Project/Area Number |
18K18684
|
Research Category |
Grant-in-Aid for Challenging Research (Exploratory)
|
Allocation Type | Multi-year Fund |
Review Section |
Medium-sized Section 9:Education and related fields
|
Research Institution | National Institute for Educational Policy Research |
Principal Investigator |
Yasuno Fumiko 国立教育政策研究所, 教育課程研究センター基礎研究部, 総括研究官 (00370081)
|
Project Period (FY) |
2018-06-29 – 2022-03-31
|
Project Status |
Completed (Fiscal Year 2021)
|
Budget Amount *help |
¥6,110,000 (Direct Cost: ¥4,700,000、Indirect Cost: ¥1,410,000)
Fiscal Year 2020: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2019: ¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
Fiscal Year 2018: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
Keywords | 数学試験 / 手書き認識 / 手書き数式入力 / 記述形式 |
Outline of Final Research Achievements |
We collected handwritten written responses to extended constructed-response questions in a mathematics examination as online "digital ink" data by inputting the data into a tablet device through the use of a stylus,and analyzed the data.The results of the analysis, which focused on the frequency of answer input and rewriting of answers, empirically showed that about 95% of mathematical expressions were correctly recognized by online handwritten mathematical expression recognition, and that the number of rewrites of answers was low.Furthermore, we were able to empirically verify that the mathematics-specific sequence of mathematical formula strokes can occur.Our results suggest that the method adopted in this study, in which the respondent confirms the recognition result and determines it, would be highly effective for automatic scoring and scoring assistance.We were unable to obtain results that could demonstrate effectiveness with respect to shape recognition.
|
Academic Significance and Societal Importance of the Research Achievements |
数学の記述式試験は,受験者が文字,数式,図形,グラフ等を自由に記述した解答による評価であり,それらの採点はその専門性を有している者が行っている。数学は,教科の特性からも,評価において思考力・表現力が重視される。本来,問題を解くということは,思考過程を経ながら行うものであり,現在,実用化されている限定された形式のキーボート入力よりも,手書き(入力)の方が長けているだけでなく,広汎な能力を測ることができる。そこで,本研究の成果は,数学試験の手書きの記述式解答の数式に関して,自動採点や採点支援の実現に向けた基礎的資料となる。
|