Mohammed Jebbari
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mohammed Jebbari has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Abdelhadi Raihani
Hassan II University of Casablanca
4 shared publications - Bouchaib Cherradi
Hassan II University of Casablanca
4 shared publications - Soufiane Hamida
Hassan II University of Casablanca
4 shared publications - Mohamed Amine Ouassil
Hassan II University of Casablanca
3 shared publications - Mouaad Errami
Hassan II University of Casablanca
2 shared publications - Rabia Rachidi
Chouaib Doukkali University
2 shared publications
Latest Publications
- Open Access
- 1 June 2026
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 15 (3)
Hybrid convolutional neural network-bidirectional long short-term memory model for Arabic sentence readability assessment
In the current educational landscape, a large number of educators prefer using generative artificial intelligence techniques to produce textual content to be presented for learning. However, these generated texts may not meet the specific needs of learners or align with their abilities. Many traditional methods and techniques can be employed to assess the complexity of a text, such as traditional readability formulas, but these techniques are time consuming and labor-intensive. In this paper, we introduce a deep learning approach for automatically evaluating the readability of Arabic texts by analyzing and classifying sentences into different difficulty levels within educational content. The initial stage of the proposed approach is preprocessing textual content and leveraging natural language processing (NLP) methodologies for feature extraction, such as Word2Vec. The approach then concentrates on refining and evaluating a deep learning model to classify text into different readability levels. This paper introduces a hybrid classification model that combines convolutional neural networks (CNNs) and bidirectional long short-term memory (BiLSTM) layers, attaining an accuracy of 96.68%. This model demonstrates the significance of applying hybrid deep learning models in analyzing educational materials and establishes a foundation for subsequent progress in the field of automated Arabic readability assessment.
- 1 June 2026
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 15 (3)
Open AccessHybrid convolutional neural network-bidirectional long short-term memory model for Arabic sentence readability assessment
In the current educational landscape, a large number of educators prefer using generative artificial intelligence techniques to produce textual content to be presented for learning. However, these generated texts may not meet the specific needs of learners or align with their abilities. Many traditional methods and techniques can be employed to assess the complexity of a text, such as traditional readability formulas, but these techniques are time consuming and labor-intensive. In this paper, we introduce a deep learning approach for automatically evaluating the readability of Arabic texts by analyzing and classifying sentences into different difficulty levels within educational content. The initial stage of the proposed approach is preprocessing textual content and leveraging natural language processing (NLP) methodologies for feature extraction, such as Word2Vec. The approach then concentrates on refining and evaluating a deep learning model to classify text into different readability levels. This paper introduces a hybrid classification model that combines convolutional neural networks (CNNs) and bidirectional long short-term memory (BiLSTM) layers, attaining an accuracy of 96.68%. This model demonstrates the significance of applying hybrid deep learning models in analyzing educational materials and establishes a foundation for subsequent progress in the field of automated Arabic readability assessment.
- Open Access
- 1 March 2025
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 37 (3) , 1758-1771
A novel hybrid model for sentiment analysis in MOOC forums with hybrid word and character-level neural networks
Sentiment analysis is crucial, in the field of natural language processing (NLP). Has applications in different areas. This study focuses on analyzing sentiments in massive open online course (MOOC) forums highlighting its importance in understanding how users interact and shaping educational strategies. The study presents a novel hybrid neural network model specifically tailored for sentiment analysis in MOOC forums. This innovative model combines word level and character level embeddings to handle the linguistic expressions commonly found in this context. The model architecture integrates bidirectional long short-term memory (BiLSTM) layers for word level embeddings and convolutional neural networks (CNNs) for character level embeddings aiming to harness the strengths of both types of embeddings for a view of the linguistic used in MOOC forum posts. Notably this model achieves an accuracy rate of 93.11% showcasing its effectiveness, in sentiment analysis within MOOC forums. This research contributes to sentiment analysis within the context of online education.
- 1 March 2025
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 37 (3) , 1758-1771
Open AccessA novel hybrid model for sentiment analysis in MOOC forums with hybrid word and character-level neural networks
Sentiment analysis is crucial, in the field of natural language processing (NLP). Has applications in different areas. This study focuses on analyzing sentiments in massive open online course (MOOC) forums highlighting its importance in understanding how users interact and shaping educational strategies. The study presents a novel hybrid neural network model specifically tailored for sentiment analysis in MOOC forums. This innovative model combines word level and character level embeddings to handle the linguistic expressions commonly found in this context. The model architecture integrates bidirectional long short-term memory (BiLSTM) layers for word level embeddings and convolutional neural networks (CNNs) for character level embeddings aiming to harness the strengths of both types of embeddings for a view of the linguistic used in MOOC forum posts. Notably this model achieves an accuracy rate of 93.11% showcasing its effectiveness, in sentiment analysis within MOOC forums. This research contributes to sentiment analysis within the context of online education.
