Users of search engines interact with the system using different size and type of queries. Current search engines perform well with keyword queries but are not for verbose queries which are too long, detailed, or are expressed in more words than are needed. The detection of verbose queries may help search engines to get pertinent results. To accomplish this goal it is important to make some appropriate preprocessing techniques in order to improve classifiers effectiveness. In this paper, we propose to use BabelNet as knowledge base in the preprocessing step and then make a comparative study between different algorithms to classify queries into two classes, verbose or succinct. Our Experimental results are conducted using the TREC Robust Track as data set and different classifiers such as, decision trees probabilistic methods, rule-based methods, instance-based methods, SVM and neural networks.