Information

16 pages, 618 KB

Open AccessArticle

Effectiveness of a Telemedicine-Based Intervention for Childhood Obesity Management: A Randomized Controlled Trial

by Naporn Uengarporn, Ratsadakorn Yimsabai Maneewong, Nuttha Piriyapokin, Boonyanurak Nantiwattara, Atcha Pongpitakdamrong and Wichulada Kiattimongkol

Information 2026, 17(4), 359; https://doi.org/10.3390/info17040359 - 9 Apr 2026

Abstract

Telemedicine can address access barriers in childhood obesity management by supporting continuity of care and caregiver engagement. This randomized controlled trial compared a telemedicine-based program with guideline-based usual care among 70 children with obesity (aged 5–15 years) and their caregivers, randomized to telemedicine [...] Read more.

Telemedicine can address access barriers in childhood obesity management by supporting continuity of care and caregiver engagement. This randomized controlled trial compared a telemedicine-based program with guideline-based usual care among 70 children with obesity (aged 5–15 years) and their caregivers, randomized to telemedicine (n = 35) or usual care (n = 35) for 6 months. The telemedicine program included online consultations, digital caregiver education, remote monitoring, and secure messaging via the SUTH application integrated with the hospital information system. The control group received standard outpatient care with routine counseling and printed materials; baseline characteristics were similar between groups. Baseline demographic and clinical characteristics were comparable between groups. After 6 months, both groups showed modest reductions in BMI; however, ANCOVA-adjusted analyses indicated no significant between-group difference in post-intervention BMI. Weight-for-height decreased in both groups, with a slightly greater percentage reduction in the telemedicine group. Caregiver satisfaction and knowledge were significantly higher in the telemedicine group at follow-up (all p < 0.01; knowledge p < 0.001). These findings suggest that telemedicine-based care may contribute to modest improvements in anthropometric outcomes while substantially enhancing caregiver knowledge and healthcare service satisfaction, supporting its role as a scalable adjunct in pediatric obesity management. Full article

(This article belongs to the Special Issue Information Technology for Smart Healthcare)

► Show Figures

Figure 1

19 pages, 1310 KB

Open AccessArticle

Security and Safety Education from the Polish Context to Reinforce Social Education at a Time of Global Uncertainty

by Małgorzata Gawlik-Kobylińska, José A. García-Berná, Dorota Domalewska, Andrzej Pieczywok, Peter Holowka and Juan Manuel Carrillo de Gea

Information 2026, 17(4), 358; https://doi.org/10.3390/info17040358 - 8 Apr 2026

Abstract

This study advances the conceptual and practical scope of social education by integrating Security and Safety Education (SSE) categories into its theoretical foundation. We demonstrate that SSE encompasses multidimensional areas highly relevant to social education and offer a structured competence model to guide [...] Read more.

This study advances the conceptual and practical scope of social education by integrating Security and Safety Education (SSE) categories into its theoretical foundation. We demonstrate that SSE encompasses multidimensional areas highly relevant to social education and offer a structured competence model to guide curriculum design. Using a mixed-methods approach, 2926 Web of Science publications were analysed through an NVivo Word Frequency Query to identify key domains associated with security and safety. The temporal scope of the corpus (2019–2021) provides a coherent analytical baseline, capturing intensified security and health-related discourse during the COVID-19 period while preceding geopolitical disruptions that could otherwise distort thematic patterns. The results show that security is associated with broad social and geopolitical issues, including food, political, economic, public, national, and international affairs, as well as health and information. In contrast, safety is mainly linked to transport-related concerns, although both domains converge in areas such as health, social, public, national, and information matters. These findings indicate that SSE encompasses multidimensional areas relevant to social education. To support curricular integration, we propose an eMEDIATOR-derived competence model that structures SSE content into measurable, outcomes-based components. Ultimately, this research provides actionable tools to elevate social education and promote active, informed citizenship in times of global uncertainty. Full article

(This article belongs to the Special Issue Advancing AI Applications in Education and Engineering: A Multidisciplinary Perspective)

► Show Figures

Graphical abstract

16 pages, 3754 KB

Open AccessArticle

Lean Implementation in Singapore: A Survey in SMEs of the Precision and Electronics Manufacturing Industry

by Yeoh Keat Chin, Pedro Alexandre De Albuquerque Marques and Arlindo Silva

Information 2026, 17(4), 357; https://doi.org/10.3390/info17040357 - 8 Apr 2026

Abstract

This study examines how lean manufacturing practices are adopted in Singapore’s SME precision and electronics manufacturing industry. Its main goal is to assess the extent of lean manufacturing method adoption and the challenges involved. The study analyzed 36 responses from 150 surveys distributed [...] Read more.

