Search Results (456)

This exploratory study primarily aims to identify and characterise profiles of digital competence and information evaluation among secondary-school students, considering their academic performance in Geography and History. It also examines gender differences in online information practices and associations between Internet use, academic performance, and information-searching and evaluation skills, including the recognition of fake news and hate speech. A quantitative methodology was employed, combining descriptive, inferential, and correlation analyses with two-step cluster analysis. The non-probabilistic convenience sample comprised 72 third- and fourth-year secondary-school students from a public rural school in Toledo (Castilla-La Mancha, Spain). Cluster analysis identified three provisional profiles: a larger profile characterised by lower reported technical competence and moderate academic performance; a second profile with higher reported digital competence and notable academic achievement; and a third combining strong academic performance with lower reported digital competence. Information-searching skills, technical knowledge, and fake news detection were the variables contributing most to profile differentiation, whereas time spent online had the lowest importance. Fake news detection was also significantly associated with academic performance. Gender comparisons showed higher reported technical competence and information-searching and verification skills among male students, while differences in fake news and hate speech recognition were not statistically significant. Given the small, single-school convenience sample and reliance on self-reported measures, these findings should be interpreted cautiously and not generalised beyond this context. Full article

With the rapid growth of social media, online news has become increasingly multimodal, combining textual and visual information, posing new challenges for fake news detection. Existing methods often suffer from redundant features, distribution differences across modalities, and insufficient modeling of semantic interactions. To address these issues, this paper proposes an Adaptive Binary Osprey Optimization Algorithm and Cross-modal Disentangled Fusion model (ABOOA-CDF). First, an Adaptive Binary Osprey Optimization Algorithm (ABOOA) is developed for multimodal feature selection by integrating chaotic initialization, adaptive search, and binary mapping strategies to identify informative feature subsets. Then, a Cross-modal Relation Disentanglement Module (CRDM) is introduced to decompose multimodal representations into shared, discrepant, and complementary components, thereby enhancing semantic relationship modeling. Furthermore, an Adaptive Semantic Fusion Module (ASFM) dynamically learns fusion weights to generate discriminative multimodal representations. Experimental results demonstrate that ABOOA-CDF effectively improves detection performance. Compared with MFO and OOA, the proposed method achieves Accuracy improvements of 1.02 and 2.66 percentage points, respectively, verifying its effectiveness in feature optimization, cross-modal relation modeling, and semantic fusion. Full article

The use of deepfake media, particularly face-swap and face-shifter videos, has proliferated rapidly on social media and online news outlets. Though there are legitimate uses for this synthetic media in certain applications, such as media reporting, there is always the possibility of misleading people, creating distrust of digital information, and even posing security threats. Most existing studies have focused on deepfake detection using either image or video frames; however, these methods are computationally costly and do not perform well in real time. To address these limitations, this work proposes a pipeline for deepfake video detection using network packet analysis. A novel PCAP dataset is constructed by streaming real and manipulated video content over WebRTC and TCP (Port 8080) protocols, and machine learning models are then trained on 48 extracted network-level features to distinguish deepfake traffic from authentic streams. For implementation, four deepfake video datasets of varying quality are utilized, namely, HIDF, FaceForensics++, SDFVD-V2, and ManualFake-2022, each containing both real and manipulated samples. Videos are segmented into 3, 6, and 9-s clips and sequentially streamed over WebRTC and TCP (Port 8080) protocols to capture network traffic in PCAP format. Experiments are conducted using six classical machine learning classifiers, namely KNN, Logistic Regression, Decision Tree, Random Forest, Histogram Gradient Boosting, and Naïve Bayes, trained on 48 network-level features. The proposed pipeline achieved the highest classification accuracy of 91.2% on TCP (Port 8080) and 79.9% on the WebRTC protocol, both obtained using 6-s video captures. Full article

