Kazuhisa Seta

Content-Dependent Question Generation for History Learning in Semantic Open Learning Space

This research’s objective is to support learners in self-directed learning of history in an open learning space. Learners who request help are provided with a list of questions to orient them to new information. All the support is provided only on request and gives them multiple possibilities to give them more freedom in self-directed learning. The originality of our research is that the generated questions are content-dependent. To be able to generate such support, we had to overcome one major problem: the information in the open learning space needs to be understood by our system. The construction of this “semantic open learning space” permits the system to generate questions depending on the studied contents and the learner’s concept map.

Social network service with maturity level for science teachers

To support Japanese teachers with sharing their knowledge on digital contents usage, this paper proposes a social networking service. While the digital contents prepared by Japan Science and Technology Agency are attractive for innovating education, most teachers spend much time to prepare their classes. We have found a necessity to define a maturity level for teachers on sharing knowledge. This paper proposes not only a user interface with a recommended message by maturity level but also an expanded data model for implementation. This proposal is expected to save time for preparing ICT-based classes and to improve classes by sharing knowledge.

Improved method for linguistic expression of time series with global trend and local features

We have various kinds of time series such as stock prices. We understand them via their linguistic expressions in a natural language rather than conventional stochastic models. We propose an improved method to have a linguistic expression with a global trend and local features of time series. A global trend is extracted via aggregated values on the fuzzy intervals in the temporal axis and local features are specified as the positions of locally large differences between the original data and the data representing the global trend. We apply the method to the data of Multimodal Summarization for Trend Information (MuST).

Capturing a Conceptual Model for End-User Programming: Task Ontology As a Static User Model

To realize a human friendly conceptual level programming environment, it is very important to build a static user model based on the analysis of what concepts are most important for end-users when performing the task and which concepts of a problem solving specification could be out of their awareness. We have investigated a task ontology for building the static user model. Putting task ontology on the basis of a Conceptual LEvel Programming Environment, CLEPE, provides three major advantages: 1. It provides human-friendly primitives in terms of which users can easily describe their own problem solving process (descriptiveness, readability). 2. The systems with the ask ontology can simulate the problem solving process at an abstract level in terms of conceptual level primitives (conceptual level operationality). 3. It provides the ontology author with an environment for building a task ontology so that he/she can build a consistent and useful ontology.

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.

An ontological approach to interactive navigation for problem solving oriented learning processes

Our research aim is to propose a support model for problem‐solving oriented learning (PSOL) and implement a humancentric system that supports learners and thereby develops their ability. We propose a human‐centric interactive framework for PSOL by employing the research results in the educational psychology field. The characteristic of our research is that our system understands the principle knowledge to support users through human‐computer interactions. It is very important to clarify the principle knowledge of the target application domain and develop the system based on it. We call the principle knowledge as ontology. By embedding ontology into the basis of a system, we can implement a more positive navigation function. In this paper, we analyze the learners’ cognitive activities in PSOL, propose a support model that encourages self‐regulated planning processes, and illustrate an interactive environment for making effective problem‐solving and learning processes based on the ontology.

Adaptive self-directed learning support by question generation in a semantic open learning space

The objective of this research is to give learners content-dependent scaffolding during self-directed learning: the system is able to generate content-dependent support adapted to the learners. Learners use a system to perform a learning task in the domain of history. They have to build a concept map containing a chronology using the system. To be able to support, we combined multiple semantic information sources and Wikipedia, for the natural language information, to create a semantic open learning space. The system provides advice by generating questions based on the semantic information and enhancing document based on the Wikipedia corresponding to the semantic information. All the advices are provided on demand and are generated depending on the learners concept map for adaptive support question generation. The generated questions aim to lead the learners to new knowledge by deepening their understanding.

