Aug 2026· International journal of computer information systems and industrial management applications· 0 citations
TL;DR
Results indicate that the proposed architecture successfully combines the process of refining the semantic features of text data while providing an explainable artificial intelligence solution for real-world applications of fake news detection.
Abstract
The online media has proliferated and become more accessible, so too has the ease with which misinformation can spread and be consumed and automated mechanisms to detect this form of online deception will be very important research targets moving forward. The implementation of new techniques from deep learning and transformer models pre-trained on large amounts of data has greatly improved the ability to detect misinformation, however many detectors are hindered by limitations on their ability to utilize semantic features and interpret the resulting predictions. In this study, we present our Adaptive Semantic Feature Refinement for Explainable Fake News Detection Utilizing Pre-Trained Transformers model, which uses a novel hybrid deep learning architecture that combines DeBERTa-v3, Bidirectional Gated Recurrent Unit (BiGRU), Multi-Head Self-Attention, and an Adaptive Semantic Refinement Module (ASRM) to produce higher-quality representations of the text used to classify fake news articles into binary categories. In addition, by applying SHAP (SHapley Additive exPlanations) values and Integrated Gradients to improve prediction transparency, we were able to produce both global and local explanations of the model's predictions. Our model was tested using a large corpus of fake news articles that included 682,661 articles, the resulting accuracy was 85.85%, with a ROC AUC statistic of .9294. Overall, results indicate that our proposed architecture successfully combines the process of refining the semantic features of text data while providing an explainable artificial intelligence solution for real-world applications of fake news detection.
A hybrid transformer-based ensemble model for automated fake news identification using the FakeNewsNet dataset is proposed and Experimental results show that the ensemble model achieves an accuracy of approximately 93%, outperforming the individual constituent models.
M. E. Babu, G. Sukanya· International Journal for Re...· 0 citations
The rapid proliferation of digitally distributed news has made large-scale automated verification an urgent research priority, as deceptive content spreads across social platforms faster than manual reviewers can evaluate it. This work introduces a two-stage deep learning pipeline in which a pretrained BERT encoder generates rich contextual token embeddings that are subsequently processed by a Bidirectional Long Short-Term Memory (BiLSTM) network, enabling the classifier to exploit both sentence-level semantics and document-level narrative flow simultaneously. Experiments on the WELFake benchmark [1] following a standardised cleaning pipeline—lowercasing, URL stripping, tokenisation, stop-word removal, and WordNet lemmatisation— yielded 98.7 % accuracy and an F1-score of 0.986. This surpasses a BERT-only baseline by 3.1 percentage points and exceeds several previously published state-of-the-art results. The gains confirm that coupling transformer-based semantic representations with recurrent sequential modelling produces a measurable and reproducible improvement in misinformation detection. Planned extensions include multilingual evaluation and knowledge-distilled encoder replacements targeting real-time throughput constraints.
Ardra P Namboodiri, Archa P S, Honey Mol O· 2026 6th International Confe...· 0 citations
Due to the fast proliferation of online news media and social networks, there is a significant increase in the dissemination of misleading data and fake news on digital platforms. Fake news detection is difficult due to the incapacity of deep learning models or conventional machine learning in comprehending semantic and higher-level interactions between news text, news author, publisher, and additional metadata. This results in decreased detection efficiency and enables the dissemination of misinformation that impacts societal behavior and public opinion. To address this problem, a Four-Level Hierarchical Attention Network (4HAN) that incorporates word-, sentence-, and headline-level attention, along with Hypergraph Convolution and Hypergraph Attention, is proposed using the LIAR dataset. By combining semantic feature extraction and relational dependency modeling, the 4HAN framework achieves better results. Results showed a detection accuracy rate of 96.00%, which beats multiple existing methodologies in fake news detection. These findings demonstrate that combining hierarchical attention with hypergraph learning provides more effective semantic and relational representation, leading to improved fake news detection performance and greater robustness in misinformation analysis.
Alpana A. Borse, Gajanan K. Kharate, N. Wasatkar· Journal of Intelligent Decis...· 0 citations
H-FuseNet is proposed, a hybrid multi-representation fusion framework that combines pretrained transformer representations with deception-oriented handcrafted linguistic, stylistic, and semantic features that can improve the reliability of automated fake news detection systems.
A. Mahmood, Marek Sikora, Muhammad Ateeb Ather et al.· Machine Learning and Knowled...· 0 citations
This new era of digitalization comes with great issues of democratic values, breach of people’s trust and hindrances to principles of welfare: distorted facts in media. Unimodal text detection can detect misleading text. However, social media is increasingly used for mismatched information involving many modalities. Mismatched information which includes misleading text along with manipulated images will challenge unimodal text detection. This paper presents an extensive study of fake news detection, which involves manually curated linguistic features, classic machine learning techniques, DL, transfomer, and fusion multimodal. We examine the key multimodal benchmark, the Fakeddit dataset. We also look at text , image based detection systems and multimodal detection systems. Lastly, we analyze the new explainable AI techniques like SHAP and LIME that make the detection systems more clear and trustworthy. We highlight certain research spheres that currently do not feature in the pertinent literature. Examples of these are dual-modality explainability, systems for the field and better integration of explainability in multimodal architectures.
Anurag, Amandeep· International Journal of Enh...· 0 citations
Fake news on social media is increased in recent years. This has led to the requirement for efficient algorithms for detecting fake news. This research proposes SAPGAN-AOA-FND, a novel framework combining a self-attention-based progressive generative adversarial network (SAPGAN) enhanced using the Aquila optimization algorithm (AOA) tailored specifically for fake news identification. The proposed methodology encompasses four key steps: data collection, data pre-processing, feature extraction, and detection. Initially, a fake news dataset is sourced from Kaggle fake news dataset, followed by a rigorous pre-processing phase involving tokenization, stop-word removal, filtering, lemmatization, hashtag removal, lowercasing, stemming, and multi-word grouping. Subsequently, a lexicon hybrid N-gram2vector model is employed for comprehensive feature extraction, encompassing content level, user level, social level, local, and global features. The extracted features are provided to the self-attention-based progressive generative adversarial network (SAPGAN) model, which typically lacks explicit optimization techniques for ensuring accurate fake news detection. To address this gap, the AOA is introduced to enhnce the weight parameters of the SAPGAN technique, enhancing its discriminative capabilities. Furthermore, the proposed approach conducts sentiment analysis to discern positive and negative sentiments within real along fake news. It observes a prevalence of positive sentiment in real news and a greater occurrence of negative sentiment in fake news. The efficiency of SAPGAN-AOA-FND is rigorously evaluated utilizing performance metrics including sensitivity, precision, recall, f-measure, specificity, accuracy, and computational complexity. The proposed technique offers 20.67%, 33.89% and 24.67% higher accuracy and 28.76%, 30.67% and 34.89% higher specificity comparing with existing techniques like Fake news detection using cross modal attention residual with multichannel convolutional neural networks (CARMN-FND), Fake news detection using capsule neural networks (CapNN-FND) and Convolutional neural network utilizing margin loss for fake news detection (CNN-FND), respectively.