduce psychological distress by 55-70%, improve safety performance by 40-55%, enhance crew retention by 45-60%, and decrease incident rates by 35-50% when integrating organizational culture change, leadership competency development, predictive analytics, and culturally-adapted interventions. Key challenges include mental health stigma (affecting 65-80% of seafarers), limited organizational investment (only 18-25% adequate), service accessibility gaps, and workforce demographic diversity requiring culturally-sensitive approaches. Findings reveal that effective mental health management requires systemic organizational transformation integrating psychological wellbeing into safety management systems, work design optimization, family support programs, and career sustainability rather than treating mental health as peripheral welfare concern, supporting maritime industry's workforce retention and operational safety imperatives.

Prelabor rupture of membranes (PROM) remains one of the most frequently encountered obstetric complications and continues to contribute substantially to maternal and neonatal morbidity and mortality. Numerous factors have been associated with PROM; however, the available evidence presents considerable variation, highlighting the need to re-evaluate these determinants using recent empirical findings. This review aims to identify and synthesize the principal factors influencing PROM based on ten studies published within the last five years. A systematic search was conducted across PubMed, Scopus, Web of Science, and Google Scholar using predefined keywords, followed by screening through established eligibility criteria. Relevant data from each study including study design, geographical setting, assessed risk factors, and statistical outcomes such as odds ratios or relative risks  were extracted and compared. The review indicates that reproductive and urinary tract infections, inadequate nutritional status, high-risk obstetric history, and short interpregnancy intervals consistently emerge as major determinants. Social factors and the quality of antenatal services were also shown to heighten the likelihood of PROM. Overall, the findings emphasize that PROM arises from a combination of medical and non-medical influences, reinforcing the need for preventive strategies that adopt a comprehensive and integrated approach.

The integration of cloud computing and data security systems is vital for the operational success and competitiveness of fintech startups. Cloud computing enables these startups to scale quickly, manage resources efficiently, and reduce infrastructure costs, making it an indispensable tool for businesses in the rapidly evolving fintech sector. However, with the benefits come significant challenges, particularly in data protection and cybersecurity. As fintech services handle sensitive financial data, ensuring robust security measures such as encryption, access controls, and continuous monitoring is crucial to maintaining user trust. Furthermore, regulatory compliance, both local and global, adds complexity to the data protection strategies of fintech companies. This research explores the key factors that drive cloud adoption in fintech, the security challenges associated with cloud environments, and the strategies implemented by startups to address these challenges. Interviews with IT managers from Indonesian fintech startups reveal that while cloud computing offers scalability and cost-effectiveness, issues like compliance with local regulations and the protection of sensitive data remain major concerns. The research suggests that fintech startups should invest in both cloud infrastructure and advanced cybersecurity measures to protect their operations and customer data. Additionally, creating a comprehensive roadmap for regulatory compliance and fostering partnerships with cybersecurity firms will help mitigate risks and ensure long-term success. The findings highlight the importance of integrating cloud computing with effective security strategies to navigate the complex regulatory and security landscape of the fintech industry.

This study analyzes the effect of Bitcoin prices, the LQ45 Index, mutual fund net asset value (NAV), and the net profit margin (NPM) of gold mining companies on the price of gold as a safe haven asset within the context of the Indonesian financial market. Gold is often seen as a safe haven asset that is the primary choice of investors when economic uncertainty increases, but the relationship between gold and various other investment instruments still requires further study. This study uses a multiple linear regression method with a robust standard errors approach to analyze 420 monthly and quarterly data observations during the 2018-2022 period. The results of the study found that the price of Bitcoin and the NPM of gold mining companies had a significant positive influence on the price of gold, while the LQ45 Index had a significant influence effect. Meanwhile, the NAV of mutual funds showed a significant positive influence that was not in line with the initial hypothesis. These findings indicate that gold does not always function absolutely as a safe haven asset, as its role is contextual and still influenced by the dynamics of other investment instruments such as digital assets, stock markets, and mutual funds. The study's results make an important contribution to financial literature by proving that the safe haven characteristics of gold are complex and dynamic, so investors need to consider various factors and market conditions before allocating investments to gold as a hedging strategy in their portfolios.

The current practice of Islamic Religious Education (PAI) learning in schools still faces the challenge of the dominance of conventional methods that tend to be teacher-centered, so that the aspect of internalization of values by students is often not optimal . This article aims to describe the characteristics and conceptual relationships between the Social Interaction and Personal learning models in the context of PAI, while also examining the relationship between the two models with constructivist and humanistic learning theories . Through a literature study, the analysis shows that the Social Interaction model based on constructivist theory emphasizes the construction of knowledge through group dynamics, collaboration, and social interaction . Meanwhile, the Personal model based on humanistic theory is oriented towards the development of individual potential, self-awareness, and spiritual reflection . The results of the study conclude that the integration of these two models offers a holistic learning approach, where students not only understand PAI material cognitively, but are also able to actualize religious values through real social experiences and deep personal appreciation .

