In this paper, we propose a completely new approach to the problem of text classification and automatic keyword extraction by using machine learning techniques. We introduce a class of representations for classifying text data based on decision trees, and present an algorithm for learning it inductively. Our algorithm has the following features: it does not need any natural language processing technique, and it is robust for noisy data. We show that our learning algorithm can be used for automatic extraction of keywords for text retrieval and automatic text categorization. We also demonstrate some experimental results using our algorithm.