Fake news often manipulates fine-grained knowledge elements such as entities, events, claims, temporal expressions, attributes, and source credibility. Existing information extraction methods usually require task-specific annotations or focus on generic named entities, making them less effective for open-domain fake news scenarios where labeled data are scarce and logical inconsistencies are subtle. This paper proposes HPDO-KEE, a hierarchical prompting framework with dynamic optimization for knowledge element extraction and feature enhancement in fake news detection. The method first defines a fake-news-oriented schema covering entities, events, claims, attribute–value pairs, relations, contradictions, and user authority. It then designs a four-layer prompt consisting of task description, core information, structure awareness, and demonstration assistance. The revised implementation distinguishes offline prompt-template rewriting from input-adaptive demonstration retrieval and automatic schema-validation retries during inference. Domain-aware demonstration selection, strict JSON constraints, redundancy removal, contradiction-candidate verification, and type correction are incorporated to improve extraction accuracy, format compliance, and stability. Experiments on CoNLL03, ACE2005, and DuEE2.0 show that HPDO-KEE achieves F1 scores of 88.9%, 82.6%, 80.3%, and 78.6% on named entity, entity, event, and Chinese event extraction tasks, respectively. Full article

In the digital era, the rapid proliferation of fake news poses critical challenges to information credibility and public trust, particularly in Arabic news ecosystems where linguistic complexity and limited annotated resources exacerbate detection difficulties. This study proposes a framework for Arabic fake news detection based on a weighted-distance ensemble learning method (WDELM). The WDELM framework combines posterior-probability estimates from six heterogeneous base classifiers: extreme gradient boosting (XGBoost), LightGBM (LGBM), random forest (RF), adaptive boosting (AdaBoost), gradient boosting (GB), and logistic regression (LR). The classifier outputs are integrated through a distance-aware adaptive weighting strategy based on cosine distance in the prediction space. Unlike conventional ensemble techniques, the proposed framework employs normalised distance-aware adaptive weighting to adapt classifier contributions while preserving the probabilistic interpretation of the final ensemble output. Experiments were conducted on an Arabic fake news dataset comprising 2538 manually annotated instances. The model was evaluated using multiple performance metrics, including precision, recall, F1-score, Cohen’s kappa, ROC-AUC, and accuracy, together with explainability analyses. Using stratified ten-fold cross-validation, the proposed WDELM achieved a mean accuracy of $92.120\pm 1.097\%$ and a mean ROC-AUC of $97.125\pm 0.686\%$. Analysis of the concatenated predictions generated across the ten outer-validation folds yielded an F1-score of 91.357% for the Fake class, an F1-score of 92.759% for the Real class, and a pooled macro-F1 score of 92.058%, indicating balanced classification performance across both classes. The results indicate that the proposed weighted-distance ensemble strategy provides improved empirical performance within the evaluated dataset and offers a transparent mechanism for combining heterogeneous classifiers. The framework is further assessed through statistical validation, error analysis, and explainability analysis, supporting its potential use as an auxiliary decision-support tool for Arabic fake news screening rather than as a fully automated replacement for professional fact-checking. Full article

Rumors, misleading claims, and other factually risky information units may gain visibility during crises before verification processes are complete. Existing detection systems often address factual status or diffusion separately, whereas operational monitoring requires identifying units that are both factually risky and highly amplified by a forecast horizon. This paper proposes the Disinformation Diffusion Virality Risk Index (DDVRI), an explainable early-warning framework for estimating this joint risk from evidence observed during a prespecified early window. The formulation defines early histories, adjudicated factual labels, fold-specific amplification thresholds estimated without test outcomes, optional absolute amplification floors, block-structured early representations, calibrated risk scores, and capacity-constrained alerting rules. The proposed framework is evaluated using two open datasets, one focused on crisis rumors and another focused on COVID-19 health misinformation with social engagement information. The results support DDVRI as a probabilistic early-warning and prioritization methodology for rare cases that combine factual risk and high-amplification, rather than as a general fake-news classifier or an automatic moderation system. Full article

