Automated Arabic Text Classification Using Hyperparameter Tuned Hybrid Deep Learning Model

The text classification process has been extensively investigated in various languages, especially English. Text models are vital several Natural Language Processing (NLP) applications. Arabic language a lot of significance. For instance, it is the fourth mostly-used on internet and sixth official United Nations. However, there few studies Arabic. A have published earlier language. In general, researchers face two challenges process: low accuracy high dimensionality features. this study, an Automated Classification using Hyperparameter Tuned Hybrid Deep Learning (AATC-HTHDL) model proposed. major goal proposed AATC-HTHDL method to identify different class labels for text. first step pre-process input data transform into useful format. Term Frequency-Inverse Document Frequency (TF-IDF) applied extract feature vectors. Next, Convolutional Neural Network with Recurrent (CRNN) utilized classify final stage, Crow Search Algorithm (CSA) fine-tune CRNN model’s hyperparameters, showing work’s novelty. was experimentally validated under parameters outcomes established supremacy over other approaches.