Design and Implementation of an Automatic Scoring Model Using a Voting Method for Descriptive Answers (투표 기반 서술형 주관식 답안 자동 채점 모델의 설계 및 구현)

허정만; So-Young Park (박소영)

Design and Implementation of an Automatic Scoring Model Using a Voting Method for Descriptive Answers

Journal of The Korea Society of Computer and Information
Abbr : JKSCI
2013, 18(8), pp.17-25
Publisher : The Korean Society Of Computer And Information
Research Area : Engineering > Computer Science

허정만 ¹, So-Young Park ²

¹상명대학교 디지털미디어학부
²상명대학교

Accredited

ABSTRACT

TIn this paper, we propose a model automatically scoring a student's answer for a descriptive problem by using a voting method. Considering the model construction cost, the proposed model does not separately construct the automatic scoring model per problem type. In order to utilize features useful for automatically scoring the descriptive answers, the proposed model extracts feature values from the results, generated by comparing the student's answer with the answer sheet. For the purpose of improving the precision of the scoring result, the proposed model collects the scoring results classified by a few machine learning based classifiers, and unanimously selects the scoring result as the final result. Experimental results show that the single machine learning based classifier C4.5 takes 83.00% on precision while the proposed model improve the precision up to 90.57% by using three machine learning based classifiers C4.5, ME, and SVM.

KEYWORDS

Automatic Scoring Model, Machine Learning based Classifier, Voting Method

Citation status

* References for papers published after 2023 are currently being built.

[journal] C. G. Jung / 2003 / A Developmental Plan on Public Education in Digital Times, 21c / Journal of The Korea Society of Computer and Information 8(1) : 120~128

[journal] 김혜정 / 2011 / Development of a Teaching and Learning Model for Educational Usage of Web 2.0 and Its Effect Analysis / 한국컴퓨터정보학회논문지 / 한국컴퓨터정보학회 16(10) : 45~52

[journal] 진경애 / 2007 / Development of automated scoring system for English writing / 영어어문교육 / 한국영어어문교육학회 13(1) : 235~259

[journal] 김광백 / 2005 / Performance Assessment System using Fuzzy Reasoning Rule / 한국컴퓨터정보학회논문지 / 한국컴퓨터정보학회 10(1) : 209~216

[thesis] O. Y. Kwon / 2004 / The Design and Implementation of Web-based Subjective questions Grading Algorithm / The Graduate School of Education. Hanseo University

[journal] 강원석 / 2007 / Design and Implementation of a Subjective-type Evaluation System Using Syntactic and Case-Role Information / 컴퓨터교육학회 논문지 / 한국컴퓨터교육학회 10(5) : 61~70

[journal] 박희정 / 2003 / Design and Implementation of a Subjective-type Evaluation System Using Natural Language processing Technique / 컴퓨터교육학회 논문지 / 한국컴퓨터교육학회 6(3) : 207~216

[report] E. H. No / 2012 / Developing an Automatic Content Scoring Program for Short Answer Korean Items in Large-Scalse Assessments / Korea Institute for Curriculum and Evaluation : 3~48

[report] Y. R. Kim / 2011 / (A)review on NAEA Korean test based on CURRV framework / Korea Institute for Curriculum and Evaluation : 1~12

[journal] 박정 / 2009 / Validating an Automated Scoring System of Constructed-response items for applications / 교육평가연구 / 한국교육평가학회 22(3) : 615~631

[journal] 정은미 / 2009 / Design and Implementation of Automatic Marking System for a Subjectivity Problem of the Program / 멀티미디어학회논문지 / 한국멀티미디어학회 12(5) : 767~776

[journal] 조지민 / 2007 / A Study on design of The Internet-based scoring system for constructed responses / 컴퓨터교육학회 논문지 / 한국컴퓨터교육학회 10(2) : 89~100

[thesis] W. J. Cho / 2006 / An Intelligent Marking System based on Semantic Kernel and Korean WordNet / Graduate School. Hallym University

[journal] J. S. Oh / 2005 / A Descriptive Question Marking System based on Semantic Kernels / Journal of Korean Institute of Information Technology 3(4) : 95~104

[thesis] D. K. Chung / 2002 / Subjective Questions Scoring System Using Vector Similarity and Thesaurus / The Graduate School of Education. Dongguk University

[confproc] J. H. Cho / 2009 / An Autonomous Assessment of a Short Essay Answer by Using the BLEU / HCI2009 : 606~605

[thesis] S. H. Jang / 2008 / Planning and realizing the Automatic Grading System for Subjective Questions Through an Analysis of Question Types / The Graduate School of Education. Andong National University

[journal] Van Halteren, H / 2001 / Improving accuracy in word class tagging through the combination of machine learning systems / Computational linguistics 27(2) : 199~229

[confproc] Van Halteren, H / 1998 / Improving data driven wordclass tagging by system combination / Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics 1 : 491~497

[journal] 이정태 / 2008 / Text-Confidence Feature Based Quality Evaluation Model for Knowledge Q&A Documents / 정보과학회논문지 : 소프트웨어 및 응용 / 한국정보과학회 35(10) : 608~615

[confproc] J. T. Lee / 2007 / Predicting the quality of answers using surface linguistic features / In Proceedings of the 6th International Conference on Advanced Language Processing and Web Information Technology, pp : 111~116

[book] Quinlan, J. Ross / 1993 / C4.5:Programs for Machine Learning / Morgan Kaufmann Publishers

[thesis] H. J. Jung / 2005 / A Maximum Entropy Approach to Korean Part-of-Speech Tagging / Information & Communications of Engineering, Myongji University

[book] Vapnik / 1999 / The Nature of Statistical Learning Theory / Springer-Verlag

[thesis] S. Y. Kim / 2002 / Incremental Supervised Learning based on SVM with Unlabeled Documents / The Graduate School of Computer Science. Yonsei University

[confproc] T. Joachims / 2000 / Estimating the Generalization Performance of an SVMEfficiently / Proceedings of the 17th International Conference on Machine Learning (ICML 2000) : 431~438

[thesis] S. Z. Lee / 1999 / New Statistical Models for Automatic Part-of-Speech Tagging / 박사 / Korea University

[journal] 김성영 / 2008 / Object of Interest Extraction Using Gabor Filters / 한국컴퓨터정보학회논문지 / 한국컴퓨터정보학회 13(2) : 87~94

KJCKorea
Journal Central

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65