In recent years, there has been an increase in the amount of fake news in the media, which is why fact-checking systems are gaining popularity, particularly those that use natural language processing (NLP) to quickly identify and flag fake news. One of the main limitations in the development of such systems is the limited number of datasets containing verified information, which are necessary for the effective training of models. The situation is particularly critical for non-English datasets, specifically those in the Ukrainian language. This article proposes a three-stage algorithm for training a model to recognize fake news in the Ukrainian language. At the core of the proposed approach lies the multilingual transformer model XLM-RoBERTa, which solves this problem by utilizing cross-lingual knowledge transfer from English to Ukrainian. This approach means there is no need to search for a large, high-quality dataset in Ukrainian; instead, a significantly smaller dataset in Ukrainian can be used for the final calibration of the model. The model developed as a result of the experiment proved effective in extreme low-resource scenarios, achieving 90.7% accuracy on just 500 training records and outperforming the baseline model by 9.7%. Full article

The proliferation of fake news poses a significant threat to democratic institutions, public trust, and crisis management, particularly as it becomes a central tactic in coordinated information operations. This paper explores the application of machine learning (ML) algorithms in detecting and classifying disinformation as a means of supporting experts engaged in combating influence campaigns. We utilize a labelled English dataset, and a custom collected Bulgarian news dataset gathered using version 1 of the NewsData.io API, as indicated by the /api/1/ endpoint. After translating the Bulgarian content and generating synthetic fake news from real articles, we construct a multilingual training set. We evaluate the performance of three ML models demonstrating that advanced ML approaches can significantly enhance the identification of disinformation. These findings highlight the potential for machine learning to assist intelligence analysts, cybersecurity professionals, and policy makers in detecting and countering modern information operations at scale. Full article

Fake news detection has become a major research topic at the intersection of artificial intelligence, data mining, and information security. In this paper, we evaluate the performance of English-trained algorithms on English translations of Romanian-sourced news articles, using a translation-mediated cross-domain evaluation design. The study is based on source code generated with the assistance of artificial intelligence systems for a set of machine learning and transformer-based models. The code was subsequently implemented in Google Colab. 2026, trained on international benchmark datasets, and tested on Romanian news content. This design allowed the rapid prototyping of multiple detection pipelines and the systematic observation of their behavior in a media environment different from that represented in the training corpora. The models were evaluated comparatively using standard classification metrics, including accuracy, precision, recall, and F1-score, complemented by additional indicators relevant to model robustness and practical usability. The experimental results revealed significant differences in performance across algorithms when applied to English translations of Romanian-language news content after training on international datasets. However, this study does not provide a direct comparison between model performance on the international benchmark datasets and the Romanian test corpus; therefore, the gap between the international training corpus and the Romanian-sourced test corpus is interpreted as an exploratory limitation and as a direction for future research. Based on these findings, we propose an empirical classification of the tested models according to their predictive effectiveness, their contextual robustness across linguistic environments, and their operational relevance as filtering tools for institutional monitoring. The results show that AI-assisted coding workflows can provide a viable starting point for reproducible misinformation research, but they also underline the limitations of directly transferring models trained on non-Romanian data to local media ecosystems. The study offers both a replicable evaluation framework and practical insights for institutions involved in strategic communication, public security, and the monitoring of information threats. Full article

This study investigates automated fake news detection as a reliability-oriented text classification problem in dynamic digital information environments. We propose H-FuseNet, a hybrid multi-representation fusion framework that combines pretrained transformer representations with deception-oriented handcrafted linguistic, stylistic, and semantic features. Using the WELFake dataset, we benchmark 15 baseline models, including classical classifiers, ensemble methods, recurrent and convolutional networks, and transformer fine-tuning models, under stratified 10-fold cross-validation with nested hyperparameter optimization. To examine generalization beyond a single benchmark, we train exclusively on WELFake and evaluate cross-dataset performance on three held-out external datasets: FakeNewsNet, CoAID, and LLM-generated misinformation. H-FuseNet integrates transformer document embeddings with a lightweight feature-processing MLP, optional contextual feature streams when metadata are available, and auxiliary supervision through pseudo-labeled headline body stance and clickbait signals. The proposed model achieves 98.9% mean accuracy and 0.998 ROC–AUC, while maintaining strong calibration, with a Brier score of 0.012 and Expected Calibration Error of 0.009, and low variance across folds. Cross-dataset evaluation yields accuracies of 87.34% on FakeNewsNet, 83.56% on CoAID, and 91.22% on LLM-generated misinformation, demonstrating robust generalization under distribution shift. Ablation analyses show that handcrafted features, auxiliary tasks, and learned fusion each contribute to performance, while Wilcoxon and McNemar tests indicate statistically significant differences against selected strong baselines. Error analysis shows that remaining failures mainly occur in professionally written misinformation that imitates neutral journalistic style. Overall, the results suggest that calibrated multi-representation fusion can improve the reliability of automated fake news detection systems. Full article

