A Novel Deep Learning ArCAR System for Arabic text Recognition with Character-Level Representation

AI-based Arabic text recognition is a process to simultaneously classify the different contextual Arabic contents into a proper category for easy understanding. With the increasing number of Arabic texts in our social life, traditional machine learning approaches are facing different challenges due to the complexity of morphology and the variation delicate of the Arabic language. In this study, a novel deep learning Arabic text computer-aided recognition (ArCAR) is proposed to represent and recognize Arabic text at the character level based on the capability of a deep convolutional neural network (CNN). The proposed ArCAR system is validated using five-fold cross-validation tests for two applications: (1) Arabic text document classification and (2) Arabic sentiment analysis. For document classification, we use nine different datasets in the multiclass problem, while four different datasets are used to evaluate our proposed system for Arabic sentiment analysis. The ArCAR system shows its capability for character-level Arabic text recognition for both applications. For document classification, the ArCAR system achieves the best performance using the Alarabiya-balance dataset in terms of overall accuracy, recall, precision, and F1-score, by 97.76%, 94.08%, 94.16%, and 94.09%, respectively. Meanwhile, the ArCAR performs well for Arabic sentiment analysis, achieving the best performance using the HARD-balance dataset in terms of overall accuracy and F1-score, by 93.58% and 93.23%, respectively. The proposed ArCAR seems to provide a practical solution for accurate Arabic text representation, understanding, and classifications system.