On the internet, information technology generated massive amounts of data. Because this data was initially primarily in English, the majority of data mining research was conducted on English text documents. As internet usage grew, so did data in other languages such as Gujarati, Marathi, Tamil, Telugu, and Punjabi, among others. We present a text categorization method based on artificial text summarization of Gujarati Articles in this paper. For the classification of text documents, various learning techniques such as Naïve Bayes, Support Vector Machines, and Decision Trees are available. We gathered articles from various e-newspaper editorials. This paper focuses on a brief review of the various techniques and methods for Gujarati Articles Classification, so that research in Text Classification can be further explored using various classifier algorithms. The dataset, which contains 1604 documents from 8 different categories, is used by the system. The result shows that Stacking Classifier with Bernoulli Naïve Bayes Classifier and Extra-trees Classifier is efficient for Gujarati Articles.