This study investigates the role of higher education institutions (HEIs) in strengthening social entrepreneurship ecosystems in Malang Raya, Indonesia. Using an explanatory sequential mixed-method design, quantitative data were collected from 100–150 respondents representing key ecosystem actors, including faculty members, students, social entrepreneurs, supporting institutions, and government stakeholders. Quantitative data were analyzed using Structural Equation Modeling (SEM) with LISREL software, while qualitative data from 15–25 key informants were analyzed thematically through in-depth interviews and focus group discussions (FGD). The study integrates Resource-Based View (RBV), Triple Helix Model, and Social Capital Theory to develop a comprehensive framework. Findings demonstrate that HEIs significantly influence ecosystem sustainability, although some relationships show non-significant effects due to external factors and institutional readiness. The study recommends implementing collaborative strategies based on the triple helix model and strengthening social capital to enhance the social entrepreneurship ecosystem. This research contributes to advancing community-based entrepreneurship theory and provides practical implications for policymakers and institutional leaders in Indonesia.

This study investigates the impact of intrinsic motivation, workload, and competence on job satisfaction, exploring its implications for employee performance, with job satisfaction serving as a mediating variable. A quantitative approach was employed, utilizing Partial Least Squares Structural Equation Modeling (PLS-SEM) for data analysis collected via questionnaires. The results reveal that intrinsic motivation has a positive but insignificant impact on job satisfaction and performance. Workload significantly improves job satisfaction but does not affect performance, while competence significantly enhances both job satisfaction and performance. Additionally, job satisfaction positively affects employee performance. The mediation analysis reveals that job satisfaction mediates the relationship between competence and workload on performance, but does not mediate the relationship between intrinsic motivation and performance. These findings highlight the critical roles of competence and job satisfaction in improving employee performance, suggesting that intrinsic motivation and workload may require additional factors, such as compensation and work environment, to be more effective.

This study examines the factors influencing Indonesia’s motor vehicle exports to nine developing countries using the gravity model approach with long-term and short-term panel data. The variables analyzed include the Gross Domestic Product (GDP) of partner countries, exchange rates, economic distance, and trade cooperation agreements. The data are analyzed using the Error Correction Model (ECM) to capture short-term dynamics and long-term relationships. The long-term results show that partner countries’ GDP has a significant positive effect on Indonesia’s vehicle exports, indicating that economic growth in partner countries increases demand for Indonesian automotive products. Conversely, exchange rates and economic distance have significant negative effects, suggesting that depreciation of partner currencies and economic disparities reduce export volumes. Trade cooperation agreements do not have a significant impact in the long term. In the short term, changes in GDP continue to have a significant positive effect, while exchange rates maintain a significant negative impact on exports. Economic distance and trade agreements are not significant in the short term. The significant and negative error correction term (ECT) confirms the existence of an adjustment mechanism toward long-term equilibrium. This study highlights the importance of partner countries’ economic growth and exchange rate stability in supporting Indonesia’s vehicle exports to developing countries, as well as the need to address structural barriers to improve long-term competitiveness.

This study aims to conduct a systematic literature review and bibliometric analysis on Transformational Leadership (TL), based on empirical research. Despite extensive studies on TL in recent decades, comprehensive research remains limited. The methodology used is a Systematic Literature Review (SLR) of articles containing “Transformational Leadership” in the title, abstract, or keywords, sourced from the Scopus database, which yielded 1,297 publications from 1977 to 2025. The data were analyzed using VOSviewer software. The findings suggest that TL is an innovative model in vocational education, bridging industrial systems with academic environments for authentic, practice-based learning. However, challenges include limited resources, insufficient instructor training, and inadequate institutional support. Recent innovations, such as advanced ICT, holographic technology for real-time interaction, and digital twins for process optimization, have enhanced the model's effectiveness. The study also discusses the conceptual framework of TL. This research uses the Scopus database, and future studies could broaden its scope by incorporating other databases like Web of Science. Practically, the study’s findings suggest integrating modern pedagogical strategies, including gamification, simulation, and project-based learning, to enhance student engagement and understanding of manufacturing processes. Socially, it encourages educational institutions to invest in infrastructure, strengthen industry partnerships, and provide continuous instructor training. This study highlights the growing global research on TL and calls for deeper exploration of the topic in existing literature.

This study examines the relationship between market efficiency and digital financial innovation in the context of global financial transformation over the past decade, when fintech, cryptocurrency, and Decentralized Finance (DeFi) have significantly altered price formation and information dissemination mechanisms. The main issue raised is whether the Efficient Market Hypothesis (EMH) theory remains relevant in the face of digital market dynamics characterized by high volatility, speculative behavior, and regulatory uncertainty. The objective of this study is to assess the impact of digital innovation on information efficiency, price transparency, and the stability of modern financial markets. The study used the Systematic Literature Review (SLR) method, examining 15 scientific articles published between 2015 and 2025 from various academic databases. The findings indicate that digital technology increases access and speed of information distribution, but does not always result in consistently efficient markets. Crypto and DeFi markets have been shown to exhibit fluctuating efficiency due to price anomalies, information asymmetry, and weak regulation. Overall, the literature synthesis confirms that market efficiency in the digital era is dynamic and influenced by the interaction between technology, investor behavior, and governance quality. This study concludes that the EMH remains relevant as a basic framework, but needs reinterpretation to suit the complex and rapidly changing characteristics of digital markets.