A ML-SENTIMENT ANALYSIS ON MONKEYPOX OUTBREAK

Abstract

The sudden and unexpected increase in the number of people suffering from anemia worldwide has caused increased concern. A zoonotic disease characterized by symptoms similar to smallpox has spread to nearly two countries and many others and has been labeled as potentially contagious by experts. There is no specific treatment for monkeypox. However, because smallpox is very similar to monkeypox, administration of antibiotics and smallpox vaccines can be used to prevent and treat scarlet fever. Since the disease has become a global problem, there is a need to examine its impact and public health. Number of infections, deaths, hospital visits, hospitalizations, etc. Analyzing basic results such as can play an important role in preventing infection. In this study, we analyzed the spread of monkeypox disease in different countries using machine learning techniques such as linear regression (LR), decision tree (DT), random forest (RF), elastic net regression (EN), Artificial Neural Network (ANN). ) and Convolutional Neural Network (CNN). Our research has shown that CNN performs best and uses statistics such as mean error (MAE), mean square error (MSE), mean percent error (MAPE) and Rsquared error to measure the effectiveness of this model (R2). This study also presents a time series analysis using the Autoregressive Integrated Moving Average (ARIMA) and Seasonal Autoregressive Integrated Moving Average (SARIMA) models to measure time differences. Understanding spread can lead to an understanding of risk that can be used to prevent further spread and ensure timely and effective treatment. Machine learning; Neural networks.