This study examines how lean manufacturing practices are adopted in Singapore’s SME precision and electronics manufacturing industry. Its main goal is to assess the extent of lean manufacturing method adoption and the challenges involved. The study analyzed 36 responses from 150 surveys distributed online. The results show that about 50% of manufacturers find it difficult to implement lean manufacturing practices. Our research reveals that most SMEs face significant challenges when applying lean manufacturing techniques. The findings identify barriers such as a lack of experience, skills, and knowledge, which significantly slow progress. Additionally, the study emphasizes that management support is vital for successful lean implementation. Key factors include employee training, goal alignment, and the creation of a supportive environment. While tools and external expertise are helpful, internal resources and organizational culture are considered more critical. Full article

► Show Figures

Figure 1

22 pages, 2073 KB

Open AccessArticle

TVAE-GAN: A Generative Model for Providing Early Warnings to High-Risk Students in Basic Education and Its Explanation

by Chao Duan, Yiqing Wang, Wenlong Zhang, Zhongtao Yu, Yu Pei, Mingyan Zhang and Qionghao Huang

Information 2026, 17(4), 356; https://doi.org/10.3390/info17040356 - 8 Apr 2026

Abstract

The rapid development of intelligent learning guidance systems has created a favorable environment for personalized learning. By accurately predicting students’ future performance, education can be tailored and teaching strategies optimized. However, traditional prediction algorithms seldom account for highly imbalanced datasets in basic education, [...] Read more.

The rapid development of intelligent learning guidance systems has created a favorable environment for personalized learning. By accurately predicting students’ future performance, education can be tailored and teaching strategies optimized. However, traditional prediction algorithms seldom account for highly imbalanced datasets in basic education, overlook temporal factors, and lack further interpretability of the prediction results. To address these shortcomings, we propose Temporal Variational Autoencoder-Generative Adversarial Network (TVAE-GAN), a temporal variational autoencoder-generative adversarial network model aimed at providing early warnings for high-risk students in basic education, with in-depth interpretability analysis of the prediction results to suit the unique context of basic education. TVAE-GAN extracts features from real samples and introduces a Long Short-Term Memory (LSTM) network to capture dynamic features in time series, helping the model better understand temporal dependencies in the data, remember the sequential causal information of students’ online learning, and achieve better data generation performance. Using these features, the generative model generates new samples, and the discriminator model evaluates their quality, producing outputs that closely resemble real samples through training. The effectiveness of the TVAE-GAN model is validated on a collected online basic education dataset while also advancing the timing of interventions in predictions. The performance differences between the proposed method and classic resampling methods, as well as their impact in the educational field, are analyzed, highlighting that misclassification increases teacher workload and affects students’ emotions. Key influencing factors are identified using a decision-tree surrogate model, providing teachers with multidimensional references for academic assessment. Full article

(This article belongs to the Special Issue Advancing Smart Systems Through Deep Learning, Generative AI, and Big Data Analytics)

► Show Figures

Figure 1

32 pages, 1738 KB

Open AccessArticle

KOSMOS: Ontology-Based Knowledge Graph Scaffolding for Medical Documentation Generation

by Ryan Henry and Jiaqi Gong

Information 2026, 17(4), 355; https://doi.org/10.3390/info17040355 - 8 Apr 2026

Abstract

We investigate whether an ontology-typed knowledge graph (KG) can improve SOAP note generation from clinician–patient encounter transcripts by serving as a structured intermediate representation that organizes clinically salient content while preserving provenance. We introduce Knowledge graph Ontology Supported Medical Output System (KOSMOS), which [...] Read more.

We investigate whether an ontology-typed knowledge graph (KG) can improve SOAP note generation from clinician–patient encounter transcripts by serving as a structured intermediate representation that organizes clinically salient content while preserving provenance. We introduce Knowledge graph Ontology Supported Medical Output System (KOSMOS), which extracts typed clinical entities with attributes and relationships, grounds entities to UMLS concepts and a schema, and retains links to supporting transcript turns. The resulting graph is provided as context for large language model (LLM)-based SOAP generation either alone (KG-only) or combined with the original transcript (Transcript + Nodes, Transcript + KG). We evaluate these conditions against DocLens and Ambient Clinical Intelligence Benchmark (ACI-BENCH) baselines on their benchmark, claim, and citation analyses. Across all three test sets, transcript-inclusive KOSMOS variants achieve the highest raw scores, numerically exceeding the transcript-only baselines. Claim-level evaluation shows modest, non-significant recall gains for Transcript + Nodes and low hallucination under transcript-conditioned GPT-5.2, while citation analysis shows about a 3% accuracy gain for KOSMOS (Transcript + KG) over DocLens GPT-5.2. Overall, ontology-guided KG structure appears most beneficial as a complementary scaffold paired with transcript access, while relationships provide limited additional benefit under current extraction quality. Full article

(This article belongs to the Special Issue Large Language Models and Knowledge Graphs: Opportunities and Challenges)

► Show Figures

Figure 1

23 pages, 4282 KB

Open AccessArticle

FPGA-Accelerated Machine Learning for Computational Environmental Information Processing in IoT-Integrated High-Density Nanosensor Networks

by Alaa Kamal Yousif Dafhalla, Fawzia Awad Elhassan Ali, Asma Ibrahim Gamar Eldeen, Ikhlas Saad Ahmed, Ameni Filali, Amel Mohamed essaket Zahou, Amal Abdallah AlShaer, Suhier Bashir Ahmed Elfaki, Rabaa Mohammed Eltayeb and Tijjani Adam

Information 2026, 17(4), 354; https://doi.org/10.3390/info17040354 - 8 Apr 2026

Abstract

This study presents a nanosensor network system for autonomous microclimate optimization in precision horticulture, leveraging a field-programmable gate array (FPGA)-based control architecture that is integrated with an edge-level machine learning inference. Unlike the conventional greenhouse automation systems, which exhibit thermal and hygroscopic hysteresis [...] Read more.

