The Detection of Fake News in Arabic Tweets Using Deep Learning

Abstract

Fake news has been around for a long time, but the rise of social networking applications over recent years has rapidly increased the growth of fake news among individuals. The absence of adequate procedures to combat fake news has aggravated the problem. Consequently, fake news negatively impacts various aspects of life (economical, social, and political). Many individuals rely on Twitter as a news source, especially in the Arab region. Mostly, individuals are reading and sharing regardless of the truth behind the news. Identifying fake news manually on these open platforms would be challenging as they allow anyone to build networks and publish the news in real time. Therefore, creating an automatic system for recognizing news credibility on social networks relying on artificial intelligence techniques, including machine learning and deep learning, has attracted the attention of researchers. Using deep learning methods has shown promising results in recognizing fake news written in English. Limited work has been conducted in the area of news credibility recognition for the Arabic language. This work proposes a deep learning-based model to detect fake news on Twitter. The proposed model utilizes the news content and social context of the user who participated in the news dissemination. In seeking an effective detection model for fake news, we performed extensive experiments using two deep learning algorithms with varying word embedding models. The experiments were evaluated using a self-created dataset. The experimental results revealed that the MARBERT with the convolutional neural network (CNN) model scores a superior performance in terms of accuracy and an F1-score of 0.956. This finding proves that the proposed model accurately detects fake news in Arabic Tweets relating to various topics.

Detecting Arabic Misinformation Using an Attention Mechanism-Based Model

“…Although the BiLSTM model achieved good results, with precision, recall, and F1-score of 92%, 93%, and 93%, respectively, its performance was lower than that of the Att-BiLSTM model, thus proving the efficacy of the attention mechanism in enhancing the overall model performance. To evaluate the performance of our model, we compared the performance of our proposed model with the baseline models in studies [10,11,12,14] which utilized the same dataset. We compared our model with baseline models in four studies from the related works section that utilized the AraNews dataset and the ArCOV19-Rumors dataset, including:…”

“…In [14], the authors introduce deep learning-based models for identifying fake news within Arabic tweets by exploiting the content of the news in tweets. They conducted experiments using CNN and BiLSTM architecture and investigated the utilization of five distinct word embeddings, including word2vec, FastText, and a BERT-based model for extracting textual features.…”

A Review of Fake News Detection Techniques for Arabic Language

“…Meanwhile, RF outperformed the others using 4-and 5-grams based on accuracy. In study [69], they also relied on a set of extracted features from user and textual features. To extract the textual features, they used both classic word embedding (word2vec, fastText, and Keras embedding layer) and context-based embedding (Multilingual Arabic Bidirectional Encoder Representations from Transformers (MARBERT) and ARBERT) with deep learning models [70].…”

Improving Prediction of Arabic Fake News Using ELMO’s Features-Based Tri-Ensemble Model and LIME XAI

“…The study found that the BiLSTM model was the most accurate compared to other employed models. Alyoubi et al [26] applied deep learning techniques to identify fake news within Arabic tweets. Their model took into account both the content of the news and the social background of the users spreading the news.…”

“…Technique Accuracy [17] QARiB transformer 95% [18] CNN 95% [19] LR using n-gram-level TF-IDF 93% [21] RF 78% [22] CNN-LSTM 91% [23] AFND-CNN-LSTM 70% [24] ARBERT 98% [25] BiLSTM 84% [26] CNN using MARBERT embedding model. 95% Proposed Stacking Classifier (bagging, boosting, baseline) 99%…”