One of the most important aspects of the precision of a classification is the suitable selection of a classification algorithm and a training set for a given task. Basic principles of machine learning can be used for this selection [3]. In this paper, we have focused on improving the precision of classification algorithms results. Two kinds of approaches are known: Boosting and Bagging. This paper describes the use of the first method – boosting [6] which aims at algorithms generating decision trees. A modification of the AdaBoost algorithm was implemented. Another similar method called Bagging [1] is mentioned. Results of performance tests focused on the use of the boosting method on binary decision trees are presented. The minimum number of decision trees, which enables improvement of the classification performed by a base machine learning algorithm, was found. The tests were carried out using the Reuters 21578 collection of documents and documents from an internet portal of TV Markíza.