Arabic diacritics are signs used in Arabic orthography to represent essential morphophonological and syntactic information. It is a common practice to leave out those diacritics in written Arabic. Most Arabic electronic texts lack such diacritics. The processing of those texts for various puposes of Natural Language Processing is a complicated task. Diacritized words are necessary for applications such as machine translation, sentiment analysis, and speech synthesis. To address this problem, several studies proposed automatic systems to restore diacritics in Arabic texts. The present paper presents an in-depth survey of 56 most recent Arabic diacritization studies. The studies encompassed in this survey have been selected from the following databases: IEEE Xplore, Clarivate, Analytics, Google Scholar, and Science Direct. Based on the diacritization approach, the studies are grouped into four sections in terms of method; rule-based, simple statistical, hybrid, and Neural Networks. While rule-based methods such as morphological analyzers and lexicon retrievals were the earliest approaches, results indicated that they are still valuable tools that can aid in the process of diaciritization. Effective statistical methods that produced diacritics with acceptable accuracy include Hidden Markov Model, n-grams, and Support Vector Machines. They are often accompanied by either rule-based or neural networks in hybrid systems. Neural networks, specifically Bidirectional Long Short Term Memory, reached very high diacritization accuracy levels. Studies employing neural networks focused on evaluating and comparing the efficacy of several types of neural networks or a hybrid of them, testing alternatives of input units or suggested schemes for partial daicritization. The study synthesizes the results of the studies, identifies research gaps, and offers recommendations for future research.

The use of glosses to aid vocabulary learning in second languages has been one of the most actively studied areas in computer-assisted language learning (CALL) literature. To compile research articles that examine the effect of utilizing glosses on second language (L2) vocabulary learning, the present study employed a second-order meta-analysis technique. The second-order meta-analysis is a study that synthesizes and analyzes the findings of multiple meta-analyses rather than individual primary studies, providing a higher level of abstraction and overview of existing evidence. The study synthesizes the results from seven primary meta-analyses conducted between 2008 and 2023, which included 136 original studies. Results showed that the overall mean effect size for using glosses was medium (g = 0.63 for the fixed-effect size model and 0.76 for the random-effect size model). The results showed that moderators had a significantly mitigated the effects of multimedia glosses. In particular, beginner-level students benefited greatly from being exposed to multimedia glosses, resulting in a large effect size. Additionally, the recognition test tended to produce a higher effect size compared to other types of vocabulary tests. Furthermore, glossing was found to be more effective in improving vocabulary acquisition in expository texts rather than narrative texts. Moreover, single-mode glosses were reported to be more effective than multi-mode glosses. The findings indicated that in-text glosses, out-text glosses, and bottom glosses exhibited a small effect size, whereas pop-up and margin glosses demonstrated a medium effect size. Implications for language learning and suggestions for future meta-analytic research are provided.

Scholars have debated whether comprehensive or focused written corrective feedback is more beneficial for EFL learners; however, learner preferences have not been sufficiently explored. Therefore, this study examined adult EFL learners' preferences and perceptions regarding teachers' written corrective feedback, focusing on a number of key aspects: perceived importance, preferred degree of comprehensiveness, preferred focus, preferred timing, preferred type (direct vs. indirect), and method of presenting feedback. A mixed-methods approach was employed, using a questionnaire to obtain quantitative data from 143 Saudi EFL learners enrolled at a Saudi university. Additionally, retrospective semi-structured interviews were conducted to obtain qualitative data from a subset of 49 participants. The findings revealed that participants highly valued teacher feedback and recognized its vital role in their writing development. As opposed to the prevalent assumption that "less is more," participants collectively preferred comprehensive feedback that addresses various aspects of writing, including language, content, organization, and overall quality. They preferred feedback on the multiple drafts, particularly regarding content and organization. Moreover, participants preferred a combination of direct and indirect feedback methods, offering specific guidance, detailed explanations, and opportunities for self-correction. Participants emphasized the importance of clear, specific, and actionable feedback and the motivational impact of positive and encouraging comments. The preferences for comprehensive feedback and explicit guidance are crucial for informing EFL teaching practices and curriculum development. Furthermore, pedagogical implications and practical recommendations are discussed.

The study of sentiment in Natural Language Processing (NLP) is among the most successful research areas because of the availability of millions of user opinions online since the turn of the century. The economic, political, and medical fields are just some of the many that have benefited from studies of sentiment research. While numerous studies have examined more mainstream topics like consumer electronics, movies, and restaurants, relatively few have examined health and medical concerns. Considerable insight into where to direct efforts to improve public health might be gained by a study of how people feel about healthcare as a whole and of individual drug experiences in particular. When it comes to medicine, automatic analysis of online user evaluations paves the way for sifting through massive amounts of user feedback to find information regarding medications' efficacy and side effects that might be used to enhance pharmacovigilance programs. Simple rules-based methods have given way to more complex machine learning approaches like deep learning, which is developing as a technology for many natural language processing jobs. The opensource datasets have been analyzed with models that use word embeddings and term frequency-inverse document frequency (TF-IDF). A feature-enhanced text-inception model for sentiment classification was presented to work in tandem with this approach. The model first employed a cutting-edge text-inception module to glean useful shallow features from the text. K-MaxPooling was subsequently employed to reduce the dimensionality of its shallow and deep includes as well as enhance the generalization of characteristics, and a deep feature extraction module was formed using the bidirectional gated recurrent unit (Bi-GRU) and the capsule neural network to comprehend the text's semantic data. By combining traditional methods with cutting-edge artificial intelligence techniques, this hybrid approach can revolutionize public health initiatives, decision-making, and pharmacovigilance in the healthcare industry. This model achieved an exceptional accuracy rate of 99%, underscoring its effectiveness in sentiment classification and demonstrating its potential to significantly contribute to advancing healthcare and medical research.