This study presents a nanosensor network system for autonomous microclimate optimization in precision horticulture, leveraging a field-programmable gate array (FPGA)-based control architecture that is integrated with an edge-level machine learning inference. Unlike the conventional greenhouse automation systems, which exhibit thermal and hygroscopic hysteresis often exceeding 32 °C and 78% relative humidity, the proposed framework embeds a random forest regression (RFR) model directly within the Altera DE2-115 FPGA fabric to enable predictive environmental regulation. The model achieved an R² of 0.985 and root mean square error (RMSE) of 0.28 °C, allowing proactive compensation for the thermodynamic disturbances from the high-intensity light-emitting diode (LED) lighting with a 120 s predictive horizon. The real-time monitoring and remote supervision were supported via a NodeMCU-based IoT gateway, achieving a 140 ms mean communication latency and a 99.8% packet delivery reliability. The preliminary validation using lettuce (Lactuca sativa) optimized the environmental parameters, while the subsequent experiments with pepper (Capsicum annuum), a commercially important and environmentally sensitive crop, demonstrated system performance under real-world conditions. The control system maintained a temperature and humidity within ±0.3 °C and ±1.2% of the setpoints, respectively, and outperformed the baseline rule-based control with a 28% increase in fresh biomass, a 22% improvement in dry matter accumulation, a 25% reduction in actuator duty-cycle switching, and an 18% decrease in overall energy consumption. These results highlight the efficacy of FPGA-integrated edge intelligence combined with low-latency IoT telemetry as a scalable, energy-efficient, and high-fidelity solution for sub-degree environmental control in next-generation, controlled-environment, and vertical farming systems. Full article

(This article belongs to the Special Issue Next-Generation Vision Systems in Agriculture—Toward Explainable and Trustworthy AI)

► Show Figures

Figure 1

18 pages, 5511 KB

Open AccessArticle

Exploring the Application of Large Language Models (LLMs) in Data Structure Instruction: An Empirical Analysis of Student Learning Outcomes in Computer Science

by Hongzhi Li, Lijun Xiao, Kezhong Lu, Dun Li, Zheqing Zhang and Qishou Xia

Information 2026, 17(4), 353; https://doi.org/10.3390/info17040353 - 8 Apr 2026

Abstract

Recent advancements in Large Language Models (LLMs), including ChatGPT, DeepSeek, and Claude, have facilitated their growing integration into computer science education, including data structure courses. Despite their widespread adoption, the association between sustained and informal LLM usage and students’ learning outcomes remains insufficiently [...] Read more.

Recent advancements in Large Language Models (LLMs), including ChatGPT, DeepSeek, and Claude, have facilitated their growing integration into computer science education, including data structure courses. Despite their widespread adoption, the association between sustained and informal LLM usage and students’ learning outcomes remains insufficiently understood. This study seeks to address this gap by empirically examining the association between LLM usage and undergraduate performance in data structure education. We conduct a twelve-week empirical study involving fifty-four undergraduate students, in which LLMs were made freely accessible but neither explicitly encouraged nor discouraged during coursework and assignments. Students’ LLM usage patterns are analyzed in relation to their academic performance across different task types. Findings reveal a significant negative association between extensive reliance on LLMs for cognitively demanding tasks and overall learning outcomes. Additionally, an inverse associative trend is observed between the frequency of LLM usage across some learning activities and academic performance. In contrast, the use of LLMs for supplementary purposes, including conceptual clarification and theoretical understanding, exhibits a notably positive association with final performance. These findings suggest a task-dependent associative relationship between LLM usage and learning outcomes: LLM usage for conceptual learning shows a positive association with the mastery of relevant knowledge when used as a supplementary learning tool, while excessive LLM usage shows a negative association with the development of fundamental analytical and problem-solving skills. This study highlights the importance of carefully integrating LLMs into data structure education to support learning while preserving students’ independent cognitive engagement. Full article

(This article belongs to the Special Issue AI Technology-Enhanced Learning and Teaching)

► Show Figures

Graphical abstract

22 pages, 1170 KB

Open AccessArticle

Adverse Drug Reaction Detection on Social Media Based on Large Language Models

by Hao Li and Hongfei Lin

Information 2026, 17(4), 352; https://doi.org/10.3390/info17040352 - 7 Apr 2026

Abstract

Adverse drug reaction (ADR) detection is essential for ensuring drug safety and effective pharmacovigilance. The rapid growth of users’ medication reviews posted on social media has introduced a valuable new data source for ADR detection. However, the large scale and high noise inherent [...] Read more.

