DEEP LEARNING MODELS APPLIED TO ARABIC QURANIC TEXT
| dc.contributor.author | Khelifi, Ayoub | |
| dc.contributor.author | Sahbi, Ramzi | |
| dc.contributor.author | Halassa, Madiha: Supervisor | |
| dc.date.accessioned | 2024-07-03T11:23:15Z | |
| dc.date.available | 2024-07-03T11:23:15Z | |
| dc.date.issued | 2024-06 | |
| dc.description.abstract | Deep learning has seen significant growth and development in natural language processing (NLP) for many languages, including Arabic. However, the unique characteristics of Arabic represent many challenges for deep learning models. The aim of this research is to develop accurate and effective systems for classifying Arabic verses of the Holy Quran using recurrent neural networks (RNN) and convolutional neural networks (CNN). The proposed model achieved promising results on the data set used, demonstrating its effectiveness in classifying the verses of the Holy Quran with high accuracy. This research contributes to the promotion of Quranic text classification techniques and opens new avenues for exploring deep learning applications in Islamic studies. | |
| dc.identifier.uri | https://repository.univ-msila.dz/handle/123456789/43142 | |
| dc.language.iso | en | |
| dc.publisher | UNIVERSITY OF MOHAMED BOUDIAF – MSILA, FACULTY OF MATHMATICS AND COMPUTER SCIENCE, DEPARTEMENT OF COMPUTER SCIENCE | |
| dc.subject | HUMANITIES and RELIGION::Languages and linguistics::Other languages::Arabic language | |
| dc.subject | Holy Quran | |
| dc.subject | Deep Learning | |
| dc.subject | Natural Language | |
| dc.subject | Processing (NLP) | |
| dc.subject | CNN | |
| dc.subject | RNN | |
| dc.title | DEEP LEARNING MODELS APPLIED TO ARABIC QURANIC TEXT | |
| dc.type | Thesis |