A Study on Automated Writing/Speech Feedback
| Project/Area Number |
17K13511
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Foreign language education
|
|---|
| Research Institution | Nihon University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2017-04-01 – 2021-03-31
|
| Project Status |
Completed (Fiscal Year 2020)
|
| Budget Amount *help |
¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000)
Fiscal Year 2020: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2019: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2018: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2017: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
|
|---|
| Keywords | 自動採点 / 学習者コーパス / フィードバック / 自動評価 / コーパス / 自然言語処理 / 機械学習 |
|---|
| Outline of Final Research Achievements |
The purpose of the present study is to assess written/spoken English as a foreign language (EFL) using automated scoring techniques. Automated scoring, in which computer technology evaluates and scores written or spoken content, aims to sort a large body of data, which it assigns to a small number of discrete proficiency levels. Objectively measurable features are used as exploratory variables to predict scores defined as criterion variables. We automatically evaluated the L2 speech of 364 Japanese EFL learners. As a result, the accuracy rate of the random forests model using basic information pertaining to speech was 65.66% and that of the model using lexical and grammatical features was 70.88% in total. In addition, we identified some major linguistic futures that are useful for automated feedback. However, we were not able to conduct the feedback experiment in the classroom setting due to the Covid-19.
|
| Academic Significance and Societal Importance of the Research Achievements |
学習者が好きな時間に、好きな場所で繰り返し英語を学習し、フィードバックを受けられるシステムの開発は、社会的に極めて有用である。また、現在のように、感染症対策のためのオンライン授業が多くなっている状況を考えると、自宅学習に活用することができる、自動採点・自動フィードバックを用いた学習コンテンツのニーズは高いと思われる。
|
Report
(5 results)
Research Products
(40 results)
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
[Book] 文化情報学事典2019
Author(s)
村上征勝、小林雄一郎他
Total Pages
850
Publisher
勉誠出版
ISBN
9784585200710
Related Report
-
