Knowledge acquisition in Intelligent Tutoring System: a data mining approach Simone Riccucci 1 , Antonella Carbonaro 2 , and Giorgio Casadei 1 1 University of Bologna, Computer Science Department, Via Mura Anteo Zamboni 7, 40121, Bologna, Italy, {riccucci,casadei}@cs.unibo.it, WWW home page: http://www.cs.unibo.it/~{riccucci,casadei} 2 University of Bologna, Computer Science Department, Via Sacchi 3, 47023, Cesena, Italy, carbonar@csr.unibo.it, WWW home page: http://www.csr.unibo.it/~carbonar Abstract. In the last years Intelligent Tutoring Systems have been a very successful way for improving learning experience. Many issues must be addressed until this technology can be defined mature. One of the main problems within the Intelligent Tutoring Systems is the process of contents authoring: knowledge acquisition and manipulation process is a difficult task because it requires specialized skills on computer program- ming and knowledge engineering. In this paper we propose a mechanism based on first order data mining to partially automate the process of knowledge acquisition. The knowledge has to be used in the ITS dur- ing the tutoring process for personalized instruction. Such a mechanism can be applied in Constraint Based Tutor and in the Pseudo-Cognitive Tutor. 1 Introduction Intelligent Tutoring Systems are very useful tools to support and enhance the learning process in many fields. This kind of systems includes the necessary infor- mation for a real simulation of teaching activity: nowadays, most of the systems used in learning support, are a slight improvements of automated textbook. Fur- thermore, they do not embody any particular instructional approach, theory, or philosophy, other than the instructional approach that exist in the textbook on which the system is based. On the other hand, ITSs can adapt their behaviour on the base of the domain and student models, approaching the benefits of one-on-one instruction. Many ITSs have been proved highly effective. PAT Algebra Tutor [1] was developed for use in High-School setting and is based on the ACT theory [2]. The main purpose of the system is teaching to apply mathematics learned at school to real world problems. An experiment was conducted on 470 students using this sys- tem and the experimental classes outperformed students in comparison classes by 15% on standardized tests and 100% on tests targeting the ITS objectives