<p>The rapid growth of Mobile Edge Computing has reshaped network architecture, driven by the need for low-latency, high-bandwidth applications. One of the most significant issues for businesses in this field is accurate detection of aspect categories in customer reviews to understand consumer sentiment and enhance the quality of service. Traditional approaches for aspect category detection fail to capture the nuances of customer feedback accurately, resulting in reduced performance. To tackle this issue this method introduces a novel Meta-ensemble Linear Random Gradient-based Crossover Osprey. The method combines different datasets and employs preprocessing tasks such as, noise removal, standardization, tokenization, stemming and lemmatization to improve the input data quality. The Feature extraction is performed by applying the Modified Principal Component Analysis, which captures semantic, sentimental, and morphological features from customer reviews. The detection of aspect categories is performed on ensemble of machine learning algorithms including Gradient Boosting Machines, Random Forest, Linear Regression, and a Meta Ensemble approach. The Osprey Optimization Algorithm with a crossover strategy is employed for efficient hyperparameter tuning, which guarantees faster convergence and better accuracy. Experimental findings demonstrate that the proposed model outperforms the existing method to achieve accuracy of 99.0% and F1-score of 98.59% based on the edge computing / edge servers dataset. This study provides a useful, scalable result for automated sentiment analysis and aspect-based classification that provides significant value to businesses in the MEC enterprise by providing actionable insights from customer reviews.</p>