Adverse drug reaction (ADR) detection is essential for ensuring drug safety and effective pharmacovigilance. The rapid growth of users’ medication reviews posted on social media has introduced a valuable new data source for ADR detection. However, the large scale and high noise inherent in social media text pose substantial challenges to existing detection methods. Although large language models (LLMs) exhibit strong robustness to noisy and interfering information, they are often limited by issues such as stochastic outputs and hallucinations. To address these challenges, this paper proposes two generative detection frameworks based on Chain of Thought (CoT), namely LLaMA-DetectionADR for Supervised Fine-Tuning (SFT) and DetectionADRGPT for low-resource in-context learning. LLaMA-DetectionADR automatically generates CoT reasoning sequences to construct an instruction tuning dataset, which is then used to fine-tune the LLaMA3-8B model via Quantized Low-Rank Adaptation (QLoRA). In contrast, DetectionADRGPT leverages clustering algorithms to select representative unlabeled samples and enhances in-context learning by incorporating CoT reasoning paths together with their corresponding labels. Experimental results on the Twitter and CADEC social media datasets show that LLaMA-DetectionADR achieves excellent performance, with F1 scores of 92.67% and 86.13%, respectively. Meanwhile, DetectionADRGPT obtains competitive F1 scores of 87.29% and 82.80% with only a few labeled examples, approaching the performance of fully supervised advanced models. The overall results demonstrate the effectiveness and practical value of the proposed CoT-based generative frameworks for ADR detection from social media. Full article

(This article belongs to the Topic Generative AI and Interdisciplinary Applications)

► Show Figures

Figure 1

18 pages, 2634 KB

Open AccessArticle

Evidence-Grounded LLM Summarization for Actionable Student Feedback Analysis

by Zhanerke Baimukanova, Yerassyl Saparbekov, Hyesong Ha and Minho Lee

Information 2026, 17(4), 351; https://doi.org/10.3390/info17040351 - 7 Apr 2026

Abstract

Analyzing large-scale student feedback is critical for higher education quality assurance, yet manual analysis is inefficient and subjective. This paper proposes an integrated framework that unifies supervised classification, unsupervised clustering, and retrieval-augmented generation (RAG) to produce evidence-grounded and actionable insights. Ensemble-based supervised models [...] Read more.

Analyzing large-scale student feedback is critical for higher education quality assurance, yet manual analysis is inefficient and subjective. This paper proposes an integrated framework that unifies supervised classification, unsupervised clustering, and retrieval-augmented generation (RAG) to produce evidence-grounded and actionable insights. Ensemble-based supervised models perform thematic classification, while multi-encoder embedding fusion enables unsupervised discovery of coherent feedback clusters. A multi-stage RAG module integrates category predictions and cluster structure to retrieve representative evidence and generate transparent summaries with citation traceability. The framework is evaluated on student feedback collected from a Central Asian university and two public benchmarks, EduRABSA and Coursera course reviews, covering seven thematic categories. The supervised ensemble achieves 83.0% accuracy and 0.829 Macro-F1 on the primary dataset, while unsupervised clustering attains a silhouette score of 0.271 under the best fusion strategy. Independent evaluation on external benchmarks yields ensemble accuracy of 81.1% on EduRABSA and 49.8% on Coursera, confirming the framework’s adaptability across diverse educational contexts. By leveraging supervised labels and unsupervised structure, the proposed framework enables evidence-grounded, category-aware LLM-based summaries that faithfully reflect the diversity and distribution of student feedback and support actionable educational decision-making. Full article

(This article belongs to the Special Issue AI Technology-Enhanced Learning and Teaching)

► Show Figures

Figure 1

26 pages, 1451 KB

Open AccessArticle

LDA Analysis of Institutional Policy Texts: A Case Study of Regulations on the Protection of Historical and Cultural Cities, Towns, and Villages in China

by Zongcheng Hu and Li Shao

Information 2026, 17(4), 350; https://doi.org/10.3390/info17040350 - 7 Apr 2026

Abstract

Against the backdrop of a multi-tiered governance system and increasingly institutionalized norms, China’s historical and cultural preservation policies have long emphasized institutional standardization and hierarchical uniformity. Local policy texts are typically viewed as localized replicas of central institutional logic, overlooking internal variations and [...] Read more.

