AutoKeras for Fake News Identification in Arabic: Leveraging Deep Learning with an Extensive Dataset DOI Open Access
Raed S. Matti, Suhad A. Yousif

Al-Nahrain Journal of Science, Journal Year: 2023, Volume and Issue: 26(3), P. 60 - 66

Published: Sept. 1, 2023

Social media and the World Wide Web have led to a worrying rise in spreading false information, which presents significant worldwide issue. Identifying preventing information is crucial promoting an informed knowledgeable society. The identification of specifically Arabic dialect, inherent difficulties due its diverse characteristics linguistic intricacies. This study implements AutoKeras, deep learning-based machine learning framework. Using advanced optimization techniques, neural network architecture search, hyperparameter adjustments, model selection can all be automated AutoKeras. Therefore, it suitable for our fake news detection task. methodology employs proficient algorithms natural language processing methods acquire distinct that enable accurate differentiation between genuine news. present uses various sources, including websites, social platforms, blogs, construct dataset. AutoKeras-based approach superior multiple state-of-the-art approaches detecting fabricated Arabic, as evidenced by experimental results. suggested method outperforms 93.2% accuracy identifying news, demonstrating efficacy. demonstrates great promise Auto information.

Language: Английский

Fake news detection: state-of-the-art review and advances with attention to Arabic language aspects DOI Creative Commons
Eman Btoush, Keng Hoon Gan,

Saif A. Ahmad Alrababa

et al.

PeerJ Computer Science, Journal Year: 2025, Volume and Issue: 11, P. e2693 - e2693

Published: March 11, 2025

The proliferation of fake news has become a significant threat, influencing individuals, institutions, and societies at large. This issue been exacerbated by the pervasive integration social media into daily life, directly shaping opinions, trends, even economies nations. Social platforms have struggled to mitigate effects news, relying primarily on traditional methods based human expertise knowledge. Consequently, machine learning (ML) deep (DL) techniques now play critical role in distinguishing necessitating their extensive deployment counter rapid spread misinformation across all languages, particularly Arabic. Detecting Arabic presents unique challenges, including complex grammar, diverse dialects, scarcity annotated datasets, along with lack research field detection compared English. study provides comprehensive review examining its types, domains, characteristics, life cycle, approaches. It further explores recent advancements leveraging ML, DL, transformer-based for detection, special attention delves Arabic-specific pre-processing techniques, methodologies tailored language, datasets employed these studies. Additionally, it outlines future directions aimed developing more effective robust strategies address challenge content.

Language: Английский

Citations

0
Deep learning and sentence embeddings for detection of clickbait news from online content DOI Creative Commons

Amara Muqadas,

Hikmat Ullah Khan, Muhammad Ramzan

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 17, 2025

With the rise of user-generated content, ensuring authenticity and originality online information has become increasingly challenging. Artificial intelligence (AI) Natural Language Processing (NLP) play a crucial role in large-scale content analysis moderation. However, widespread use clickbait-sensational or misleading headlines designed to maximize engagement-undermines reliability shared information. The existing studies focus on news clickbait detection from English using NLP techniques. To best our knowledge, this study is novel Urdu language content. We propose state art deep features including sentence embeddings be applied as input learning models. dataset prepared authentic source, labelled by domain experts, pre-processed standard steps. In contrast, traditional models, machine ensemble learning, utilize textual word embedding are used baseline models for comparing performance proposed approaches. All evaluated measures, accuracy, precision, recall, F1-score, ROC curve analysis, determine their effectiveness identifying headlines. results show that Bi-LSTM model with achieved highest accuracy 88% identification low resource language.

Language: Английский

Citations

0
AutoKeras for Fake News Identification in Arabic: Leveraging Deep Learning with an Extensive Dataset DOI Open Access
Raed S. Matti, Suhad A. Yousif

Al-Nahrain Journal of Science, Journal Year: 2023, Volume and Issue: 26(3), P. 60 - 66

Published: Sept. 1, 2023

Social media and the World Wide Web have led to a worrying rise in spreading false information, which presents significant worldwide issue. Identifying preventing information is crucial promoting an informed knowledgeable society. The identification of specifically Arabic dialect, inherent difficulties due its diverse characteristics linguistic intricacies. This study implements AutoKeras, deep learning-based machine learning framework. Using advanced optimization techniques, neural network architecture search, hyperparameter adjustments, model selection can all be automated AutoKeras. Therefore, it suitable for our fake news detection task. methodology employs proficient algorithms natural language processing methods acquire distinct that enable accurate differentiation between genuine news. present uses various sources, including websites, social platforms, blogs, construct dataset. AutoKeras-based approach superior multiple state-of-the-art approaches detecting fabricated Arabic, as evidenced by experimental results. suggested method outperforms 93.2% accuracy identifying news, demonstrating efficacy. demonstrates great promise Auto information.

Language: Английский

Citations

5