Several leadership studies have linked e-leadership behaviours to individual, team, and organizational outcomes, but the magnitude of the link across settings and levels of analysis is still unclear. This association may be affected by various causes and mechanisms. Therefore, additional research is needed to determine how e-leadership behaviours are more effective. This study explored how e-leadership affects faculty members’ organizational citizenship behaviour (OCB). Information and communication technology (ICT) was proposed as a developmental mechanism to mediate the link between e-leadership and OCB. This study used quantitative methods. Researchers obtain data using basic random sampling. Google Forms were used to distribute the questionnaires. The proposed model was evaluated with 355 respondents from 11 Palestinian universities. This study employed the structural equation model partial least squares (SEM-PLS) technique utilizing SmartPLS 4 software. This study used validity, reliability, and hypothesis tests. This study has one second-order construct and all reflective variables. Thus, the three latent variables affect the indicators. The results showed that e-leadership is linked to high faculty OCB and that ICT usage mediates this relationship. Additionally, this study examined the theoretical and practical consequences, limitations, and future research areas and suggestions.

1. In times of crisis, effective inventory management has become one of the main issues of operational efficiency and organizational competitive advantage. Organizations face unending challenges in...

Morphological complexity and dialectal variation make Arabic one of the most demanding languages for automated sentiment analysis (SA). To tackle these limitations, this work proposes a hybrid framework that couples a Large Language Model with a Graph Neural Network (LLM–GNN), combining the complementary strengths of contextual text encoding and relational structure learning. Specifically, AraBERT v2 serves as the backbone encoder, while a Graph Convolutional Network (GCN) built on cosine-similarity edges captures inter-sentence dependencies that purely sequential architectures tend to overlook. The framework is benchmarked on the publicly available Arabic 100k Reviews dataset (99,999 authentic user-generated reviews balanced equally across Positive, Negative, and Mixed sentiment classes). Against four established baselines (fine-tuned AraBERT, AraBERT-BiLSTM, AraBERT-MLP, multilingual BERT and modern Arabic-centric LLMs such as Jais-13B), the proposed model achieves an overall accuracy of 66.9% and a macro F1-score of 66.55%, representing gains of 7.6% and 4.4% over the strongest comparable baseline, respectively. Training curves indicate stable loss reduction from the earliest epochs, reflecting consistent optimization behavior throughout the 50-epoch schedule. A noted constraint is that graph construction operates at the mini-batch level, which limits the model’s exposure to corpus-wide semantic relationships. Nevertheless, the results confirm that integrating graph-based relational reasoning with transformer-derived embeddings surfaces nuanced sentiment signals that sequential models routinely miss, pointing to practical utility in Arabic social media monitoring and large-scale customer review analysis.

Determining the optimal number of neurons and layers in an Artificial Neural Network (ANN) remains a largely heuristic and computationally expensive process, commonly addressed through trial-and-error, pruning, or automated search strategies. The current paper introduces a new signal-driven method that uses wavelet transformation along with window-based scanning of the input features as a tool to lead the principle design of ANN architectures. The approach proposed by the authors first takes into account the multi-scale structural complexity of the input signal in the wavelet domain, then, it extracts the localized frequency and variation characteristics that inform the required network depth and width directly. The window scanning technique allows for the identification of complexity variations throughout the signal, hence leading to the selection of the architecture according to the content of the data instead of the empirical tuning. Thereby, the proposed framework is distinctly different from the traditional architecture selection methods, as it actively links signal complexity to network capacity thus providing the architecture determination that is transparent, reproducible, and inexpensive in terms of computation power. Experimental results conducted on benchmark datasets reveal that networks designed by this method obtain competitive accuracy and generalization performance along with the reduction of architectural redundancy. Therefore, the authors conclude that the wavelet-guided architectural design is a very effective alternative to the heuristic-based ANN configuration and moreover, it is the first step in the data-aware neural networks development.

Arabic sentiment analysis (SA) faces significant challenges due to the language’s morphological richness and dialectal diversity. This study introduces a novel hybrid large language model-graph neural network (LLM-GNN) framework designed to address these challenges. The proposed model integrates the contextual understanding of AraBERT v2 with the structural learning capability of a graph convolutional network (GCN). It constructs a graph of sentences using cosine similarity, allowing the GCN to capture crucial inter-sentence semantic dependencies often missed by sequential models. Findings: The model is evaluated on a publicly available Arabic 100k Reviews dataset consisting of authentic user-generated Arabic reviews balanced across positive, negative, and mixed sentiment classes. The results demonstrate that the proposed LLM-GNN model performed better as compared to the baseline models, including fine-tuned AraBERT, AraBERT-BiLSTM, AraBERT-MLP, and multilingual BERT. The hybrid model achieves an overall accuracy of 66.8% and a F1-score of 66.55%, with an improvement of 7.6% and 4.4%, respectively. The model demonstrated stable convergence from the first training epoch. Research limitations/implications: The graph construction is performed at the mini batch level, which restricts the modeling of global semantic relationships across the entire corpus. The results show that the hybrid model identifies subtle sentiment cues that sequential models frequently miss by fusing relational graph reasoning with contextual embeddings. By effectively identifying subtle sentiment cues, the hybrid model can significantly enhance the accuracy of real-world applications such as social media monitoring and customer review analysis for Arabic content.

The growing sophistication of cyber-attacks exposes the limitations of conventional deep neural networks, which often suffer from slow convergence and high computational costs. This paper introduces the Conformable Fractional Deep Neural Network (CFDNN), a framework that replaces standard backpropagation with conformable fractional gradient descent. By operating in the super-integer regime ( $$\alpha \in [1.2, 1.8]$$ ), the model smooths the loss landscape to accelerate training. Evaluated on NSL-KDD and CIC-IDS2018 using cross-validation, the CFDNN achieves 99.42% and 99.86% accuracy, respectively. It attains these results in just 30 epochs–a 40% reduction in training time. On the large-scale CIC-IDS2018 dataset, the model converged in approximately 24.2 minutes on a system equipped with an standard CPU. The CFDNN thus provides a computationally efficient, high-performance alternative to classical methods, offering a robust solution for modern cyber-defense.