Against the backdrop of a multi-tiered governance system and increasingly institutionalized norms, China’s historical and cultural preservation policies have long emphasized institutional standardization and hierarchical uniformity. Local policy texts are typically viewed as localized replicas of central institutional logic, overlooking internal variations and differences in information structure. Accordingly, this study examines the Regulations on the Protection of Historical and Cultural Cities, Towns, and Villages issued by 13 provincial-level administrative regions in China. It conceptualizes provincial regulatory texts as institutionalized policy information systems, constructs a cross-regional corpus, and develops a comparative information structure analytical framework based on the Latent Dirichlet Allocation (LDA) topic model. This study operationalizes LDA-derived topic-weight distributions into a comparative analytical framework that captures structural prominence, dispersion, concentration, and priority hierarchy in provincial policy texts. The findings reveal that provincial-level historical and cultural preservation regulations in China exhibit a highly institutionalized information backbone, centered on administrative procedures, legal norms, and macro-level planning controls, and demonstrate significant institutional similarity across provinces. However, within this unified institutional framework, provinces exhibit structural differences in the distribution of thematic weights, information prioritization, and internal textual sequencing, resulting in multiple distinguishable information organization patterns. Consequently, this study highlights the coexistence of formal institutional uniformity and structural differentiation in provincial regulatory texts, providing a more precise basis for understanding variation in local policy expression within China’s historical and cultural governance field. Full article

(This article belongs to the Section Information Theory and Methodology)

► Show Figures

Figure 1

21 pages, 2700 KB

Open AccessArticle

Bridging Stochasticity and Fuzziness: Automated Construction of Triangular Fuzzy Numbers via LLM Temperature Sampling for Managerial Decision Support

by Meng Zhang, Wenjie Bai, Yuanfei Guo, Wenlong Xu, Ranjun Wang, Yingdong Chen and Yuliang Zhao

Information 2026, 17(4), 349; https://doi.org/10.3390/info17040349 - 6 Apr 2026

Abstract

Traditional fuzzy decision-making often relies on manual expert calibration, which is labor-intensive and susceptible to subjective bias. This study addresses these limitations by proposing a novel framework that transforms the intrinsic probabilistic outputs of Large Language Models (LLMs) into Triangular Fuzzy Numbers (TFNs). [...] Read more.

Traditional fuzzy decision-making often relies on manual expert calibration, which is labor-intensive and susceptible to subjective bias. This study addresses these limitations by proposing a novel framework that transforms the intrinsic probabilistic outputs of Large Language Models (LLMs) into Triangular Fuzzy Numbers (TFNs). We introduce a multi-temperature sampling strategy coupled with weighted quantile aggregation and an adaptive interval adjustment mechanism to systematically map model stochasticity to fuzzy possibility distributions. Empirical validation on a structured prototype dataset demonstrates that the proposed method achieves high consistency with expert consensus, with GPT-4.2 exhibiting superior central accuracy and Gemini-2.5 excelling in uncertainty coverage. Furthermore, in complex unstructured scenarios involving business public opinion, the integration of Model Context Protocol (MCP) and Retrieval-Augmented Generation (RAG) significantly corrects cognitive biases and converges uncertainty boundaries. This research establishes a rigorous pathway from generative AI probabilities to fuzzy decision theory, offering a robust automated solution for quantitative risk assessment and intelligent decision support. Full article

(This article belongs to the Special Issue AI and Machine Learning in the Big Data Era: Advanced Algorithms and Real-World Applications)

► Show Figures

Figure 1

23 pages, 14151 KB

Open AccessArticle

Participatory Digital Traceability Systems for Information Governance: Design and Real-World Deployment in Urban Afforestation Programs

by Luis Veas-Castillo, Gerson Andrade, Christian Lazo, Tania Letelier, Iván Díaz, Mónica Alacid and María Hermosilla

Information 2026, 17(4), 348; https://doi.org/10.3390/info17040348 - 5 Apr 2026

Abstract

Large-scale urban tree donation campaigns are widely implemented worldwide as nature-based solutions for climate adaptation and mitigation; however, most programs lack individual-level traceability and post-donation monitoring, limiting accountability and evidence-based management. A fundamental prerequisite for longitudinal survival assessment is the existence of a [...] Read more.

Large-scale urban tree donation campaigns are widely implemented worldwide as nature-based solutions for climate adaptation and mitigation; however, most programs lack individual-level traceability and post-donation monitoring, limiting accountability and evidence-based management. A fundamental prerequisite for longitudinal survival assessment is the existence of a reliable traceability infrastructure capable of linking individual trees to verified planting records over time. This study proposes and empirically evaluates a participatory digital traceability system that establishes this foundational infrastructure, conceptualized as a distributed data validation architecture for donation-based urban afforestation programs. The framework integrates (i) persistent digital identifiers, (ii) geospatial registration, (iii) distributed multi-stage validation, and (iv) structured citizen reporting, and is operationalized through an installation-free progressive web application (ArborizaCL). The approach was deployed in five real-world campaigns conducted in Valdivia, Chile (May–September 2025), registering 642 trees distributed to 240 participants. A total of 190 georeferenced planting reports were submitted, corresponding to an overall reporting rate of 29.6%. Reporting behavior varied substantially by institutional follow-up strategy: campaigns with active follow-up achieved a mean reporting rate of 54.0%, compared with 13.0% under passive strategies, yielding a 41.0 percentage point difference (315.8% relative increase). Spatial analysis of reported plantings showed a predominance of urban (51.1%) and peri-urban (42.1%) locations, enabling differentiated territorial assessment. These results indicate that while digital infrastructure enables traceability and transparent monitoring, sustained citizen engagement is strongly associated with institutional coordination mechanisms. Beyond environmental monitoring, the proposed framework contributes to information governance by demonstrating how participatory digital traceability systems can support distributed public-sector oversight and outcome-oriented evaluation. The framework provides a transferable methodological basis for strengthening monitoring capacity, transparency, and governance design in publicly funded afforestation initiatives and other distributed civic programs. Full article