Development of Meta-Learning Support System based on Model based Approach

Meta-cognition plays an important role in acquiring and transferring expertise. Although we recognize the necessity of building a learning scheme for developing meta-cognitive skills, little knowledge for it has been acquired. We try to accumulate knowledge of meta-learning support system development in presentation based meta-learning scheme. Many researchers try to develop meta-learning support systems but their design principles are not necessarily described explicitly. Consequently, the know-how of developing meta-learning support system cannot be accumulated. Therefore, we adopt design model based approach to confront the problem. In our learning scheme, we provide a presentation task in specific learning area to a learner, who thinks he/she had already learned that specific topic. In this learning scheme, we intend to give the learner a chance to reflect his/her own learning processes. In this paper, we propose a guidance function to encourage learners’ reflection for meta-learning based on a design model. References [1] Bransford, John, Ann Brown, and Rodney Cocking, eds., Brain, Mind, Experience, and School., in How People Learn, National Academy Press, Washington, DC, 2000 [2] Brown, A.L., Bransford, J.D., Ferrara, R.A., and Campione, J.C.: Learning, Remembering, and Understanding’, In: E. M. Markman & J. H. Flavell. (Eds.), Handbook of child psychology (4th ed.) Cognitive Development, Vol. 3, Wiley: New York, pp. 515–529, 1983 [3] Erich Gamma, Richard Helm, Ralph Johnson, John M. Vlissides, Design Patterns: Elements of Reusable Object-Oriented Software, Addison-Wesley Professional; illustrated edition, 1994 [4] Flavell, J. H.: Metacognitive aspects of problem solving, In L. Resnick (Ed.): The Nature of Intelligence, Lawrence Erlbaum Associates: Hillsdale, NJ, pp. 231-235, 1976 [5] Kashihara, A., Taira, K., Shinya, M., and Sawazaki, K: Cognitive Apprenticeship Approach to Developing Meta-Cognitive Skill with Cognitive Tool for Web-based Navigational Learning, Proc. of the IASTED International Conference on Web-Based Education (WBE2008), Innsbruck, Austria, pp.351-356 (2008.3.17-19). [6] Kayashima, M., Inaba, A. and Mizoguchi, R.: What Do You Mean by to Help Learning of Metacognition?, Proc. of the 12th Artificial Intelligence in Education (AIED2005), pp. 346-353, Amsterdam, The Netherlands, July 18-22, 2005. [7] Kojima, K., & Miwa, K.. A Case Retrieval System for Mathematical Learning from Analogical Instances. Proc. of the International Conference on Computers in Education ( ICCE), pp. 1124-1128, (2003) [8] Maeno. H., & Seta, K., “Guidance Generation for Facilitating Meta-Cognitive Learning Through Presentation Task,* Proc. of the 2009 International Conference on Multimedia, Information Technology and its Applications, IEEE Press, ISSN 1975-4736, pp. 5-8, Osaka, Japan, 2009 [9] Nakano, A., Hirashima, T., Takeuchi, A., Developing and evaluation of a computer-based problem posing in the case of arithmetical word problems, The Fourth International Conference on Computer Applications, ICCA2006, (2006) [10] Okamoto, N., Review of Metacognitive Research – from educational implications to teaching methods -, Journal of Japanese Society for Information and Systems in Education, Vol.19, No.3, pp. 178-187, (2002) [11] Seta, K. & Ikeda, M., “Conceptualizations for Designing a Learning System to Facilitate Meta-Cognitive Learning”, In Proceedings of World Conference on Educational Multimedia, Hypermedia and Telecommunications (ED-MEDIA), pp.2134-2143, Vienna, Austria, 2008 [12] Seta, K., and Ikeda, M.: Design of an Environment for Developing Presentation Skills, Proc. of the International Conference on Computers in Education (ICCE-06), Beijing, China, pp. 29-36, 2006

A Conversational Agent to Encourage Willingness to Communicate in the Context of English as a Foreign Language

Abstract We propose an embodied conversational agent based on the willingness to communicate (WTC) model in L2 to help increase WTC in the context of English as a Foreign Language (EFL) by providing users with various daily conversation contexts. To simulate realistic and efficient conversations, we adopted a semantic approach in the response generation and created a system with flexible and adaptable domain knowledge, users intent detection, and mixed-initiative conversation strategy. Our evaluation of the proposed system demonstrated its potential to increase WTC in the EFL context.

Learning environment for improving Critical Thinking skills in nursing domain

For advance of the quality of medical care, nurses must perform Critical Thinking (CT) processes to clarify the evidence of ones own decision-making explicitly and to validate it. To train CT skills, it is important to analyse characteristics of CT task as a base of our learning scheme design. In this paper, we firstly analyse the characteristics of CT to specify design principle for our learning system based on the analysis. Then, we propose a learning system which facilitates valid decision-making processes. And then, we illustrate a scenario of a learners system utilisation to encourage CT learning.