Data mining techniques in education and learning are still in their infancy. Even academic references are scarce on the ground, although some education-related publications are already beginning to pay attention to this new area and its research potential. The present article describes the results of a medium-scale (N = 56) study, using log files from open remote laboratory at Charles University in Prague, Faculty of Mathematics and Physics, to observe secondary school students’ behavior during their work in virtual environment. The simplest data mining and text mining techniques were used to reveal individual user’s behavioral patterns, to detect disengagement, and to compare learning outcomes and student preferences. The results will be used mainly to improve systems’ adaptability to students’ requirements and capacities.