Fake news detection (FND) involves predicting the likelihood that a particular news article (news report, editorial, expose, etc.) is intentionally deceptive. Arabic FND started to receive more attention in the last decade, and many detection approaches demonstrated some ability to detect fake news on multiple datasets. However, most existing approaches do not consider recent advances in natural language processing, i.e., the use of neural networks and transformers. This paper presents a comprehensive comparative study of neural network and transformer‐based language models used for Arabic FND. We examine the use of neural networks and transformer‐based language models for Arabic FND and show their performance compared to each other. We also conduct an extensive analysis of the possible reasons for the difference in performance results obtained by different approaches. The results demonstrate that transformer‐based models outperform the neural network‐based solutions, which led to an increase in the F1 score from 0.83 (best neural network‐based model, GRU) to 0.95 (best transformer‐based model, QARiB), and it boosted the accuracy by 16% compared to the best in neural network‐based solutions. Finally, we highlight the main gaps in Arabic FND research and suggest future research directions.

With recent advancements in Semantic Web technologies, a new trend in MCQ item generation has emerged through the use of ontologies. Ontologies are knowledge representation structures that formally describe entities in a domain and their relationships, thus enabling automated inference and reasoning. Ontology-based MCQ item generation is still in its infancy, but substantial research efforts are being made in the field. However, the applicability of these models for use in an educational setting has not been thoroughly evaluated. In this paper, we present an experimental evaluation of an ontology-based MCQ item generation system known as OntoQue. The evaluation was conducted using two different domain ontologies. The findings of this study show that ontology-based MCQ generation systems produce satisfactory MCQ items to a certain extent. However, the evaluation also revealed a number of shortcomings with current ontology-based MCQ item generation systems with regard to the educational significance of an automatically constructed MCQ item, the knowledge level it addresses, and its language structure. Furthermore, for the task to be successful in producing high-quality MCQ items for learning assessments, this study suggests a novel, holistic view that incorporateslearning content, learning objectives, lexical knowledge,andscenariosinto a single cohesive framework.

Conversational AI is one of the most active research areas in AI, and it has gained more attention from academia as well as industry. Given recent advancements in several conversational AI systems in addition to the availability of several datasets, the aim of this study is to explore the landscape of Arabic text-based conversational AI systems. In this work, we provide a thorough review of recent Arabic conversational AI systems. We group them into three categories based on their functionality: (1) question-answering (QA) systems, (2) task-oriented dialogue systems (DS), and (3) chatbots. Furthermore, we describe the common datasets used in building and evaluating conversational AI systems in Arabic. Few surveys have targeted the conversational AI field for the Arabic language, and we aim to cover this gap with this study. Our contribution focuses on reviewing and analyzing the literature in the field and highlighting future research directions towards human-like conversational AI systems in Arabic.

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 performance outcomes; however, developing such systems to support Arabic remains a challenge. This challenge is mainly due to the lack of Arabic dialogue datasets. This study introduces the first Arabic end-to-end generative model for task-oriented DS (AraConv), which uses the multi-lingual transformer model mT5 with different settings. We also present an Arabic dialogue dataset (Arabic-TOD) and used it to train and test the proposed AraConv model. The results obtained are reasonable compared to those reported in the studies of English and Chinese using the same mono-lingual settings. To avoid problems associated with a small training dataset and to improve the AraConv model’s results, we suggest joint-training, in which the model is jointly trained on Arabic dialogue data and data from one or two high-resource languages such as English and Chinese. The findings indicate the AraConv model performed better in the joint-training setting than in the mono-lingual setting. The results obtained from AraConv on the Arabic dialogue dataset provide a baseline for other researchers to build robust end-to-end Arabic task-oriented DS that can engage with complex scenarios.

Fake news detection (FND) remains a challenge due to its vast and varied sources, especially on social media platforms. While numerous attempts have been made by academia and the industry to develop fake news detection systems, research on Arabic content remains limited. This study investigates transformer-based language models for Arabic FND. While transformer-based models have shown promising performance in various natural language processing tasks, they often struggle with tasks involving complex linguistic patterns and cultural contexts, resulting in unreliable performance and misclassification problems. To overcome these challenges, we investigated an ensemble of transformer-based models. We experimented with five Arabic transformer models: AraBERT, MARBERT, AraELECTRA, AraGPT2, and ARBERT. Various ensemble approaches, including a weighted-average ensemble, hard voting, and soft voting, were evaluated to determine the most effective techniques for boosting learning models and improving prediction accuracies. The results of this study demonstrate the effectiveness of ensemble models in significantly boosting the baseline model performance. An important finding is that ensemble models achieved excellent performance on the Arabic Multisource Fake News Detection (AMFND) dataset, reaching an F1 score of 94% using weighted averages. Moreover, changing the number of models in the ensemble has a slight effect on the performance. These key findings contribute to the advancement of fake news detection in Arabic, offering valuable insights for both academia and the industry

Written Medicine Information (WMI) is one of the sources that patients use to obtain information concerning medicine. This paper aims to assess the readability of two types of WMIs in Arabic language based on vocabulary use and sentence structure using a panel of experts and consumers. This is a descriptive study. Two different types of materials, including the online text from King Abdullah Bin Abdulaziz Arabic Health Encyclopaedia (KAAHE) and medication leaflets submitted by the manufacturers to the Saudi Food and Drug Authority (SFDA) were evaluated. We selected a group of sentences from each WMI. The readability was assessed by experts (n = 5) and consumers (n = 5). The sentence readability of each measured using a specific criteria and rated as 1 = easy, 2 = intermediate, or 3 = difficult. A total of 4476 sentences (SFDA 2231; KAHEE 2245) extracted from websites or patient information leaflets on 50 medications and evaluated. The majority of the vocabulary and sentence structure was considered easy by both expert (SFDA: 68%; KAAHE: 76%) and consumer (SFDA: 76%; KAAHE: 84%) groups. The sentences with difficult or intermediate vocabulary and sentence structure are derived primarily from the precautions and side effects sections. The SFDA and KAAHE WMIs are easy to read and understand as judged by our study sample. However; there is room for improvement, especially in sections related to the side effects and precautions.