Presentation 2008-01-21
Grading support system of short essay using SVM
Junya MURATA, Daisuke KATAGAMI, Katsumi NITTA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we aimed to grade a large amount of papers of the short essay (statement type) examinations efficiently and stably. We have developed and evaluated the grading support system including GUI (Graphical User Interface). By analyzing sample papers which were graded by human graders according to each item in the questions, and by making the pattern classification machine called SVM (Support Vector Machine) learn the pairs of the features and the results, this system calculates the grades of the exam papers of most remainder. Moreover, graders confirm and compile them, which makes the final evaluation of the exam papers. Evaluation experiments made it clear that our automatic grading method with steadiness and high accuracy enough to be used practically was realized without background knowledge about the question.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Essay / Automated Scoring / Support Vector Machine
Paper # AI2007-29,KBSE2007-39
Date of Issue

Conference Information
Committee KBSE
Conference Date 2008/1/14(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Knowledge-Based Software Engineering (KBSE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Grading support system of short essay using SVM
Sub Title (in English)
Keyword(1) Essay
Keyword(2) Automated Scoring
Keyword(3) Support Vector Machine
1st Author's Name Junya MURATA
1st Author's Affiliation Tokyo Institute of Technology Interdisciplinary Graduate School of Science and Engineering()
2nd Author's Name Daisuke KATAGAMI
2nd Author's Affiliation Tokyo Institute of Technology Interdisciplinary Graduate School of Science and Engineering
3rd Author's Name Katsumi NITTA
3rd Author's Affiliation Tokyo Institute of Technology Interdisciplinary Graduate School of Science and Engineering
Date 2008-01-21
Paper # AI2007-29,KBSE2007-39
Volume (vol) vol.107
Number (no) 429
Page pp.pp.-
#Pages 6
Date of Issue