Arabic Fake News Detection: Comparative Study of Neural Networks and Transformer-Based Approaches
Al-Yahya, Maha . 2021
Fake news detection (FND) involves predicting the likelihood that a particular news article (news report, editorial, expose, etc.) isintentionally deceptive. Arabic FND started to receive more attention in the last decade, and many detection approachesdemonstrated some ability to detect fake news on multiple datasets. However, most existing approaches do not consider recentadvances in natural language processing, i.e., the use of neural networks and transformers. +is paper presents a comprehensivecomparative study of neural network and transformer-based language models used for Arabic FND. We examine the use of neuralnetworks and transformer-based language models for Arabic FND and show their performance compared to each other. We alsoconduct an extensive analysis of the possible reasons for the difference in performance results obtained by different approaches.+e results demonstrate that transformer-based models outperform the neural network-based solutions, which led to an increasein the F1 score from 0.83 (best neural network-based model, GRU) to 0.95 (best transformer-based model, QARiB), and it boostedthe accuracy by 16% compared to the best in neural network-based solutions. Finally, we highlight the main gaps in Arabic FNDresearch and suggest future research directions
Abstract: In the domain of law and legal systems, jurisprudence principles (JPs) are considered major sources of legislative reasoning by jurisprudence scholars. Generally accepted JPs are often…
ABSTRACT Conversational AI is one of the most active research areas in AI, and it has gained more attention from academia as well as industry.
Abstract: Task-oriented dialogue systems (DS) are designed to help users perform daily activities using natural language. Task-oriented DS for English language have demonstrated promising…