Nguyen-Thinh Le

A Review of AI-Supported Tutoring Approaches for Learning Programming

In this paper, we review tutoring approaches of computer-supported systems for learning programming. From the survey we have learned three lessons. First, various AI-supported tutoring approaches have been developed and most existing systems use a feedback-based tutoring approach for supporting students. Second, the AI techniques deployed to support feedback-based tutoring approaches are able to identify the student’s intention, i.e. the solution strategy implemented in the student solution. Third, most reviewed tutoring approaches only support individual learning. In order to fill this research gap, we propose an approach to pair learning which supports two students who solve a programming problem face-to-face.

Autonomous agents in organized localities regulated by institutions

This paper proposes a new metaphor for constructing systems of systems: Autonomous Agents in Organized Localities (AAOL). An agent-based approach is used for modeling structure and behavior of complex systems that consist of (semi-)autonomous systems, where goals, resources, capabilities are described locally while a need for superordinated ”global” regulation exists. The notion of organized localities is used to describe spatially or logically constrained spheres of influence of regulation bodies. Agents inhabit — and can move across — localities; regulation rules are modeled via computational norms and enforced by electronic institutions. A key objective of our work is to explore and advance applicability of AAOL to constructing mechatronic systems with (at least soft) real-time constraints. We describe requirements for modeling systems of systems, and outline the key pillars of AAOL: a conceptual architecture and a metamodel providing the basic constructs for describing AAOL-type systems. A case study of a decentrally organized airport transportation infrastructure illustrates the concepts and the feasibility of AAOL-based systems of systems design.

Automatic Question Generation for Educational Applications – The State of Art

Recently, researchers from multiple disciplines have been showing their common interest in automatic question generation for educational purposes. In this paper, we review the state of the art of approaches to developing educational applications of question generation. We conclude that although a great variety of techniques on automatic question generation exists, just a small amount of educational systems exploiting question generation has been developed and deployed in real classroom settings. We also propose research directions for deploying the question technology in computer-supported educational systems.

A Classification of Adaptive Feedback in Educational Systems for Programming

Over the last three decades, many educational systems for programming have been developed to support learning/teaching programming. In this paper, feedback types that are supported by existing educational systems for programming are classified. In order to be able to provide feedback, educational systems for programming deployed various approaches to analyzing students’ programs. This paper identifies analysis approaches for programs and introduces a classification for adaptive feedback supported by educational systems for programming. The classification of feedback is the contribution of this paper.

Operationalizing the Continuum between Well-Defined and Ill-Defined Problems for Educational Technology

One of the most effective ways to learn is through problem solving. Recently, researchers have started to develop educational systems which are intended to support solving ill-defined problems. Most researchers agree that there is no sharp distinction but rather a continuum between well-definedness and ill-definedness. However, positioning a problem within this continuum is not always easy, which may lead to difficulties in choosing an appropriate educational technology approach. We propose a classification of the degree of ill-definedness of educational problems based on the existence of solution strategies, the implementation variability for each solution strategy, and the verifiability of solutions. The classification divides educational problems into five classes: 1) one single solution, 2) one solution strategy with different implementation variants, 3) a known number of typical solution strategies, 4) a great variety of solution strategies beyond the anticipation of a teacher where solution correctness can be verified automatically, and 5) problems whose solution correctness cannot be verified automatically. The benefits of this problem classification are twofold. First, it helps researchers choose or develop an appropriate modeling technique for educational systems. Second, it offers the learning technology community a communication means to talk about sorts of more or less ill-defined educational problems more precisely.

Using constraint-based modelling to describe the solution space of ill-defined problems in logic programming

Intelligent Tutoring Systems have made great strides in recent years. Many of these gains have been achieved for well-defined problems. However, solving ill-defined problems is important because it can enhance the cognitive, metacognitive and argumentation skills of a student. In this paper, we demonstrate how to apply the constraint-based modelling approach to describe the solution space of ill-defined problems in logic programming. This technology has been integrated into a web-based ITS (INCOM) and has been evaluated with student solutions from past examinations.

Preface for the Special Issue on AI-Supported Education in Computer Science

Over the last two decades, Computer Science (CS) has emerged as a field of study et al.most all levels of education. Computer science has gone beyond an important skill required for a wide range of modern professions, to become an essential competence for everyday life. CS is a young domain that is still developing effective teaching traditions. CS is also a very dynamic domain, where technologies, skills and even subfields are constantly emerging and evolving, challenging CS education researchers to find ways to promote effective education even while its core concepts are being defined. The critical need to increase access to computer science education is highlighted by President Obama’ BCSforAll^ initiative to provide CS education for all K-12 children in the United States (Smith 2016). Because of the central importance of Computer Int J Artif Intell Educ (2017) 27:1–4 DOI 10.1007/s40593-016-0123-y

Automatic question generation for supporting argumentation

Given a discussion topic, students may sometimes not proceed with their argumentation. Can questions which are semantically related to a given discussion topic help students develop further arguments? In this paper, we introduce a technical approach to generating questions upon the request of students during the process of collaborative argumentation. The contribution of this paper lies in combining different NLP technologies and exploiting semantic information to support users develop their arguments in a discussion session via tailored questions of different types.

Adding weights to constraints in intelligent tutoring systems: does it improve the error diagnosis?

The constraint-based modeling (CBM) approach for developing intelligent tutoring systems has shown useful in several domains. However, when applying this approach to an exploratory environment where students are allowed to explore a large solution space for problems to be solved, this approach encounters its limitation: It is not well suited to determine the solution variant the student intended. As a consequence, systems corrective feedback might be not in accordance with the students intention. To address this problem, this paper proposes to adopt a soft computing approach for solving constraint satisfaction problems. The goal of this paper is two-fold. First, we will show that classical CBM is not well-suited for building a tutoring system for tasks which have a large solution space. Second, we introduce a weighted constraint-based model for intelligent tutoring systems. An evaluation study shows that a coaching system for logic programming based on the weighted constraint-based model is able to determine the students intention correctly in 90.3% of 221 student solutions, while a corresponding tutoring system using classical CBM can only hypothesize the students intention correctly in 35.5% of the same corpus.

Can soft computing techniques enhance the error diagnosis accuracy for intelligent tutors

Problems for which multiple solution strategies are possible can be challenging for intelligent tutors. These kinds of problems are often the norm in exploratory learning environments which allow students to develop solutions in a creative manner without many restrictions imposed by the problem solving interface. How can intelligent tutors determine a students intention in order to give appropriate feedback for problems with multiple, quite different solutions? This paper focuses on improving the diagnosis capabilities of constraint-based intelligent tutors with respect to supporting problems with multiple possible solution strategies. An evaluation study showed that by applying a soft-computing technique (a probabilistic approach for constraint satisfaction problems), the diagnostic accuracy of constraint-based intelligent tutors can be improved.