Special Session: Intelligent Tutoring and Help Systems

1987 ◽  
Vol 31 (3) ◽  
pp. 280-280
Author(s):  
Philip J. Smith ◽  
Elliot Soloway ◽  
John Carroll

In recent years, considerable effort has been focused on the development of computational models of expert human performance. One class of expertise that has been studied is that of human tutors. The resultant intelligent tutoring systems are intended to provide the user with the “instructional advantage that a sophisticated human tutor can provide,” (Anderson, Boyle and Reiser, 1985). This line of research is of interest to the human factors community for two reasons: 1. Intelligent tutoring systems offer potential tools for use in training and educational programs, a long-standing area of interest to human factors researchers and practitioners; 2. There are many human factors and human performance issues that should be addressed in the design of such tutoring systems. The speakers in this special session will provide an overview of research issues in the design of intelligent tutoring systems. Relevant conceptual issues and approaches will be highlighted in the context of a variety of application areas. Included will be a discussion of the “use of intelligent system monitors that allow users to integrate the time and effort spent on learning with actual use of a system”, (Carroll and McKendree, 1987).

Author(s):  
Carolina González ◽  
Juan Carlos Burguillo ◽  
Martín Llamas ◽  
Rosalía Laza

Intelligent Tutoring Systems (ITSs) are educational systems that use artificial intelligence techniques for representing the knowledge. ITSs design is often criticized for being a complex and challenging process. In this article, we propose a framework for the ITSs design using Case Based Reasoning (CBR) and Multiagent systems (MAS). The major advantage of using CBR is to allow the intelligent system to propose smart and quick solutions to problems, even in complex domains, avoiding the time necessary to derive those solutions from scratch. The use of intelligent agents and MAS architectures supports the retrieval of similar students models and the adaptation of teaching strategies according to the student profile. We describe deeply how the combination of both technologies helps to simplify the design of new ITSs and personalize the e-learning process for each student


2000 ◽  
Author(s):  
Christine Mitchel ◽  
Alan Chappell ◽  
W. Gray ◽  
Alex Quinn ◽  
David Thurman

Author(s):  
Ekaterina Kochmar ◽  
Dung Do Vu ◽  
Robert Belfer ◽  
Varun Gupta ◽  
Iulian Vlad Serban ◽  
...  

AbstractIntelligent tutoring systems (ITS) have been shown to be highly effective at promoting learning as compared to other computer-based instructional approaches. However, many ITS rely heavily on expert design and hand-crafted rules. This makes them difficult to build and transfer across domains and limits their potential efficacy. In this paper, we investigate how feedback in a large-scale ITS can be automatically generated in a data-driven way, and more specifically how personalization of feedback can lead to improvements in student performance outcomes. First, in this paper we propose a machine learning approach to generate personalized feedback in an automated way, which takes individual needs of students into account, while alleviating the need of expert intervention and design of hand-crafted rules. We leverage state-of-the-art machine learning and natural language processing techniques to provide students with personalized feedback using hints and Wikipedia-based explanations. Second, we demonstrate that personalized feedback leads to improved success rates at solving exercises in practice: our personalized feedback model is used in , a large-scale dialogue-based ITS with around 20,000 students launched in 2019. We present the results of experiments with students and show that the automated, data-driven, personalized feedback leads to a significant overall improvement of 22.95% in student performance outcomes and substantial improvements in the subjective evaluation of the feedback.


Sign in / Sign up

Export Citation Format

Share Document