(This article belongs to the Special Issue Information Systems and Technologies: Foundations, Techniques, and Applications)

► Show Figures

Graphical abstract

18 pages, 741 KB

Open AccessReview

A Review of Tools and Technologies to Combat Deepfakes

by Dmitry Erokhin and Nadejda Komendantova

Information 2026, 17(4), 347; https://doi.org/10.3390/info17040347 - 3 Apr 2026

Abstract

Deepfakes and adjacent synthetic-media capabilities have become a systemic challenge for information integrity, security, and digital trust. Countermeasures now span passive detection methods that infer manipulation from content traces, active provenance systems that cryptographically bind metadata to media, and watermarking approaches that embed [...] Read more.

Deepfakes and adjacent synthetic-media capabilities have become a systemic challenge for information integrity, security, and digital trust. Countermeasures now span passive detection methods that infer manipulation from content traces, active provenance systems that cryptographically bind metadata to media, and watermarking approaches that embed detectable signals into content or generative processes. This review presents a rigorous synthesis of tools and technologies to combat deepfakes across modalities (image, video, audio, and selected multimodal settings), drawing primarily from the peer-reviewed literature, standardized benchmarks, and official technical specifications and reports. The review analyzes detection methods, provenance and authentication technologies, with emphasis on cryptographic manifests and threat models, watermarking and content provenance, including diffusion-era watermarking and industrial deployments, adversarial robustness and attacker adaptation, datasets and benchmarks, evaluation metrics across tasks, and deployment and scalability constraints. A dedicated section addresses legal, ethical, and policy issues, focusing on emerging transparency obligations and platform governance. The review finds that no single countermeasure is sufficient in realistic adversarial settings. The strongest practical approach is a layered defense that combines provenance, watermarking, content-based detection, and human oversight. The study concludes with limitations of the current evidence base and prioritized research directions to improve generalization, interoperability, and trustworthy user experiences. Full article

(This article belongs to the Special Issue Surveys in Information Systems and Applications)

► Show Figures

Graphical abstract

22 pages, 691 KB

Open AccessArticle

Context-Aware Hybrid Detection of DOM-Based Cross-Site Scripting via Runtime Semantic Modeling

by Maksim Iavich, Daviti Botchorishvili and Audrius Lopata

Information 2026, 17(4), 346; https://doi.org/10.3390/info17040346 - 3 Apr 2026

Abstract

DOM-based Cross-Site Scripting (DOM XSS) remains a critical web application vulnerability due to its exclusive manifestation within client-side execution contexts, rendering traditional server-side defenses ineffective. Existing machine learning approaches achieve high recall but suffer from critically low precision in DOM-specific scenarios. Payload-centric classifiers [...] Read more.

DOM-based Cross-Site Scripting (DOM XSS) remains a critical web application vulnerability due to its exclusive manifestation within client-side execution contexts, rendering traditional server-side defenses ineffective. Existing machine learning approaches achieve high recall but suffer from critically low precision in DOM-specific scenarios. Payload-centric classifiers frequently misclassify syntactically suspicious but semantically benign injections, causing high false positive rates. This paper introduces a context-aware hybrid detection framework integrating dynamic taint tracking with runtime DOM semantic analysis and lightweight machine learning classification. The proposed architecture extracts a 42-dimensional feature vector combining 22 lexical payload features with 20 contextual execution features capturing sink semantics, element type, attribute execution capability, and DOM state properties. A Random Forest classifier is employed to enable low-latency inference and demonstrates potential for real-time deployment. By modeling exploitability as a function of execution context rather than payload syntax alone, the framework significantly reduces false positives while maintaining high detection capability. Experimental evaluation demonstrates that contextual feature integration substantially improves precision compared to payload-only baselines, achieving a favorable precision-efficiency trade-off. The primary contribution lies in elevating runtime semantic context to a first-class feature space for DOM XSS detection, representing a shift from text-centric classification toward execution-aware security modeling in client-side web environments. Full article

(This article belongs to the Section Information Applications)

► Show Figures

Graphical abstract

18 pages, 5346 KB

Open AccessArticle

MFT-PTM: A Multisource-Fused and Temporally-Aware Framework for Evolutionary Analysis of Rare Earth Patent Topics Model

by Haofei Zhang, Jingyu Wang, Jinling Yu and Lixin Liu

Information 2026, 17(4), 345; https://doi.org/10.3390/info17040345 - 2 Apr 2026

Abstract

Rare-earth elements are critical to a wide range of high-technology applications, and analyzing patents involving rare-earth elements is essential for understanding technological progress and innovation trends. Traditional topic models cannot fully exploit patent network structures and temporal information, limiting their ability to capture [...] Read more.

