With the growing popularity of Web 2.0 tools in educational settings, it becomes important to investigate the influence of students' learning styles on the adoption and use of these emerging tools. Currently, there are only few studies addressing this issue and most of them are based on student selfreported data, e.g., preference, acceptance or attitude toward social media tools, captured by means of questionnaires. This paper explores the relationships between actual students' use of the Web 2.0 tools and their learning styles classified according to Felder-Silverman model. The context of the study is an undergraduate course on Web Applications' Design, with 45 enrolled students. Several machine learning algorithms for classification, association rule induction and feature selection are applied. Results show that learning styles have a limited influence on the students' level of interaction with each of the four Web 2.0 tools considered.