The study proposes an innovative approach called “Text to Visual Chart Prediction,” which harnesses the power of machine learning to predict visualization charts from computational linguistics text. The method is made up of three main steps: cleaning the data, preprocessing the data (using TF-IDF and FastText), and classifying the data (using XGBOOST, Decision Tree Classifier, and K-Nearest Neighbor). Notably, the approach achieves a promising accuracy of 78.51% in chart prediction from the analytical text, highlighting its effectiveness in automatically generating appropriate visualizations based on linguistic data. The results show that the Text to Visual Chart Prediction method is a strong and effective way to deal with the problems that come up when trying to use automated visualization synthesis in textual analysis.