Recently, the phenomenon of the spread of fake news or misinformation in most fields has taken on a wide resonance in societies. Combating this phenomenon and detecting misleading information manually is rather boring, takes a long time, and impractical. It is therefore necessary to rely on the fields of artificial intelligence to solve this problem. As such, this study aims to use deep learning techniques to detect Arabic fake news based on Arabic dataset called the AraNews dataset. This dataset contains news articles covering multiple fields such as politics, economy, culture, sports and others. A Hybrid Deep Neural Network has been proposed to improve accuracy. This network focuses on the properties of both the Text-Convolution Neural Network (Text-CNN) and Long Short-Term Memory (LSTM) architecture to produce efficient hybrid model. Text-CNN is used to identify the relevant features, whereas the LSTM is applied to deal with the long-term dependency of sequence. The results showed that when trained individually, the proposed model outperformed both the Text-CNN and the LSTM. Accuracy was used as a measure of model quality, whereby the accuracy of the Hybrid Deep Neural Network is (0.914), while the accuracy of both Text-CNN and LSTM is (0.859) and (0.878), respectively. Moreover, the results of our proposed model are better compared to previous work that used the same dataset (AraNews dataset).

No abstract

In the context of the great change in the labor market and the higher education sector, great attention is given to individuals with an academic degree or the so-called graduates class. However, each educational institution has a different approach towards students who wish to complete their university degree. This study aims at (1) identifying the most important factors that directly affect the completion, and (2) predicting the completion rates of students for university degrees according to the system of higher education in the United States. Unlike previous studies, this project contributes to the use of the fuzzy logic technique on three methods for feature selection, namely the Correlation Attribute Evaluation, Relief Attribute Evaluation, and Gain Ratio Method. Since these three methods give different weight to the same attribute, the fuzzy logic technique has been used to get one weight for the attribute. A great challenge faced throughout this study is the curse of dimensionality, because the college scorecard dataset launched by the US Department of Education contains approximately (8000) educational institutions and (1825) features. Applying the method used in this study to identify important features lead to their reduction to only (79). Accordingly, two models have been used to predict the completion rates of students for their university studies which are the Random Forest and the Support Vector Regression with a Mean Absolute Error (MAE) value of (0.068) and (0.097) respectively.

 In conjunction with the global concern regarding the spread of fake news on social media, there is a large flow of research to address this phenomenon. The wide growth in social media and online forums has made it easy for legitimate news to merge with comprehensive misleading news, negatively affecting people’s perceptions and misleading them. As such, this study aims to use deep learning, pre-trained models, and machine learning to predict Arabic and English fake news based on three public and available datasets: the Fake-or-Real dataset, the AraNews dataset, and the Sentimental LIAR dataset. Based on GloVe (Global Vectors) and FastText pre-trained models, A hybrid network has been proposed to improve the prediction of fake news. In this proposed network, CNN (Convolution Neural Network) was used to identify the most important features. In contrast, BiGRU (Bidirectional Gated Recurrent Unit) was used to measure the long-term dependency of sequences. Finally, multi-layer perceptron (MLP) is applied to classify the article news as fake or real. On the other hand, an Improved Random Forest Model is built based on the embedding values extracted from BERT (Bidirectional Encoder Representations from Transformers) pre-trained model and the relevant speaker-based features. These relevant features are identified by a fuzzy model based on feature selection methods. Accuracy was used as a measure of the quality of our proposed models, whereby the prediction accuracy reached 0.9935, 0.9473, and 0.7481 for the Fake-or-Real dataset, AraNews dataset, and Sentimental LAIR dataset respectively. The proposed models showed a significant improvement in the accuracy of predicting Arabic and English fake news compared to previous studies that used the same datasets.