Towards an Intelligent Tutoring System for Logical Reasoning in Multiple Contexts

In this paper we present a participatory approach to design Logic-Muse, an Intelligent Tutoring System that helps learners develop reasoning skills in multiple contexts (situations). The study was conducted jointly with the active participation of experts

  • PDF / 146,373 Bytes
  • 7 Pages / 439.37 x 666.142 pts Page_size
  • 3 Downloads / 179 Views

DOWNLOAD

REPORT


stract. In this paper we present a participatory approach to design Logic-Muse, an Intelligent Tutoring System that helps learners develop reasoning skills in multiple contexts (situations). The study was conducted jointly with the active participation of experts in the field of logic and the psychology of reasoning. An explicit catalogue of systematic errors in classical logic is built, followed by an explicit representation and encoding of the semantic knowledge behind reasoning as well as reasoning procedural structures and meta-structures. Logic-Muse innovates through its design rationale, which leads to strong structures on which learning is based. It also innovates with the projection of reasoning skills in a variety of well-defined classes of situations to ensure an absolute mastery of reasoning skills regardless of the content effect. Keywords: Intelligent tutoring system learning



Reasoning skills



Formal logic

1 Introduction Many experiments in cognitive science have shown that systematic errors are common in human logical reasoning [5]. A number of questions are raised when looking for solutions to improve human skills in this domain: What are the phenomena involved in learning logical reasoning skills? Does modeling allow to elicit them? What are the adaptive strategies to foster the development of logical competence? What are the characteristics of an Intelligent Tutoring System (ITS) to support this learning? Answers cannot be brought to these questions without an appropriate elicitation and understanding of the knowledge behind logical reasoning and errors made by humans. Logic-Muse project aims at studying the fundamentals of learning logical reasoning skills, to understand the difficulties in such learning and to build an ITS that can detect, diagnose and correct reasoning errors in various situations. To do so, we have adopted a participatory design approach aiming at: (1) providing a catalog of current logical reasoning errors; (2) developing an original theory of the causes of these errors including a logical reasoning competence theory; (3) analyzing the formal structures of information processing we find in logical systems; (4) developing an intelligent tutoring system for helping learners improve their reasoning skills and (5) helping © Springer International Publishing Switzerland 2015 G. Conole et al. (Eds.): EC-TEL 2015, LNCS 9307, pp. 460–466, 2015. DOI: 10.1007/978-3-319-24258-3_40

Towards an Intelligent Tutoring System for Logical Reasoning

461

experts to redefine the nature of human rationality using the ITS as a test bed for the testing of other assumptions in the cognitive science of reasoning. This paper describes some results of this unique approach. It is organized as follow: Sect. 2 presents the theoretical background of our work, which highlights the main differences with some related works. Section 3 describes the system as well as the approach that leads to its main building blocks.

2 Logical Reasoning and Intelligent Tutoring Systems Multiple Standpoints on Reasoning Lea