TTUTOR: PROVIDING AUTOMATIC DIAGNOSIS RESOURCES DURING THE DIAGNOSIS PROCESS FOR A FUZZY-BASED STUDENT MODEL
In this paper, we present an Intelligent Tutoring System (ITS) based on e-assesment, which automatically generates tests in function of the current student's knowledge. Our system arises in the absence of proposals able to handle the generation of diagnosis resources during the diagnosis process in an automatic manner. Current ITSs usually gather the student model through a diagnosis process, which is about inferring what the student knows from a set of observable facts. Diagnosis provides detailed information about students' competencies which are used for guiding the selection of subsequent teaching operations. Common ITSs perform the diagnosis process through two major approaches. Firstly, a number of approaches use navigational features. In web spaces, this might not be the best strategy. One of the strengths of ITSs relies on their availability without temporal and spatial constraints. Without a direct supervision of a teacher, the system cannot guarantee that the student is not distracted in a concrete session. Therefore a diagnosis based on navigational features could infer incorrect student's knowledge states. Secondly, most of approaches perform the diagnosis process through a set of quizzes or problems (in problem-solving scenarios) manually created by a tutor and solved by students. In this sense, the teacher must consider all the possible students' cognitive states, being this a time-consumption and error-prone task. Hence, a method which dynamically generates diagnosis resources in function of the current student model is arguably recommendable.
The above consideration has encouraged us to develop TTutor, a Test-based ITS. The knowledge representation of the domain is defined following an hybrid approach mixing the overlay model with ontological features. The student model is gathered in basis of an e-assessment engine that automatically generates tests for each student in function of his/her knowledge state. The tests serve as diagnosis resources as well as teaching operations. First, the tests will be fitted for any student state, guaranteeing the correctness of the subsequent diagnosis process. Also teachers are released from the tedious task of manually creating each test. Second, students can acquire the knowledge of the course following an e-assessment strategy. In addition, the system promotes self-assessment by adding game-like features. The curriculum, sequence is divided into game-like stages. The system shows prompts to the student when he/she has passed one stage. Then the student can select a new stage or stay in the same one in order to completely master the current concepts.
Furthermore, we propose an open student model for students. It might help them to better understand their learning and therefore enhance their learning processes. Knowing specific information about their concrete learning states may encourage them to reflect on their knowledge and on the learning process. Thence we have designed an intuitive user interface where the knowledge state of each stage is shown. The student model interface is also accessible for teachers who are able to control the performance of the course at any moment. To test the validity of our proposal we have performed a pre-experimental evaluation of TTutor attending to the opinions of a group of volunteer university students. The gathered reactions showed that the students were satisfied with our TTutor system, and therefore, the results were highly promising.