Intelligent tutoring system

About: Intelligent tutoring system is a research topic. Over the lifetime, 3472 publications have been published within this topic receiving 58217 citations. The topic is also known as: ITS.

A proposal for student modeling based on ontologies and diagnosis rules

Abstract: The advances in the educational field and the high complexity of student modeling have provoked it to be one of the aspects more investigated in Intelligent Tutoring Systems (ITSs). The Student Models (SMs) should not only represent the student's knowledge, but rather they should reflect, as faithfully as possible, the student's reasoning process. To facilitate this goal, in this article a new approach to student modeling is proposed that benefits from the advantages of Ontological Engineering, advancing in the pursue of a more granular and complete knowledge representation. It's focused, mainly, on the SM cognitive diagnosis process, and we present a method providing a rich diagnosis about the student's knowledge state - especially, about the state of learning objectives reached or not. The main goal is to achieve SMs with a good adaptability to the student's features and a high flexibility for its integration in varied ITSs.

NORMIT: a Web-enabled tutor for database normalization

Abstract: The paper describes the design and development of NORMIT, an intelligent tutoring system (ITS) that teaches database normalization to university students. NORMIT is a Web-enabled system, and we discuss its architecture and techniques used to deal with multiple students. We also discuss constraint-based modeling (CBM), the underlying student and domain modelling approach. NORMIT is the first in the series of constraint-based tutors developed at ICTG that teaches a procedural task, and we comment on the suitability of CBM for such tasks. We also discuss the plans for the evaluation of the system and future work.

A Motivationally Supportive Affect-Sensitive AutoTutor

Abstract: This chapter describes a fully automated affect-sensitive Intelligent Tutoring System (ITS) called the Affective AutoTutor. AutoTutor is an ITS that helps students learn topics in Newtonian physics, computer literacy, and critical thinking via natural language dialogues that simulate the dialogue patterns observed in human–human tutoring. AutoTutor uses state-of-the-art natural language understanding mechanisms to model learners’ cognitive states and plan its dialogue moves in a manner that is sensitive to these states. While the original AutoTutor is sensitive to learners’ cognitive states, the affect-sensitive tutor is responsive to their affective states as well. This Affective tutor automatically detects learners’ boredom, confusion, and frustration by monitoring conversational cues, gross body language, and facial features. The sensed affective states guide the tutor’s responses in a manner that helps learners regulate their negative emotions. The tutor also synthesizes affect via the verbal content of its responses and the facial expressions and speech of an embodied pedagogical agent. An experiment comparing the affect-sensitive and nonaffective tutors indicated that the affective tutor improved learning for low-domain knowledge learners, particularly at deeper levels of comprehension.

Recasting the feedback debate: benefits of tutoring error detection and correction skills

Abstract: Traditionally, intelligent tutoring systems have provided feedback on the basis of a so-called expert model. Expert model tutors incorporate production rules associated with error free and efficient task performance. These systems intervene with corrective feedback as soon as a student deviates from a solution path. This thesis explores the effects of providing feedback on the basis of a so-called intelligent novice cognitive model. An intelligent novice tutor allows students to make errors, and provides guidance through the exercise of error detection and correction skills. The underlying cognitive model in such a tutor includes both rules associated with solution generation, and rules relating to error detection and correction. There are two pedagogical motivations for feedback based on an intelligent novice model. First, novice performance is often error prone and students may need error detection and correction skills in order to succeed in real world tasks. Second, the opportunity to reason about the causes and consequences of errors may allow students to form a better model of the behavior of domain operators. Learning outcomes associated with the two models were experimentally evaluated. Results show that learners who receive intelligent novice feedback demonstrate better learning overall, including better retention and transfer performance than students receiving expert model based feedback. Another focus of the research described here has been to help students form a robust and accurate encoding of declarative knowledge prior to procedural practice with an intelligent tutoring system. Examples have been widely used as a component of declarative instruction. However, research suggests that the effectiveness of examples is limited by the fact that inferences concerning the specific conditions under which operators may be applicable are only implicit in most examples, and may not be apparent to students without self-explanation. This thesis explores the effectiveness of a technique referred to in this thesis as example walkthroughs. Example walkthroughs interactively guide students through the study of examples. They present question prompts that help students make the inferences necessary to select problem solving operators that will lead to a solution. Students make these inferences by responding to multiple choice prompts. Evaluations suggest that example walkthroughs may provide a cost effective way to boost learning outcomes in intelligent tutoring systems.

General Features in Knowledge Tracing to Model Multiple Subskills, Temporal Item Response Theory, and Expert Knowledge.

Abstract: Knowledge Tracing is the de-facto standard for inferring student knowledge from performance data. Unfortunately, it does not allow modeling the feature-rich data that is now possible to collect in modern digital learning environments. Because of this, many ad hoc Knowledge Tracing variants have been proposed to model a specific feature of interest. For example, variants have studied the effect of students’ individual characteristics, the effect of help in a tutor, and subskills. These ad hoc models are successful for their own specific purpose, but are specified to only model a single specific feature. We present FAST (Feature Aware Student knowledge Tracing), an efficient, novel method that allows integrating general features into Knowledge Tracing. We demonstrate FAST’s flexibility with three examples of feature sets that are relevant to a wide audience. We use features in FAST to model (i) multiple subskill tracing, (ii) a temporal Item Response Model implementation, and (iii) expert knowledge. We present empirical results using data collected from an Intelligent Tutoring System. We report that using features can improve up to 25% in classification performance of the task of predicting student performance. Moreover, for fitting and inferencing, FAST can be 300 times faster than models created in BNT-SM, a toolkit that facilitates the creation of ad hoc Knowledge Tracing variants.