Rare-earth elements are critical to a wide range of high-technology applications, and analyzing patents involving rare-earth elements is essential for understanding technological progress and innovation trends. Traditional topic models cannot fully exploit patent network structures and temporal information, limiting their ability to capture the dynamic evolution of technology topics. To overcome these limitations, we propose a novel multisource-fused framework (MFT-PTM), which integrates three types of multisource features: textual, network, and temporal features via the time-aware TemporalK-Means algorithm. Specifically, we use SciBERT to extract text embeddings, TransR to generate network embeddings, and derive temporal scalars from patent data. After fusing and reducing these features with Uniform Manifold Approximation and Projection (UMAP), we apply TemporalK-Means clustering with a time-decay mechanism to capture evolutionary trends. Experiments on 43,322 rare-earth-related patents indicate that the proposed framework achieves improved performance compared with traditional methods such as LDA and BERTopic in terms of topic coherence, cluster quality, and cluster separation. Furthermore, the analysis suggests a noticeable technological transition in rare-earth applications, gradually shifting from environmental catalysis toward advanced energy and biomedical domains. Overall, the framework provides a quantitative approach for integrating multisource patent information and exploring technological evolution patterns. Full article

(This article belongs to the Section Information Applications)

► Show Figures

Figure 1

32 pages, 2911 KB

Open AccessArticle

End-to-End Personalization via Unifying LLM Agents and Graph Attention Networks for Entertainment Recommendation

by Danial Ebrat, Sepideh Ahmadian and Luis Rueda

Information 2026, 17(4), 344; https://doi.org/10.3390/info17040344 - 2 Apr 2026

Abstract

Recommender systems are central to helping users navigate the rapidly expanding entertainment ecosystem, yet achieving strong personalization with limited feedback while maintaining interpretability remains difficult, particularly under cold-start conditions and heterogeneous item metadata. This work presents an end-to-end hybrid recommendation framework that unifies [...] Read more.

Recommender systems are central to helping users navigate the rapidly expanding entertainment ecosystem, yet achieving strong personalization with limited feedback while maintaining interpretability remains difficult, particularly under cold-start conditions and heterogeneous item metadata. This work presents an end-to-end hybrid recommendation framework that unifies a Large Language Model (LLM) with Graph Attention Network (GAT)-based collaborative filtering to improve both ranking accuracy and explanation quality across movies, books, and music. LLM-based agents first transform raw metadata such as titles, genres, descriptions, and auxiliary attributes into semantically grounded user and item profiles, which are embedded and used as initial node features in a user–item bipartite graph processed by a GAT-based recommender. Model optimization relies on a hybrid objective combining Bayesian Personalized Ranking, cosine-similarity regularization, and robust negative sampling to better align semantic and collaborative signals. Finally, in the post-processing stage, an LLM-based agent re-ranks the GAT outputs using a proposed Hybrid Confidence-Weighted Binary Search Tree, and another LLM-based agent that produces natural-language justifications tailored to each user. Experiments on diverse benchmark datasets and extensive ablations demonstrate that the proposed methodology increases precision, recall, NDCG, and MAP across various values of K. In addition, the post processing step is especially effective in cold-start scenarios, consistently strengthening recommendation metrics and enhancing transparency at smaller values of K. Overall, integrating LLM-enriched representations with attention-based graph modeling enables more accurate and explainable entertainment recommendations. Full article

(This article belongs to the Special Issue 2nd Edition of Modern Recommender Systems: Approaches, Challenges and Applications)

► Show Figures

Figure 1

23 pages, 1950 KB

Open AccessArticle

Mobile App Privacy Disclosures on Google Play in the Post-GDPR Context: A Large-Scale Analysis of Data Safety Section and Permissions

by Gerasimos S. Magoulas and Spyros E. Polykalas

Information 2026, 17(4), 343; https://doi.org/10.3390/info17040343 - 2 Apr 2026

Abstract

Mobile apps are essential for communication, transactions and leisure and frequently rely on access to personal data. This study examines Google Play’s Data Safety section and declared permissions five years after the GDPR came into force, focusing on how developers disclose data collection, [...] Read more.

Mobile apps are essential for communication, transactions and leisure and frequently rely on access to personal data. This study examines Google Play’s Data Safety section and declared permissions five years after the GDPR came into force, focusing on how developers disclose data collection, sharing, security practices and deletion controls. We use metadata from 49,578 Android apps and analyze self-reported disclosures in relation to permission categories, app categories, installs and user ratings. The results show that free apps request broader permission access than paid ones and that declared permission use has gradually increased over time. In addition, 25.44% of the sampled apps had not completed any part of the Data Safety section and non-completion was associated with app age, installation band and pricing model. Among apps with completed relevant Data Safety section disclosures, 11% of developers explicitly declared that data are not encrypted in transit and 34% explicitly declared that no user-initiated data deletion mechanism is available. Category-level differences in declared data collection and sharing were modest, while the relationship between permission breadth and user ratings was small. Overall, the findings indicate that structured disclosure mechanisms can improve visibility of privacy-related information, but do not necessarily ensure its completeness or consistency. Full article

