Integrating various features to grade students' writings based on improved multivariate Bernoulli model

Tao Hsing Chang, Chien Liang Liu, Shou Yen Su, Yao-Ting Sung

Research output: Contribution to journalArticle

Abstract

Most of AES systems use various writing features as the scoring criteria. A valid mathematical model then integrates the various features demonstrated in the essay and calculates a possible score. Many studies have addressed the advantages and necessity of using multiple features to predict the score of an essay. These traditional prediction models have difficulty integrating various types of numerical data. However, the values, calculated by the features proposed by recent researches, are often not continuous numerical values. This study will propose an improved multivariate Bernoulli model to integrate features to predict an essay score even the value types of features are different

Original languageEnglish
Pages (from-to)45-52
Number of pages8
JournalInformation (Japan)
Volume17
Issue number1
Publication statusPublished - 2014 Jan 1

Fingerprint

Students
Mathematical models

Keywords

  • Automatic essay scoring
  • Chinese
  • Feature integration
  • Multivariate Bernoulli model

ASJC Scopus subject areas

  • Information Systems

Cite this

Integrating various features to grade students' writings based on improved multivariate Bernoulli model. / Chang, Tao Hsing; Liu, Chien Liang; Su, Shou Yen; Sung, Yao-Ting.

In: Information (Japan), Vol. 17, No. 1, 01.01.2014, p. 45-52.

Research output: Contribution to journalArticle

Chang, Tao Hsing ; Liu, Chien Liang ; Su, Shou Yen ; Sung, Yao-Ting. / Integrating various features to grade students' writings based on improved multivariate Bernoulli model. In: Information (Japan). 2014 ; Vol. 17, No. 1. pp. 45-52.
@article{aa856cce5780494986251895309eb2ff,
title = "Integrating various features to grade students' writings based on improved multivariate Bernoulli model",
abstract = "Most of AES systems use various writing features as the scoring criteria. A valid mathematical model then integrates the various features demonstrated in the essay and calculates a possible score. Many studies have addressed the advantages and necessity of using multiple features to predict the score of an essay. These traditional prediction models have difficulty integrating various types of numerical data. However, the values, calculated by the features proposed by recent researches, are often not continuous numerical values. This study will propose an improved multivariate Bernoulli model to integrate features to predict an essay score even the value types of features are different",
keywords = "Automatic essay scoring, Chinese, Feature integration, Multivariate Bernoulli model",
author = "Chang, {Tao Hsing} and Liu, {Chien Liang} and Su, {Shou Yen} and Yao-Ting Sung",
year = "2014",
month = "1",
day = "1",
language = "English",
volume = "17",
pages = "45--52",
journal = "Information",
issn = "1343-4500",
publisher = "International Information Institute",
number = "1",

}

TY - JOUR

T1 - Integrating various features to grade students' writings based on improved multivariate Bernoulli model

AU - Chang, Tao Hsing

AU - Liu, Chien Liang

AU - Su, Shou Yen

AU - Sung, Yao-Ting

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Most of AES systems use various writing features as the scoring criteria. A valid mathematical model then integrates the various features demonstrated in the essay and calculates a possible score. Many studies have addressed the advantages and necessity of using multiple features to predict the score of an essay. These traditional prediction models have difficulty integrating various types of numerical data. However, the values, calculated by the features proposed by recent researches, are often not continuous numerical values. This study will propose an improved multivariate Bernoulli model to integrate features to predict an essay score even the value types of features are different

AB - Most of AES systems use various writing features as the scoring criteria. A valid mathematical model then integrates the various features demonstrated in the essay and calculates a possible score. Many studies have addressed the advantages and necessity of using multiple features to predict the score of an essay. These traditional prediction models have difficulty integrating various types of numerical data. However, the values, calculated by the features proposed by recent researches, are often not continuous numerical values. This study will propose an improved multivariate Bernoulli model to integrate features to predict an essay score even the value types of features are different

KW - Automatic essay scoring

KW - Chinese

KW - Feature integration

KW - Multivariate Bernoulli model

UR - http://www.scopus.com/inward/record.url?scp=84899694454&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899694454&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84899694454

VL - 17

SP - 45

EP - 52

JO - Information

JF - Information

SN - 1343-4500

IS - 1

ER -