High Dimensional Text Document Clustering and Classification using Machine Learning Methods

摘要

Although High Dimensional documents are used for classification, document dimensions are a major concern and a worrying sign. The effects of Dimensional reduction can be both the positive and negative aspects. If a dimensional reduction is not in a correct format, classification using lower-dimensional documents will not produce the desired results. Our research studies centered on dimensional reduction using the fundamental similarity property, but they haven't yet discussed text classification. This approach discusses the classification and clustering task by providing various algorithms. We used clustering and classification methods on various datasets in this paper. It also suggested improving the efficiency of the K-means clustering and the Naive Bayes classification technique. Popular parameters like precision, recall, and F-score are used to evaluate the recommended method's performance. The results of the experiments would demonstrate that the proposed model outperforms current algorithms.