A multi-tier NL-knowledge clustering for classifying students' essays

Umarani Pappuswamy, Dumisizwe Bhembe, Pamela W. Jordan, Kurt VanLehn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

In this paper, we describe a multi-tier Natural Language (NL) clustering approach to text classification for classifying students' essays for tutoring applications. The main task of the classifier is to map the students' essay statements into target concepts, namely physics principles and misconceptions. A simple 'Bag-Of-Words (BOW)' classifier using a naïve-Bayes algorithm was unsatisfactory for our purposes as it frequently misclassified due to the semantic relatedness of the NL descriptions of the target concepts. We describe how we used the NL descriptions to define clusters of concepts that reduce the dimensionality of the data when classifying students' essays. The clustering generated multi-tier tagging schemata (cluster, sub-cluster and class) which led to better classification of the student's essay.

Original languageEnglish (US)
Title of host publicationProceedings of the Eighteenth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2005 - Recent Advances in Artifical Intelligence
EditorsI. Russell, Z. Markov
Pages566-571
Number of pages6
StatePublished - 2005
Externally publishedYes
EventRecent Advances in Artifical Intelligence - Eighteenth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2005 - Clearwater Beach, FL, United States
Duration: May 15 2005May 17 2005

Other

OtherRecent Advances in Artifical Intelligence - Eighteenth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2005
CountryUnited States
CityClearwater Beach, FL
Period5/15/055/17/05

Fingerprint

Students
Classifiers
Physics
Semantics

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Pappuswamy, U., Bhembe, D., Jordan, P. W., & VanLehn, K. (2005). A multi-tier NL-knowledge clustering for classifying students' essays. In I. Russell, & Z. Markov (Eds.), Proceedings of the Eighteenth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2005 - Recent Advances in Artifical Intelligence (pp. 566-571)

A multi-tier NL-knowledge clustering for classifying students' essays. / Pappuswamy, Umarani; Bhembe, Dumisizwe; Jordan, Pamela W.; VanLehn, Kurt.

Proceedings of the Eighteenth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2005 - Recent Advances in Artifical Intelligence. ed. / I. Russell; Z. Markov. 2005. p. 566-571.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Pappuswamy, U, Bhembe, D, Jordan, PW & VanLehn, K 2005, A multi-tier NL-knowledge clustering for classifying students' essays. in I Russell & Z Markov (eds), Proceedings of the Eighteenth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2005 - Recent Advances in Artifical Intelligence. pp. 566-571, Recent Advances in Artifical Intelligence - Eighteenth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2005, Clearwater Beach, FL, United States, 5/15/05.
Pappuswamy U, Bhembe D, Jordan PW, VanLehn K. A multi-tier NL-knowledge clustering for classifying students' essays. In Russell I, Markov Z, editors, Proceedings of the Eighteenth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2005 - Recent Advances in Artifical Intelligence. 2005. p. 566-571
Pappuswamy, Umarani ; Bhembe, Dumisizwe ; Jordan, Pamela W. ; VanLehn, Kurt. / A multi-tier NL-knowledge clustering for classifying students' essays. Proceedings of the Eighteenth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2005 - Recent Advances in Artifical Intelligence. editor / I. Russell ; Z. Markov. 2005. pp. 566-571
@inproceedings{f85a7fad380b4981b29277fc87d86fd2,
title = "A multi-tier NL-knowledge clustering for classifying students' essays",
abstract = "In this paper, we describe a multi-tier Natural Language (NL) clustering approach to text classification for classifying students' essays for tutoring applications. The main task of the classifier is to map the students' essay statements into target concepts, namely physics principles and misconceptions. A simple 'Bag-Of-Words (BOW)' classifier using a na{\"i}ve-Bayes algorithm was unsatisfactory for our purposes as it frequently misclassified due to the semantic relatedness of the NL descriptions of the target concepts. We describe how we used the NL descriptions to define clusters of concepts that reduce the dimensionality of the data when classifying students' essays. The clustering generated multi-tier tagging schemata (cluster, sub-cluster and class) which led to better classification of the student's essay.",
author = "Umarani Pappuswamy and Dumisizwe Bhembe and Jordan, {Pamela W.} and Kurt VanLehn",
year = "2005",
language = "English (US)",
isbn = "1577352343",
pages = "566--571",
editor = "I. Russell and Z. Markov",
booktitle = "Proceedings of the Eighteenth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2005 - Recent Advances in Artifical Intelligence",

}

TY - GEN

T1 - A multi-tier NL-knowledge clustering for classifying students' essays

AU - Pappuswamy, Umarani

AU - Bhembe, Dumisizwe

AU - Jordan, Pamela W.

AU - VanLehn, Kurt

PY - 2005

Y1 - 2005

N2 - In this paper, we describe a multi-tier Natural Language (NL) clustering approach to text classification for classifying students' essays for tutoring applications. The main task of the classifier is to map the students' essay statements into target concepts, namely physics principles and misconceptions. A simple 'Bag-Of-Words (BOW)' classifier using a naïve-Bayes algorithm was unsatisfactory for our purposes as it frequently misclassified due to the semantic relatedness of the NL descriptions of the target concepts. We describe how we used the NL descriptions to define clusters of concepts that reduce the dimensionality of the data when classifying students' essays. The clustering generated multi-tier tagging schemata (cluster, sub-cluster and class) which led to better classification of the student's essay.

AB - In this paper, we describe a multi-tier Natural Language (NL) clustering approach to text classification for classifying students' essays for tutoring applications. The main task of the classifier is to map the students' essay statements into target concepts, namely physics principles and misconceptions. A simple 'Bag-Of-Words (BOW)' classifier using a naïve-Bayes algorithm was unsatisfactory for our purposes as it frequently misclassified due to the semantic relatedness of the NL descriptions of the target concepts. We describe how we used the NL descriptions to define clusters of concepts that reduce the dimensionality of the data when classifying students' essays. The clustering generated multi-tier tagging schemata (cluster, sub-cluster and class) which led to better classification of the student's essay.

UR - http://www.scopus.com/inward/record.url?scp=32844471178&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=32844471178&partnerID=8YFLogxK

M3 - Conference contribution

SN - 1577352343

SP - 566

EP - 571

BT - Proceedings of the Eighteenth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2005 - Recent Advances in Artifical Intelligence

A2 - Russell, I.

A2 - Markov, Z.

ER -