This study relied on datasets from global B2C and C2C to investigate the relationship between short video advertising (SV), customer satisfaction, price, quality signals, and sales in digital marketing. Using the web-scraping mining technique, the results from over twenty-three thousand online shops indicate that logistics service quality overrides the relevance of location in digital marketing. SV directly impacts sales and increases the shops’ dynamic scores, including quality of service and customer satisfaction. We identified actual online data to justify why SV adoption is essential in digital marketing and recommend logistic service quality and price fairness to improve sales in e-commerce.

The survival of the global economy is rooted in the production of goods, rendering of valuable services, and formulation and implementation of favorable trade policies. These goods and services supported by related policies however, must reach prospective customers unblemished in good time, through planned advertisement strategies. Advertisement over the years has evolved from the traditional one-on-one to technology induced ones such as digital marketing and sales. Technological advancement has diversified advertisement into a multi-faceted and dynamic channel with enormous growth and prospects. In this paper, we made a significant effort to identify actual online data to justify why short video (SV) adoption is essential in e-commerce and digital marketing. A total of 23589 datasets were drawn from three global B2C and C2C websites using the scrappy web crawlers to investigate a resilience model in the relationship between SV advertising adoption, quality signals, customer satisfaction, price fairness, and sales in digital marketing. Whereas shop location is vital in traditional shopping, logistics service quality overrides its influence in online shopping settings.

Power consumption is a major obstacle facing almost every industry, especially in Africa. The amount of energy needed to keep everyone connected in a region where the cost of power production is twice higher than in other regions is a concern, leading stakeholders to focus their efforts on reducing global C02 footprint. We leveraged network virtualization to provide a greener commutation Africa. We proved that network resource and virtualization at the physical infrastructure would allow multiple internet service providers to provide quality service to UEs and improve the availability, accessibility, and affordability of wireless communication. Our model will set the bases for policies to regulate the number and dangers that accompany cell-sited mounted by multiple Telco and internet service providers in Africa. It is also expected that the cost of internet service and the cost of doing business in Africa will reduce and attract foreign trade and investment to Africa.

This study evaluates the performance of conventional machine learning classifiers for sentiment analysis of ChatGPT-related tweets. While deep learning approaches have demonstrated advanced capabilities, their substantial computational requirements present practical limitations. Using a dataset of 219,294 tweets from November 2022 to April 2023, we assess four classifiers (Logistic Regression, Support Vector Machines, Random Forest, and Naive Bayes) with two feature extraction techniques (Bag of Words and TF-IDF) across balanced and imbalanced datasets. Results indicate that Linear SVM with TF-IDF vectorization achieves the highest accuracy (84.02%) and macro F1-score (80.81%) without balancing techniques. Random Forest with Bag of Words and balancing techniques shows competitive performance (80.08% macro F1-score), while Naive Bayes consistently underperforms across configurations. n-gram analysis reveals predominantly positive public sentiment toward ChatGPT, focusing on capabilities and utility, while negative sentiments center on performance limitations and broader AI implications. This research provides empirical insights into sentiment analysis methodologies for emerging AI technologies and demonstrates the continued effectiveness of conventional machine learning approaches in resource-constrained environments.

This study proposes a multilevel stacking approach that extends Wolpert's (1992) stacked generalisation, aiming to minimise forecasting error, reduce systematic bias, and enforce temporal domain invariance. It incorporates walk-forward out-of-fold and step-based walk-forward validation, enriched metadata, and a domain adversarial neural network (DANN). The base learners XGB and LSTM function as residual and latent encoders for the Random Forest with DANN meta-learner. DANN is integrated in meta-learning to minimise task regression loss and maximize domain discrimination loss through a gradient reversal layer. This fusion improves domain transition stability, as the model’s high explanatory power with ^2 values exceed 0.98 across validation and test regimes. The MASE values below 0.07 on both regimes indicate strong predictive performance relative to a naïve benchmark, and NRMSE values around 0.025 confirm that the proposed stacking framework effectively captures temporal dependencies. Moreover, the model achieves a near-symmetric residual distribution, with a skewness of 0.37 on the validation set and -0.01 on the test set, suggesting that adversarial feature learning helps reduce asymmetric prediction errors and stabilise meta-learning. This proposed framework demonstrates empirically that stacking should not be evaluated solely on MAE/RMSE but on residual distribution behaviour under domain transition. Furthermore, SHAP analysis provides empirical evidence that enriched metadata significantly enhances the learning capacity, allowing the meta-learner to capture complex dependencies.