The literature pays little attention to the impact of gratifications on fake news sharing among Chinese social media users, and fuzzy-set qualitative comparative analysis (fsQCA) is rarely used in fake news research. This study investigated the relationship between gratifications and fake news sharing among Chinese users. Study 1 employed partial least squares structural equation modeling (PLS-SEM) and fsQCA on the questionnaire data from 315 participants. Study 2 analyzed predictions of self-reported sharing intentions in task scenarios using data from 98 new participants. The PLS-SEM revealed that instant news sharing was positively predicted by time-passing, entertainment, and socializing gratifications; and negatively predicted by information seeking. Fake news sharing is positively predicted by instant news sharing and negatively predicted by fact-checking. The fsQCA revealed three distinct antecedent configurations leading to high sharing among users, demonstrating that sharing is driven by diverse, equifinal pathways rather than a single set of common characteristics. Study 2 confirmed that self-reported sharing intention predicts sharing intention in task scenarios. Gratifications influence users’ fake news sharing through instant sharing and fact-checking, and three configurations prompt users to share fake news. These findings promote the cultural richness of the fake news-sharing research and offer practical implications. Full article

There is an enormous rise in the amount of user-generated content on social media. That makes it easier for hateful and fake messages to spread, and threatens both societal stability and public trust in institutions. Most of current solutions have fundamental limitations due to modal limitations (i.e., each solution only uses one type of data at a time), lack of user context integration, poor synchronization across different types of data, and poor resilience to manipulation by adversaries. As a result, most solutions are subject to compound loss in terms of their ability to generalize well, classify correctly, or remain reliable when deployed in real-world environments. To address all of the above challenges, we propose a comprehensive and modular analytical framework consisting of five interconnected components that integrate contextual representation learning, multimodal semantic alignment, graph-based propagation modeling, adaptive inference, and consistency validation for hate speech and fake post detection. First is our Context-Driven Social Vector Extraction methodology, which provides enriched contextual embeddings by extracting and combining text-based metadata, image-based metadata, temporal metadata, and behavioral metadata. We use those embeddings in our second module, Multimodal Label Fusion via Mutual Co-Attention (CMF-MCA). Our CMF-MCA module incorporates two transformers with co-attention mechanisms that can mutually annotate text and images. In our third methodology, Semantic Propagation Graph for Hate and Fake Correlation (SPG-HFC), we implement a relational graph attention mechanism that captures both the influence of semantics and how communities propagate information about hate and fake posts. The fourth module, Adaptive Modality Routing via Reinforcement (AMR-R), routes based on the modality of the input and whether the input is simple enough to be classified using machine learning or complex enough to require deep learning. Finally, our Counterfactual Consistency Validation Engine (CCVE) is used after prediction to validate that the model’s predictions are consistent with the output data by creating counterfactuals and validating them. Therefore, in addition to improving the overall accuracy of hate speech and fake post detections, our proposed framework also improves its scalability and inference reliability. Additionally, because our framework allows multimodal classifications that include both context and behavior, it enables the scalable and trustworthy development of content moderation systems. Full article

