Jun’ichi Toyoda

How Can We Form Effective Collaborative Learning Groups

Our research objectives include constructing a collaborative learning support system that detects appropriate situation for a learner to join in a collaborative learning session, and forms a collaborative learning group appropriate for the situation dynamically. In this paper, we describe a system of concepts concerning learning goals expected to attain by learners through collaborative learning process with justification by the learning theories. With the ontology, it will be possible to compare and synthesize the learning theories to design the collaborative learning settings.

Context-sensitive filtering for browsing in hypertext

Modeling of the user’s interests is one of the most important issues to support a user to gather information. Although there are several promising methods to infer the interests from the user’s browsing behavior, they assume that the interests are consistent during the information gathering. However, in browsing which is one of the most popular ways to gather information, the user’s interests are often strongly dependent on the local context of the browsing. This paper describes a method to model the user’s shifting interests from the browsing history. An information filtering method using the model of the interests has been implemented. We call it “context-sensitive filtering.” The results of an experimental evaluation, by real users’ browsing for an encyclopedia in CDROM format, are also reported.

A framework for ICAI systems based on inductive inference and logic programming

The main components of an Intelligent Computer-Assisted Instruction (ICAI) system are the expertise, the student model and tutoring strategies. The student model manages what the student dose and dose not understand, and the performance of an ICAI system depends largely on how well the student model approximates the human student. We propose a new framework for ICAI systems which uses the inductive inference for constructing the student model from the student’s behavior. In the framework, both the expertise and the student model are represented as Prolog programs, which enables to express the meta-knowledge that is the knowledge of how to use the knowledge. Since the construction of the student models is performed independently of the expertise, the framework is domain-independent. Therefore, an ICAI system for any subject area can be built with the framework. As an example, the ICAI system teaching chemical reaction is presented together with a sample performance. The authors believe that the new framework for ICAI systems based on logic programming and inductive inference could be a breakthrough of the future ICAI systems.

Adaptive Navigation Path Previewing for Learning on the Web

The main issue addressed in this paper is how to help learners plan a navigation path in existing web-based learning resources, which is an important process of self-directed learning in hyperspace. Our approach to this issue is to provide learners with the adaptive preview of a sequence of web pages as navigation path. Following the idea of path previewing, we have developed an assistant system. The system displays an overview of a web page selected by learners from a hyperspace map, by extracting information from the HTML document file related to the navigation path-planning context. It also enables learners to transform a sequence of previewed pages into a navigation path plan.

A navigation path planning on the Web

The main issue addressed in this paper is how to help learners navigate in existing Web-based learning resources. Our approach to this issue is to provide learners with a space, in which they can see through WWW pages to plan a navigation path in a learner-centered way. We describe an assistant system for the navigation path planning, which is composed of a hyperspace map, page previewer and path previewer. The page previewer generates an overview of each WWW page in the map by extracting representative information from the HTML file. The path previewer helps learners make a sequence of the pages previewed as a navigation path plan. These facilities help learners decide which page to visit and plan a navigation path without visiting hyperspace.

A Framework for ICAI Systems Based on Inductive Inference and Logic Programming

The main components of an Intelligent Computer-Assisted Instruction (ICAI) system are the expertise, the student model and tutoring strategies. The student model manages what the student does and does not understand, and the performance of an ICAI system depends largely on how well the student model approximates the human student. We propose a new framework for ICAI systems which uses the inductive inference for constructing the student model from the students behavior. In the framework, both the expertise and the student model are represented as Prolog programs, which enables to express the meta-knowledge that is the knowledge of how to use the knowledge. Since the construction of the student model is performed independently of the expertise, the framework is domain-independent. Therefore, an ICAI system for any subject area can be built with the framework. As an example, the ICAI system teaching chemical reaction is presented together with a sample performance. The authors believe that the new framework for ICAI systems based on logic programming and inductive inference could be a breakthrough of the future ICAI systems.

Supporting Interaction Analysis for Collaborative Learning

Many of software designers of CSCL environment have been suffering from complex and subtle educational requirements offered by clients. One of major causes of the problem they face is the lack of shared understanding of collaborative learning. We do not know what design rationale of CSCL environment is and even do not have common vocabulary to describe what the collaborative learning is. In this research, we are aiming at supporting such complex instructional design (ID) process of CSCL environment. To fulfill the aim we have been constructing an ontology to represent CSCL session[1,2]. The ontology will work as both vocabulary to describe the session and design patterns referred to during the instructional design process. To represent learning scenarios using the ontology will facilitate users’ shared understandings and reuse the scenarios. It is useful to store and provide effective learning scenarios as design patterns. As the first step to fulfill our aim, we adopt learning theories as foundation to analyze, design, and develop the learning sessions. The design patterns inspired by the theories provide design rationale for CSCL design.

A step towards integration of learning theories to form an effective collaborative learning group

We are aiming at building a sophisticated ontology through a survey of existing learning theories. On top of that, our research objectives include constructing a collaborative learning (CL) support system that detects appropriate situation for a learner to join in a CL session, and forms a CL group appropriate for the situation dynamically. To fulfill these objectives, we have to consider the following: n n1. n nHow to detect the appropriate situation to start a CL session and to set up the learning goal, n n n n n2. n nHow to form an effective group which ensures educational benefits to the members of the group, and n n n n n3. n nHow to facilitate desired interaction among learners in the learning group. n n n n n n nWe have discussed item 1 in our previous papers, and now focus on item 2.

Annotating Exploration History and Knowledge Mapping for Learning with Web-Based Resources

Exploring hyperspace provided by hypermedia/hypertexts often involves constructing knowledge from the contents that have been explored. This would enhance learning. However, learners often fail in knowledge construction since what and why they have explored so far become hazy as the exploration progresses. The main way to resolve this problem is to encourage learners to reflect on what they have constructed during exploration in hyperspace. The reflection also involves rethinking the exploration process that they have carried out since it has a great influence on their knowledge construction. In particular, exploration purposes, which mean the reasons why the learners have searched for the next node in hyperspace, play a crucial role in knowledge construction. For instance, a learner may search for the meaning of an unknown term to supplement what is learned at the current node or look for elaboration of the description given at the current node. Each exploration purpose would provide its own way to shape the knowledge structure. The reflection support accordingly needs to adapt to their exploration activities and the knowledge structure being constructed by the learners.