(This article belongs to the Section Information Security and Privacy)

► Show Figures

Graphical abstract

37 pages, 856 KB

Open AccessArticle

Unbiasing Greek: In-Context Learning Strategies for Gender Bias Identification and Mitigation for Legal Documents and Job Ads

by Dimitrios Doumanas, Andreas Soularidis, Nikolaos Zafeiropoulos, Stamatis Chatzistamatis, George E. Tsekouras, Andreas El Saer, Chrisaphis Nathanailidis and Konstantinos Kotis

Information 2026, 17(4), 342; https://doi.org/10.3390/info17040342 - 2 Apr 2026

Abstract

Gender bias embedded in legal and professional texts perpetuates systemic inequality, yet research on bias identification and mitigation remains largely confined to English. Morphologically rich languages such as Greek, where grammatical gender pervades nouns, adjectives, pronouns, and participles, present unique challenges that existing [...] Read more.

Gender bias embedded in legal and professional texts perpetuates systemic inequality, yet research on bias identification and mitigation remains largely confined to English. Morphologically rich languages such as Greek, where grammatical gender pervades nouns, adjectives, pronouns, and participles, present unique challenges that existing approaches fail to address. This paper elaborates on a systematic methodology primarily focusing on identifying and mitigating gender bias in Greek-language job advertisements and legal documents. To accomplish that task, we define a taxonomy of nine gender bias rules tailored to the linguistic properties of Greek and construct domain-specific annotated datasets comprising 90 expert-curated few-shot examples across both textual domains. Using these resources, we employ XML-structured prompt engineering with in-context learning (ICL)and systematically compare three classes of models: (i) commercial large language models (LLMs), namely Claude Sonnet 4.5 and GPT-5.2, (ii) two open-weight small language models (SLMs), Mistral Small (24B) and Ministral (14B), and (iii) Llama Krikri (8B), a Greek-native language model built on Llama 3.1 and fine-tuned on high-quality Greek corpora. For each input text, the system identifies biased expressions, maps them to specific bias rules, provides explanations, and generates a fully corrected inclusive version. Our experiments reveal substantial performance disparities across model scales and linguistic specialization, with LLMs demonstrating superior contextual reasoning and SLMs exhibiting systematic over-correction and grammatical errors in Greek morphology. We further introduce a critical meta-rule addressing gender agreement with named entities to prevent spurious corrections in legal texts referencing identified individuals. The findings highlight the importance of model scale, language-specific adaptation, and carefully designed prompting strategies for bias mitigation in underrepresented languages. Full article

(This article belongs to the Special Issue Modeling in the Era of Generative AI)

► Show Figures

Figure 1

21 pages, 1291 KB

Open AccessArticle

Development of a Software Model for Classification and Automatic Cataloging of Archive Documents

by Adilbek Dauletov, Bahodir Muminov, Noila Matyakubova, Uldona Abdurahmonova, Khurshida Bakhriyeva and Makhbubakhon Fayzieva

Information 2026, 17(4), 341; https://doi.org/10.3390/info17040341 - 1 Apr 2026

Abstract

This study proposes an integrated software model for automatic document classification and metadata generation based on the Dublin Core standard to address the issue of rapid and consistent management of archival documents in a digital environment. This approach combines the stages of receiving [...] Read more.

This study proposes an integrated software model for automatic document classification and metadata generation based on the Dublin Core standard to address the issue of rapid and consistent management of archival documents in a digital environment. This approach combines the stages of receiving incoming documents, converting them to text using optical character recognition (OCR), image preprocessing (binarization, deskew, noise reduction), and text cleaning and vectorization (TF–IDF) into a single pipeline. In the document classification stage, the Bidirectional Encoder Representations from Transformers (BERT) model with a context-sensitive transformer architecture is used, along with classical machine learning models (Logistic Regression, Naive Bayes, Support Vector Machine) and an ensemble approach (LightGBM), to increase the accuracy by modeling the document content at a deep semantic level. Experiments were conducted on the RVL-CDIP dataset, and the OCR efficiency was evaluated using the Character Error Rate (CER) indicator, and the classification results were evaluated using the accuracy, precision, recall and F1-score metrics. The results confirmed the high stability and generalization ability of the BERT (accuracy, 95.1%; F1, 95.0%) and LightGBM (accuracy, 93.2%; F1, 93.2%) models. In the final stage, OCR, NER, and classification outputs are automatically organized into Dublin Core metadata elements (Title, Creator, Date, Description, Subject, Type, Format, Language) and exported in JSON/XML formats. This automation significantly reduces manual cataloging effort and improves indexing and retrieval efficiency in digital archival systems. Full article

(This article belongs to the Topic Advances in Integrative AI, Machine Learning, and Big Data for Transformative Applications)

► Show Figures

Graphical abstract

Journal Description

Information

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI