A novel assessment procedure based on knowledge space theory (KST) is presented along with a complete implementation of an intelligent tutoring system (ITS) that has been used to test our theor- etical findings. The key idea is that correct assessment of the student knowledge is strictly related to the structure of the domain ontology. Suitable relationships between the concepts must be present to allow the creation of a reverse path from the ''knowledge state'' representing the student goal to the one that contains her actual knowledge about this topic. Knowledge space theory is a very good framework to guide the process of building the ontology used by the artificial tutor. The system we present uses a conversational agent to assess the student knowledge through a natural language question=answer procedure. The system exploits a Cyc-based common sense ontology about the spe- cific domain of interest to select the concepts needed to explain unknown topics emerging from the dialogue. Besides, the latent semantic analysis (LSA) technique is used to determine the correctness of the student sentences in order to establish which concepts she knows. As a result, the system sup- plies learning material arranged as a path between the unknown topics resulting from the student assessment. The learning path is presented to the student by a user-friendly graphical interface, which allows to access documents browsing a visual map. The procedure is explained in detail along with the rest of the system, and the assessment validation results are presented.
A KST-based system for Student Tutoring
Giovanni Pilato;
2008
Abstract
A novel assessment procedure based on knowledge space theory (KST) is presented along with a complete implementation of an intelligent tutoring system (ITS) that has been used to test our theor- etical findings. The key idea is that correct assessment of the student knowledge is strictly related to the structure of the domain ontology. Suitable relationships between the concepts must be present to allow the creation of a reverse path from the ''knowledge state'' representing the student goal to the one that contains her actual knowledge about this topic. Knowledge space theory is a very good framework to guide the process of building the ontology used by the artificial tutor. The system we present uses a conversational agent to assess the student knowledge through a natural language question=answer procedure. The system exploits a Cyc-based common sense ontology about the spe- cific domain of interest to select the concepts needed to explain unknown topics emerging from the dialogue. Besides, the latent semantic analysis (LSA) technique is used to determine the correctness of the student sentences in order to establish which concepts she knows. As a result, the system sup- plies learning material arranged as a path between the unknown topics resulting from the student assessment. The learning path is presented to the student by a user-friendly graphical interface, which allows to access documents browsing a visual map. The procedure is explained in detail along with the rest of the system, and the assessment validation results are presented.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.