#
A Novel Deep Learning ArCAR System for Arabic Text Recognition with Character-Level Representation^{ †}

^{1}

^{2}

^{3}

^{4}

^{*}

^{†}

## Abstract

**:**

## 1. Introduction

## 2. Related Works

#### 2.1. Representation

#### 2.2. Classification

## 3. Proposed Model

#### 3.1. Architecture

#### 3.2. Machine Learning

#### 3.3. Deep Learning

## 4. Experimental Analysis

^{2}, TensorFlow, and Kera’s. We used a classification system based on CNN and character level representation to classify Arabic text.

#### 4.1. Dataset

#### 4.2. Implementation Environment

#### 4.3. Evaluation Metrics

## 5. Results and Discussion

#### 5.1. Machine Learning

#### 5.2. Our Proposed Deep Learning

## 6. Conclusions

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Conflicts of Interest

## References

- Hakak, S.; Kamsin, A.; Tayan, O.; Idris, M.Y.I.; Gilkar, G.A. Approaches for preserving content integrity of sensitive online Arabic content: A survey and research challenges. Inf. Process. Manag.
**2019**, 56, 367–380. [Google Scholar] [CrossRef] - Elnagar, A.; Al-Debsi, R.; Einea, O. Arabic text classification using deep learning models. Inf. Process. Manag.
**2020**, 57, 102121. [Google Scholar] [CrossRef] - Ameur, M.; Belkebir, R.; Guessoum, A. Robust Arabic Text Categorization by Combining Convolutional and Recurrent Neural Networks. ACM Trans. Asian Low-Resour. Lang. Inf. Process. (TALLIP)
**2020**, 19, 1–16. [Google Scholar] [CrossRef] - Harrat, S.; Meftouh, K.; Smaili, K. Machine translation for Arabic dialects (survey). Inf. Process. Manag.
**2019**, 56, 262–273. [Google Scholar] [CrossRef] [Green Version] - Bounhas, I.; Soudani, N.; Slimani, Y. Building a morpho-semantic knowledge graph for Arabic information retrieval. Inf. Process. Manag.
**2020**, 57, 102124. [Google Scholar] [CrossRef] - Daif, M.; Kitada, S.; Iyatomi, H. AraDIC: Arabic Document Classification using Image-Based Character Embeddings and Class-Balanced Loss. arXiv
**2020**, arXiv:2006.11586. [Google Scholar] - Etaiwi, W.; Awajan, A. Graph-based Arabic text semantic representation. Inf. Process. Manag.
**2020**, 57, 102183. [Google Scholar] [CrossRef] - Almuzaini, G.H.A.; Azmi, A.M. Impact of stemming and word embedding on deep learning-based Arabic text categorization. IEEE Access
**2020**, 8, 127913–127928. [Google Scholar] [CrossRef] - Oueslati, O.; Cambria, E.; HajHmida, M.B.; Ounelli, H. A review of sentiment analysis research in Arabic language. Future Gener. Comput. Syst.
**2020**, 112, 408–430. [Google Scholar] [CrossRef] - Al-Taani, A.T.; Al-Sayadi, S.H. Classification of Arabic Text Using Singular Value Decomposition and Fuzzy C-Means Algorithms. In Applications of Machine Learning; Springer: Berlin, Germany, 2020; pp. 111–123. [Google Scholar]
- Zhang, X.; Zhao, J.; LeCun, Y. Character-level convolutional networks for text classification. In Advances in Neural Information Processing Systems; NeurIPS Proceedings; Palais Des Congrès De Montréal: Montréal, QC, Canada, 2015; pp. 649–657. [Google Scholar]
- Muaad, A.Y.; Jayappa, H.; Al-antari, M.A.; Lee, S. ArCAR: A Novel Deep Learning ComputerAided Recognition for CharacterLevel Arabic Text Representation and Recognition. Algorithms
**2021**, 14, 216. [Google Scholar] [CrossRef] - Al-Antari, M.A.; Hua, C.H.; Bang, J.; Lee, S. Fast deep learning computer-aided diagnosis of COVID-19 based on digital chest X-ray images. Appl. Intell.
**2020**, 51, 2890–2907. [Google Scholar] [CrossRef] [PubMed] - Hanumanthappa, J.; Muaad, A.Y.; Bibal Benifa, J.V.; Chola, C.; Hiremath, V.; Pramodha, M. IoT-Based Smart Diagnosis System for HealthCare. In Sustainable Communication Networks and Application; Karrupusamy, P., Balas, V.E., Shi, Y., Eds.; Lecture Notes on Data Engineering and Communications Technologies; Springer: Singapore, 2022; Volume 93. [Google Scholar] [CrossRef]
- Muaad, A.Y.; Hanumanthappa, J.; Al-antari, M.A.; JV, B.B.; Chola, C. AI-based Misogyny Detection from Arabic Levantine Twitter Tweets. Algorithms
**2021**, 14, 4–11. [Google Scholar]

Class Name | No. of Documnet |
---|---|

Finance | 6500 |

Sports | 6500 |

Culture | 6500 |

Technology | 6500 |

Politics | 6500 |

Medical | 6500 |

Religion | 6500 |

Classifiers | BOW without Pre | BOW with Pre | TFIDF without Pre | TFIDF with Pre |
---|---|---|---|---|

Multinomial NB | 88 | 88 | 64 | 58 |

Bernoulli NB | 61 | 73 | 61 | 73 |

Logistic Regression | 92 | 92 | 90 | 91 |

SGD Classifier | 91 | 91 | 93 | 92 |

SVC | 90 | 91 | 90 | 92 |

Linear SVC | 92 | 91 | 93 | 92 |

Metrics | Accuracy | F Measure-Score | Precision | Recall |
---|---|---|---|---|

AlKhaleej data | 97.47 | 92.63 | 92.75 | 92 |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Muaad, A.Y.; Al-antari, M.A.; Lee, S.; Davanagere, H.J.
A Novel Deep Learning ArCAR System for Arabic Text Recognition with Character-Level Representation. *Comput. Sci. Math. Forum* **2022**, *2*, 14.
https://doi.org/10.3390/IOCA2021-10903

**AMA Style**

Muaad AY, Al-antari MA, Lee S, Davanagere HJ.
A Novel Deep Learning ArCAR System for Arabic Text Recognition with Character-Level Representation. *Computer Sciences & Mathematics Forum*. 2022; 2(1):14.
https://doi.org/10.3390/IOCA2021-10903

**Chicago/Turabian Style**

Muaad, Abdullah Y., Mugahed A. Al-antari, Sungyoung Lee, and Hanumanthappa Jayappa Davanagere.
2022. "A Novel Deep Learning ArCAR System for Arabic Text Recognition with Character-Level Representation" *Computer Sciences & Mathematics Forum* 2, no. 1: 14.
https://doi.org/10.3390/IOCA2021-10903