A hybrid approach to content analysis for automatic essay grading

Carolyn P. Rosé; Antonio Roque; Dumisizwe Bhembe; Kurt VanLehn

A hybrid approach to content analysis for automatic essay grading

Carolyn P. Rosé
, Antonio Roque
, Dumisizwe Bhembe
, Kurt VanLehn

Research output: Contribution to conference › Paper › peer-review

Abstract

We present CarmelTC, a novel hybrid text classification approach for automatic essay grading. Our evaluation demonstrates that the hybrid CarmelTC approach outperforms two “bag of words” approaches, namely LSA and a Naive Bayes, as well as a purely symbolic approach.

Original language	English (US)
Pages	88-90
Number of pages	3
State	Published - 2003
Externally published	Yes
Event	2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, HLT-NAACL 2003 - Edmonton, Canada Duration: May 27 2003 → Jun 1 2003

Conference

Conference	2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, HLT-NAACL 2003
Country/Territory	Canada
City	Edmonton
Period	5/27/03 → 6/1/03

ASJC Scopus subject areas

Language and Linguistics
Linguistics and Language

Cite this

A hybrid approach to content analysis for automatic essay grading. / Rosé, Carolyn P.; Roque, Antonio; Bhembe, Dumisizwe et al.
2003. 88-90 Paper presented at 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, HLT-NAACL 2003, Edmonton, Canada.

Research output: Contribution to conference › Paper › peer-review

@conference{8a6e6cc9b61047f1b66edc95b3770b1f,

title = "A hybrid approach to content analysis for automatic essay grading",

abstract = "We present CarmelTC, a novel hybrid text classification approach for automatic essay grading. Our evaluation demonstrates that the hybrid CarmelTC approach outperforms two “bag of words” approaches, namely LSA and a Naive Bayes, as well as a purely symbolic approach.",

author = "Ros{\'e}, \{Carolyn P.\} and Antonio Roque and Dumisizwe Bhembe and Kurt VanLehn",

note = "Funding Information: This research was supported by the ONR, Cognitive Science Division under grant number N00014-0-1-0600 and by NSF grant number 9720359 to CIRCLE. Publisher Copyright: {\textcopyright} HLT-NAACL 2003.All right reserved.; 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, HLT-NAACL 2003 ; Conference date: 27-05-2003 Through 01-06-2003",

year = "2003",

language = "English (US)",

pages = "88--90",

}

TY - CONF

T1 - A hybrid approach to content analysis for automatic essay grading

AU - Rosé, Carolyn P.

AU - Roque, Antonio

AU - Bhembe, Dumisizwe

AU - VanLehn, Kurt

N1 - Funding Information: This research was supported by the ONR, Cognitive Science Division under grant number N00014-0-1-0600 and by NSF grant number 9720359 to CIRCLE. Publisher Copyright: © HLT-NAACL 2003.All right reserved.

PY - 2003

Y1 - 2003

N2 - We present CarmelTC, a novel hybrid text classification approach for automatic essay grading. Our evaluation demonstrates that the hybrid CarmelTC approach outperforms two “bag of words” approaches, namely LSA and a Naive Bayes, as well as a purely symbolic approach.

AB - We present CarmelTC, a novel hybrid text classification approach for automatic essay grading. Our evaluation demonstrates that the hybrid CarmelTC approach outperforms two “bag of words” approaches, namely LSA and a Naive Bayes, as well as a purely symbolic approach.

UR - https://www.scopus.com/pages/publications/84857014142

UR - https://www.scopus.com/pages/publications/84857014142#tab=citedBy

M3 - Paper

SP - 88

EP - 90

T2 - 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, HLT-NAACL 2003

Y2 - 27 May 2003 through 1 June 2003

ER -

A hybrid approach to content analysis for automatic essay grading

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this