Misinformation propagates more rapidly than factual content on social media, presenting significant challenges for automated misinformation detection. Existing approaches often focus solely on textual features without incorporating temporal information, treat timing and propagation as separate factors, or apply quantum-inspired methods primarily to multimodal data rather than text-centric misinformation. This study introduces QuST-TF (Quantum-inspired Semantic encoding and Temporal Transformer Fusion), a unified model designed to detect misinformation in tweets and news articles. QuST-TF integrates quantum-inspired (classical approximation) amplitude encoding, time-aware Transformer fusion, and propagation graph attention based on engagement data, without reliance on images, audio, or quantum hardware. Performance gains are achieved through quantum-inspired (classical approximation) nonlinear angular modulation (cosine and sine rotations) implemented via classical computation, rather than genuine quantum computing. All computations utilize classical Dense layers, Rectified Linear Unit (ReLU) activations, and cosine/sine functions on CPUs or GPUs; quantum hardware is not required. The quantum-inspired (classical approximation) layer applies classical rotation-based transformations to enrich the semantic representation of BERT (Bidirectional Encoder Representations and Transformer) embeddings. Temporal information is captured by a dual-attention Transformer encoder, while propagation graph attention monitors the spread of claims. Evaluation on FakeNewsNet and PHEME datasets demonstrates 91.4% and 95.5% accuracy, respectively, with 34% fewer trainable parameters compared to standard Transformers. Ablation studies indicate that quantum encoding is the most influential component (+3.0% versus without quantum encoding), surpassing the contributions of graph attention (+2.6%) and temporal attention (+2.2%). The integration of all three components yields a 1.3% synergistic improvement, confirming effective inter-module collaboration. Attention visualization enhances interpretability, supporting the utility of QuST-TF for fact-checking applications. Full article

The widespread dissemination and societal impact of fake news underscore the critical need for effective detection. Existing methods remain limited, as they often fail to learn joint representations from multi-modal data and rely heavily on complete social interaction signals. Such information is frequently unavailable in practice, especially during the early propagation stages. To address early fake news detection in social media, this paper proposes a hierarchical cross-modal fusion framework with structured LLM-simulated social interaction (HCF-LSIM). The framework employs a progressive cross-modal attention mechanism to systematically align semantic representations across multiple levels, integrating textual, thematic, and visual features. Additionally, HCF-LSIM designs an LLM-powered social interaction simulator that generates structured triplets from adapted user profiles, effectively compensating for missing real-time interaction data. Experiments on public benchmarks demonstrate strong performance, with accuracies of 93.5% on Weibo and 87.2% on X (formerly Twitter), ranking first on Weibo and second on Twitter. Full article

The expanding capabilities of deep learning-based media synthesis have intensified concerns regarding the authenticity of digital content and the reliability of forensic analysis tools. In response to these challenges, this work introduces DeepFakeX, a collection of 800 synthetically generated videos available under controlled access for research purposes. The dataset encompasses four distinct categories of AI-driven synthesis: facial identity replacement, audio track substitution, neural voice cloning, and combined audiovisual alteration. Unlike existing deepfake datasets that predominantly focus on facial synthesis, DeepFakeX covers a broader range of manipulation modalities, reflecting the diversity of synthetic media encountered in real-world settings. All deepfakes were generated using state-of-the-art, publicly available tools. Standardized post-processing procedures were applied to each video to ensure uniformity in terms of quality, duration and encoding format. DeepFakeX also emphasizes diversity in gender, age, ethnicity, and language. Video contexts span speeches, informational videos, movie clips, news broadcasts, and interviews that reflect content scenarios commonly encountered in real-world online environments. The dataset includes videos in both English and Urdu. The dataset’s quality and structural variability were assessed through visual and audio analyses using the Structural Similarity Index Measure (SSIM), Mel-Frequency Cepstral Coefficients (MFCCs), and Principal Component Analysis (PCA). The evaluation results revealed substantial variability within each manipulation category, along with clearly distinguishable patterns specific to each modality. DeepFakeX has been developed to facilitate rigorous and transparent research in deepfake detection, cross-modal forensic analysis, and AI-driven media forensics. It is hosted on Zenodo under controlled access for research use. Full article