- Open Access
- 1 July 2024
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 35 (1) , 343-353
Enhancing learner performance prediction on online platforms using machine learning algorithms
E-learning has emerged as a prominent educational method, providing accessible and flexible learning opportunities to students worldwide. This study aims to comprehensively understand and categorize learner performance on e-learning platforms, facilitating timely support and interventions for improved academic outcomes. The proposed model utilizes various classifiers (random forest (RF), neural network (NN), decision tree (DT), support vector machine (SVM), and K-nearest neighbors (KNN)) to predict learner performance and classify students into three groups: fail, pass, and withdrawn. Commencing with an analysis of two distinct learning periods based on days elapsed (≤120 days and another exceeding 220 days), the study evaluates the classifiers’ efficacy in predicting learner performance. NN (82% to 96%) and DT (81%-99.5%) consistently demonstrate robust performance across all metrics. The classifiers exhibit significant performance improvement with increased data size, suggesting the benefits of sustained engagement in the learning platform. The results highlight the importance of selecting suitable algorithms, such as DT, to accurately assess learner performance. This enables educational platforms to proactively identify at-risk students and offer personalized support. Additionally, the study highlights the significance of prolonged platform usage in enhancing learner outcomes. These insights contribute to advancing our understanding of e-learning effectiveness and inform strategies for personalized educational interventions.
- 1 July 2024
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 35 (1) , 343-353
Open AccessEnhancing learner performance prediction on online platforms using machine learning algorithms
E-learning has emerged as a prominent educational method, providing accessible and flexible learning opportunities to students worldwide. This study aims to comprehensively understand and categorize learner performance on e-learning platforms, facilitating timely support and interventions for improved academic outcomes. The proposed model utilizes various classifiers (random forest (RF), neural network (NN), decision tree (DT), support vector machine (SVM), and K-nearest neighbors (KNN)) to predict learner performance and classify students into three groups: fail, pass, and withdrawn. Commencing with an analysis of two distinct learning periods based on days elapsed (≤120 days and another exceeding 220 days), the study evaluates the classifiers’ efficacy in predicting learner performance. NN (82% to 96%) and DT (81%-99.5%) consistently demonstrate robust performance across all metrics. The classifiers exhibit significant performance improvement with increased data size, suggesting the benefits of sustained engagement in the learning platform. The results highlight the importance of selecting suitable algorithms, such as DT, to accurately assess learner performance. This enables educational platforms to proactively identify at-risk students and offer personalized support. Additionally, the study highlights the significance of prolonged platform usage in enhancing learner outcomes. These insights contribute to advancing our understanding of e-learning effectiveness and inform strategies for personalized educational interventions.
- Open Access
- 24 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Integrating GIS Data with Machine Learning Approaches for Improved Flood Hazard Prediction
Flooding is a significant natural hazard that can cause important loss of life and property damage. The accurate prediction of flood hazards is crucial for emergency management and disaster risk reduction. In the last few years, the use of Artificial Intelligent techniques has witnessed increasing rates, specifically in the domains of hydrology and water resources management, including flood hazard prediction. This research proposes a support to policy suggestion in order to mitigate the rate of human mortality and, to reduce property destruction caused by this severe natural phenomenon. Indeed, this study aims to evaluate and discover more efficient prediction algorithms of ML to evaluate the probability of potential flood hazards using ML algorithms, namely Ensemble Learning (EL), Logistic Model Tree (LMT), Random Forest (RF), K nearest neighbor (KNN), and Logistic Regression (LR). The study comprises monthly rainfall data over a period of 113 years, random partitioning was employed in order to allocate 80% of the dataset for training, and 20%, reserved for testing. The finding revealed that Logistic Regression achieves the best accuracy of 99.15% among other models employed for flood forecasting.
- 24 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessIntegrating GIS Data with Machine Learning Approaches for Improved Flood Hazard Prediction
Flooding is a significant natural hazard that can cause important loss of life and property damage. The accurate prediction of flood hazards is crucial for emergency management and disaster risk reduction. In the last few years, the use of Artificial Intelligent techniques has witnessed increasing rates, specifically in the domains of hydrology and water resources management, including flood hazard prediction. This research proposes a support to policy suggestion in order to mitigate the rate of human mortality and, to reduce property destruction caused by this severe natural phenomenon. Indeed, this study aims to evaluate and discover more efficient prediction algorithms of ML to evaluate the probability of potential flood hazards using ML algorithms, namely Ensemble Learning (EL), Logistic Model Tree (LMT), Random Forest (RF), K nearest neighbor (KNN), and Logistic Regression (LR). The study comprises monthly rainfall data over a period of 113 years, random partitioning was employed in order to allocate 80% of the dataset for training, and 20%, reserved for testing. The finding revealed that Logistic Regression achieves the best accuracy of 99.15% among other models employed for flood forecasting.