A systematic review of text classification research based on deep learning models in Arabic language

Wahdan, Ahlam; Hantoobi, Sendeyah; Salloum, Said A.; Shaalan, Khaled

doi:10.11591/ijece.v10i6.pp6629-6643

Cited by 38 publications

(34 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, reviews are helpful to ease and expand the development of theory, important to fill research gaps when it is mandatory, or lock the research area where a plethora of literature is available [53]. Systematic review is providing the support researchers, to become familiar with their research topic [11] and previous concepts [54][55][56][57][58]. Unlike the traditional or narrative review, Systematic reviews are more rigorous, and suggest well-defined methods to analyze the literature of specific topic [11].…”

Section: Methodsmentioning

confidence: 99%

The Role of Technology Acceptance in Healthcare to Mitigate COVID-19 Outbreak

AlQudah

Salloum

Shaalan

2021

Studies in Systems, Decision and Control

Self Cite

View full text Add to dashboard Cite

The recent decade has included huge achievements in the development for information technologies in healthcare. Now, these technologies can be employed as part of the response to the COVID-19 pandemic. Information technologies in healthcare are crucial to store, manage and exchange the clinical data. On the other hand, the success or failure of a specific technology relies on the acceptance to use that technology. There is a need to assess the user's technology acceptance prior to the development or improvements for that technology. The study objective is to systematically review the studies that empirically had evaluated the acceptance of technology in healthcare through the technology acceptance model (TAM), its extensions and integrated models based on it. Also, the study will highlight the various studied technologies in healthcare arena, and how these technologies can be utilized to provide the health services, as a respond to the on-going pandemic. PRISMA guidelines were used to perform the review; and the search process has been completed using six digital libraries: Google Scholar, PubMed, IEEE Xplore, Springer Link, ACM, and Science Direct. Out of 1768 studies, a total of 99 empirical studies were found to be eligible and included in this study. A thorough statistical analysis was achieved, to understand the situation of technology acceptance as in the recent decade. The analysis included the key factors, as they were extensively utilized to clarify the technology acceptance, along with the key confirmed hypotheses to build robust and valid technology acceptance models in healthcare. It was found that electronic records, tele-medicine and mobile health solutions have attracted the most of researchers in the last ten years. Where the acceptance of those solutions was explored, through various user types and settings, within different countries particularly Taiwan and the United States; who are leading this research domain.

show abstract

Section: Methodsmentioning

confidence: 99%

The Role of Technology Acceptance in Healthcare to Mitigate COVID-19 Outbreak

AlQudah

Salloum

Shaalan

2021

Studies in Systems, Decision and Control

Self Cite

View full text Add to dashboard Cite

show abstract

“…Note that transfer learning is indeed valuable for handling insufficient data for a new domain in the neural network, and there is a big pre-existing data pool that can be transferred to the problem to be solved. The benefit of this approach is that much less data is needed, which significantly reduces the computational time (Razak et al, 2020a;Razak et al, 2020b;Wahdan et al, 2020;Yang et al, 2013).…”

Section: Literature Reviewmentioning

confidence: 99%

Arabic Handwriting Classification using Deep Transfer Learning Techniques

Almisreb¹,

Tahir²,

Turaev³

et al. 2022

JST

View full text Add to dashboard Cite

Arabic handwriting is slightly different from the handwriting of other languages; hence it is possible to distinguish the handwriting written by the native or non-native writer based on their handwriting. However, classifying Arabic handwriting is challenging using traditional text recognition algorithms. Thus, this study evaluated and validated the utilisation of deep transfer learning models to overcome such issues. Hence, seven types of deep learning transfer models, namely the AlexNet, GoogleNet, ResNet18, ResNet50, ResNet101, VGG16, and VGG19, were used to determine the most suitable model for classifying the handwritten images written by the native or non-native. Two datasets comprised of Arabic handwriting images were used to evaluate and validate the newly developed deep learning models used to classify each model’s output as either native or foreign (non-native) writers. The training and validation sets were conducted using both original and augmented datasets. Results showed that the highest accuracy is using the GoogleNet deep learning model for both normal and augmented datasets, with the highest accuracy attained as 93.2% using normal data and 95.5% using augmented data in classifying the native handwriting.

show abstract

“…Researchers were interested in investigating these metadata for search purposes [17,18,[22][23][24][25]. In this section, a number of research papers that explored the analysis and classification of Twitter metadata were surveyed to investigate different text classification approaches [26] and the text classification results.…”

Section: Literature Reviewmentioning

confidence: 99%