Arabic sentiment analysis of Monkeypox using deep neural network and optimized hyperparameters of machine learning algorithms

Sentiment analysis, a branch of natural language processing (NLP), has gained significant attention for its applications in various domains. This study focuses on utilizing machine learning and deep learning algorithms for sentiment analysis in the context of analyzing Monkeypox using Arabic sentiment text. The objective is to develop an accurate and efficient model capable of classifying Arabic text into sentiment categories, facilitating the understanding of public perceptions toward Monkeypox. The study begins by collecting a diverse dataset of Arabic text containing sentiments related to Monkeypox. Machine learning algorithms, such as Support Vector Machines, Naive Bayes, and Random Forest, along with deep learning (DNN) techniques, including Recurrent Neural Networks and Transformer models, are employed for sentiment classification. Hyperparameter optimization techniques were implemented to fine-tune the models for optimal performance. The impact of various hyperparameters on the model is assessed to select the best configuration. Experimental results demonstrate the effectiveness of the proposed sentiment analysis models in accurately classifying Arabic sentiment text related to Monkeypox. The DNN models based on Leaky ReLU showcased the significance of leveraging complex representations for NLP tasks with 92%. Hyperparameter optimization aids in selecting suitable configurations, improving model accuracy, and reducing overfitting. The findings from this study contribute to advancing sentiment analysis techniques in Arabic text and provide valuable insights into public sentiments toward Monkeypox. The developed models can be utilized in public health monitoring, crisis management, and policymaking, offering valuable insights into the sentiment landscape surrounding the disease.