 This study has developed a data set of textual information related to monkeypox, which can be used to train a machine learning model for diagnosing the disease. The model was trained using gradient boosting algorithms such as XGBoost, CatBoost, and LightGBM, as well as standard machine learning methods such as SVM and Random Forests. The best performing algorithm was XGBoost, achieving an accuracy of 1.0 in reviews. Additionally, the model's flexibility was tested through k-fold cross-validation, with an average accuracy of 0.9 achieved across five different splits of the test set. Furthermore, SHAP was used to explain the model's output, providing insight into how each feature contributes to the overall prediction. This article was authored by Ali Reza Farsapur, Roya Elmi, and Hamid Nasiri.