3 August 2022 in Cluster Computing
1 April 2019 in The Electronic Library
Purpose: This paper aims to propose a new efficient semantic recommender method for Arabic content.Design/methodology/approach: Three semantic similarities were proposed to be integrated with the recommender system to improve its ability to recommend based on the semantic aspect. The proposed similarities are CHI-based semantic similarity, singular value decomposition (SVD)-based semantic similarity and Arabic WordNet-based semantic similarity. These similarities were compared with the existing similarities used by recommender systems from the literature.Findings: Experiments show that the proposed semantic method using CHI-based similarity and using SVD-based similarity are more efficient than the existing methods on Arabic text in term of accuracy and execution time.Originality/value: Although many previous works proposed recommender system methods for English text, very few works concentrated on Arabic Text. The field of Arabic Recommender Systems is largely understudied in the literature. Aside from this, there is a vital need to consider the semantic relationships behind user preferences to improve the accuracy of the recommendations. The contributions of this work are the following. First, as many recommender methods were proposed for English text and have never been tested on Arabic text, this work compares the performance of these widely used methods on Arabic text. Second, it proposes a novel semantic recommender method for Arabic text. As this method uses semantic similarity, three novel base semantic similarities were proposed and evaluated. Third, this work would direct the attention to more studies in this understudied topic in the literature.
13 December 2018 in Multimedia Tools and Applications
1 March 2022 in Recent Advances in Computer Science and Communications
Introduction: Stemming is an important preprocessing step in text classification, and could contribute in increasing text classification accuracy. Although many works proposed stemmers for English language, few stemmers were proposed for Arabic text. Arabic language has gained increasing attention in the previous decades and the need is vital to further improve Arabic text classification. Method: This work combined the use of the recently proposed P-Stemmer with various classifiers to find the optimal classifier for the P-stemmer in term of Arabic text classification. As part of this work, a synthesized dataset was collected. Result: The previous experiments show that the use of P-Stemmer has a positive effect on classification. The degree of improvement was classifier-dependent, which is reasonable as classifiers vary in their methodologies. Moreover, the experiments show that the best classifier with the P-Stemmer was NB. This is an interesting result as this classifier is wellknown for its fast learning and classification time. Discussion: First, the continuous improvement of the P-Stemmer by more optimization steps is necessary to further improve the Arabic text categorization. This can be made by combining more classifiers with the stemmer, by optimizing the other natural language processing steps, and by improving the set of stemming rules. Second, the lack of sufficient Arabic datasets, especially large ones, is still an issue. Conclusion: In this work, an improved P-Stemmer was proposed by combining its use with various classifiers. In order to evaluate its performance, and due to the lack of Arabic datasets, a novel Arabic dataset was synthesized from various online news pages. Next, the P-Stemmer was combined with Naïve Bayes, Random Forest, Support Vector Machines, KNearest Neighbor, and K-Star.
12 March 2024 in Cluster Computing
Artificial intelligence (AI) approaches have been shown to be effective in classifying skin diseases and outperforming dermatologists in diagnosis. Using big data as a dermatological diagnosis service can present several challenges. One challenge is the need to accurately label and classify large amounts of data, such as images of infected skin. This can be time-consuming and resource-intensive. It is important to implement proper safeguards to protect sensitive medical information. Despite these challenges, the use of big data in dermatology can lead to several outcomes. It can improve the accuracy of diagnoses, leading to better patient outcomes. It can also help to identify patterns and trends in skin conditions, allowing for earlier detection and prevention. In addition, big data can be used to identify risk factors for certain conditions, enabling targeted preventative measures. Convolutional neural networks (CNNs) have been widely used for skin lesion classification, and recent advances in machine learning algorithms have led to a decrease in misclassification rates compared to manual categorization by dermatologists. This article utilizes the use of big data for accurate dermatological diagnosis services, it introduces the use of various CNNs for classifying different types of skin cancer. While deep learning and pretrained transfer learning techniques have advantages over traditional methods, they also have limitations and the potential for incorrect identification under certain circumstances. This work discusses these vulnerabilities and employs pretrained models to classify 11 different skin diseases, including monkey pox. The performance of the system is evaluated using accuracy, loss, precision, recall, and F1 score, and the results show that the system is able to diagnose the 11 skin illnesses with an accuracy rate of 97% using transfer learning in Keras and computer vision models. The best model was found to be Inception_ResNetV2 with 50 epochs and the Adam optimizer.
20 July 2023 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Lately, the use of the Internet has led to an increase in social networking sites. The world has become an open environment, and social networking sites have been increasingly used to exchange medical experiences, and they have been adopted in many cases as basic references in obtaining medical advice, which has led to the misuse of medicines. A growing problem, abuse of prescription medications can have a negative impact on all age groups and come with adverse health consequences, as individuals in societies become susceptible to many drug interactions and serious side effects and reduced drug efficacy, which makes a simple health problem turn into a complex health problem; our study aims to classify drug use in Arabic content in social media (use, abuse) by using both Machine Learning (ML) algorithms and AraBERT model. Many studies detect the drug abuse in the English language. There are no studies on Arabic language. Arabic social media dataset was created from Facebook with nearly 7,000 posts. We used different ML classifiers; the most famous of them are Support Vector Machine (SVM), Decision Tree (J48), Naive Bayes (NB), K-Nearest Neighbor (KNN) and Random Forest (RF). We also applied AraBERT based model; CNN-AraBERT, RNN-AraBERT, and LSTM-AraBERT. The classifier's accuracy was evaluated by calculating the F1-Measure, Recall, and Precision measurements. The results indicated that CNN-AraBERT classifier is given the highest value of F1-Measure for Facebook dataset for both classification tasks with (98.3%) for binary classification and (90.99%) for multi-classification.