Research on development of learning advice system using answer process analysis as teacher data

Research Project

Project/Area Number	15K12169
Research Category	Grant-in-Aid for Challenging Exploratory Research
Allocation Type	Multi-year Fund
Research Field	Learning support system
Research Institution	Nagoya Institute of Technology (2016-2017) Kyushu University (2015)
Principal Investigator	Hayashi Atsuhiro 名古屋工業大学, 工学(系)研究科(研究院), 教授 (70189637)
Research Collaborator	Tatsuoka Kikumi K. 元Columbia University Tatsuoka Curtis Case Western Reserve University
Project Period (FY)	2015-04-01 – 2018-03-31
Project Status	Completed (Fiscal Year 2017)
Budget Amount *help	¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000) Fiscal Year 2017: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000) Fiscal Year 2016: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000) Fiscal Year 2015: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Keywords	学習診断 / 問題分析 / 解答過程解析 / Task Analysis / 学習達成度 / 教育評価 / 機械学習
Outline of Final Research Achievements	Rule Space Method (RSM) is a technique developed in the domain of the cognitive science. It starts from the use of an incidence matrix Q that characterizes the underlying cognitive processes and knowledge (Attribute) involved in each Item. It is a grasping method of each examinee's mastered/non-mastered learning level (Knowledge State, KS) from item response patterns, and a list of all the possible KSs can be generated algorithmically by applying Boolean Algebra to the incidence matrix Q. But the task analysis that is the work to find some suitable attributes for each item is quite hard. We have found that RSM and NNM are similarities between the results from the two approaches, and moreover they have complementary characteristics when applied in practice. So, in this research, we discuss the comparisons of both approaches by focusing on the structure of the NNM and of KSs in the RSM. And we show an application result for a reasoning test.