Attention-Enriched Mini-BERT Fake News Analyzer Using the Arabic Language

Abstract

Internet use resulted in people becoming more reliant on social media. Social media have become the main source of fake news or rumors. They spread uncertainty in each sector of the real world, whether in politics, sports, or celebrities’ lives—all are affected by the uncontrolled behavior of social media platforms. Intelligent methods used to control this fake news in various languages have already been much discussed and frequently proposed by researchers. However, Arabic grammar and language are a far more complex and crucial language to learn. Therefore, work on Arabic fake-news-based datasets and related studies is much needed to control the spread of fake news on social media and other Internet media. The current study uses a recently published dataset of Arabic fake news annotated by experts. Further, Arabic-language-based embeddings are given to machine learning (ML) classifiers, and the Arabic-language-based trained minibidirectional encoder representations from transformers (BERT) is used to obtain the sentiments of Arabic grammar and feed a deep learning (DL) classifier. The holdout validation schemes are applied to both ML classifiers and mini-BERT-based deep neural classifiers. The results show a consistent improvement in the performance of mini-BERT-based classifiers, which outperformed ML classifiers, by increasing the training data. A comparison with previous Arabic fake news detection studies is shown where results of the current study show greater improvement.