The usage of data mining has dramatically increased over the past few years and the education sector is leveraging this field in order to analyze and gain intuitive knowledge in terms of the vast accumulated data within its confines. The primary objective of this study is to compare the results of different classification techniques such as Naïve Bayes, Logistic Regression, Conjunctive Rule and J48 Decision Tree in detection and identification of student's learning styles in a Virtual Learning Environment to provide adaptation strategy according to identified learning styles of the students. The data sets were collected from 507 students of Computer Programming 1 course with a total of 52,815 rows of data extracted from their interaction logs and navigational patterns in a virtual learning environment. A mapping of student's learning style according to the selected learning style model had been accomplished. The performance of each classification techniques and its classification quality were measured in terms of correctly classified instances, kappa statistics, receiver operating characteristics, and area under the curve plots. Based from the analysis of the comparative results, the classification technique that has produced the highest collective average accuracy is the J48 Decision Tree with correctly predicted instances of 87.42%. The classification technique could be used to identify student's learning styles in a virtual learning environment. [For the complete proceedings, see ED579395.]