Intelligent computer classification of english writing errors

Brendan Flanagan, Chengjiu Yin, Takahiko Suzuki, Sachio Hirokawa

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

4 Citations (Scopus)

Abstract

An important issue in education systems is the ability to determine the characteristics of learners and then provide intelligent and informed guidance in response. The authors of this paper have a long-term research goal to provide language learners with the ability to determine and improving their weaknesses. However, to achieve this goal a sizable amount of manually classified data is required. The task is both time consuming and labor intensive. In this paper a system was built to help intelligently classify the errors in an English learner's writings into categories (Kroll 1990, Weltig 2004). Using a randomly selected manually classified sample as training data, it was determined that there is a positive correlation between the number of samples for each error category and the effectiveness of the model created by applying SVM machine learning to the writings of language learners on the Lang-8 website. It is intended that the classification results will be used to accelerate the manually process classification and increase the amount of training data available for use.

Original languageEnglish
Title of host publicationIntelligent Interactive Multimedia Systems and Services. Proceedings of the 6th International Conference on Intelligent Interactive Multimedia Systems and Services (IIMSS2013)
EditorsGeorge Tsihrintzis, Maria Virvou, Toyohide Watanabe, Lakhmi Jain, Robert Howlett
Pages174-183
Number of pages10
DOIs
Publication statusPublished - Dec 1 2013

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume254
ISSN (Print)0922-6389

Fingerprint

Learning systems
Websites
Education
Personnel

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Flanagan, B., Yin, C., Suzuki, T., & Hirokawa, S. (2013). Intelligent computer classification of english writing errors. In G. Tsihrintzis, M. Virvou, T. Watanabe, L. Jain, & R. Howlett (Eds.), Intelligent Interactive Multimedia Systems and Services. Proceedings of the 6th International Conference on Intelligent Interactive Multimedia Systems and Services (IIMSS2013) (pp. 174-183). (Frontiers in Artificial Intelligence and Applications; Vol. 254). https://doi.org/10.3233/978-1-61499-262-2-174

Intelligent computer classification of english writing errors. / Flanagan, Brendan; Yin, Chengjiu; Suzuki, Takahiko; Hirokawa, Sachio.

Intelligent Interactive Multimedia Systems and Services. Proceedings of the 6th International Conference on Intelligent Interactive Multimedia Systems and Services (IIMSS2013). ed. / George Tsihrintzis; Maria Virvou; Toyohide Watanabe; Lakhmi Jain; Robert Howlett. 2013. p. 174-183 (Frontiers in Artificial Intelligence and Applications; Vol. 254).

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

Flanagan, B, Yin, C, Suzuki, T & Hirokawa, S 2013, Intelligent computer classification of english writing errors. in G Tsihrintzis, M Virvou, T Watanabe, L Jain & R Howlett (eds), Intelligent Interactive Multimedia Systems and Services. Proceedings of the 6th International Conference on Intelligent Interactive Multimedia Systems and Services (IIMSS2013). Frontiers in Artificial Intelligence and Applications, vol. 254, pp. 174-183. https://doi.org/10.3233/978-1-61499-262-2-174
Flanagan B, Yin C, Suzuki T, Hirokawa S. Intelligent computer classification of english writing errors. In Tsihrintzis G, Virvou M, Watanabe T, Jain L, Howlett R, editors, Intelligent Interactive Multimedia Systems and Services. Proceedings of the 6th International Conference on Intelligent Interactive Multimedia Systems and Services (IIMSS2013). 2013. p. 174-183. (Frontiers in Artificial Intelligence and Applications). https://doi.org/10.3233/978-1-61499-262-2-174
Flanagan, Brendan ; Yin, Chengjiu ; Suzuki, Takahiko ; Hirokawa, Sachio. / Intelligent computer classification of english writing errors. Intelligent Interactive Multimedia Systems and Services. Proceedings of the 6th International Conference on Intelligent Interactive Multimedia Systems and Services (IIMSS2013). editor / George Tsihrintzis ; Maria Virvou ; Toyohide Watanabe ; Lakhmi Jain ; Robert Howlett. 2013. pp. 174-183 (Frontiers in Artificial Intelligence and Applications).
@inproceedings{d11ec2544c2b4c59ad5a33aaf1304b46,
title = "Intelligent computer classification of english writing errors",
abstract = "An important issue in education systems is the ability to determine the characteristics of learners and then provide intelligent and informed guidance in response. The authors of this paper have a long-term research goal to provide language learners with the ability to determine and improving their weaknesses. However, to achieve this goal a sizable amount of manually classified data is required. The task is both time consuming and labor intensive. In this paper a system was built to help intelligently classify the errors in an English learner's writings into categories (Kroll 1990, Weltig 2004). Using a randomly selected manually classified sample as training data, it was determined that there is a positive correlation between the number of samples for each error category and the effectiveness of the model created by applying SVM machine learning to the writings of language learners on the Lang-8 website. It is intended that the classification results will be used to accelerate the manually process classification and increase the amount of training data available for use.",
author = "Brendan Flanagan and Chengjiu Yin and Takahiko Suzuki and Sachio Hirokawa",
year = "2013",
month = "12",
day = "1",
doi = "10.3233/978-1-61499-262-2-174",
language = "English",
isbn = "9781614992615",
series = "Frontiers in Artificial Intelligence and Applications",
pages = "174--183",
editor = "George Tsihrintzis and Maria Virvou and Toyohide Watanabe and Lakhmi Jain and Robert Howlett",
booktitle = "Intelligent Interactive Multimedia Systems and Services. Proceedings of the 6th International Conference on Intelligent Interactive Multimedia Systems and Services (IIMSS2013)",

}

TY - GEN

T1 - Intelligent computer classification of english writing errors

AU - Flanagan, Brendan

AU - Yin, Chengjiu

AU - Suzuki, Takahiko

AU - Hirokawa, Sachio

PY - 2013/12/1

Y1 - 2013/12/1

N2 - An important issue in education systems is the ability to determine the characteristics of learners and then provide intelligent and informed guidance in response. The authors of this paper have a long-term research goal to provide language learners with the ability to determine and improving their weaknesses. However, to achieve this goal a sizable amount of manually classified data is required. The task is both time consuming and labor intensive. In this paper a system was built to help intelligently classify the errors in an English learner's writings into categories (Kroll 1990, Weltig 2004). Using a randomly selected manually classified sample as training data, it was determined that there is a positive correlation between the number of samples for each error category and the effectiveness of the model created by applying SVM machine learning to the writings of language learners on the Lang-8 website. It is intended that the classification results will be used to accelerate the manually process classification and increase the amount of training data available for use.

AB - An important issue in education systems is the ability to determine the characteristics of learners and then provide intelligent and informed guidance in response. The authors of this paper have a long-term research goal to provide language learners with the ability to determine and improving their weaknesses. However, to achieve this goal a sizable amount of manually classified data is required. The task is both time consuming and labor intensive. In this paper a system was built to help intelligently classify the errors in an English learner's writings into categories (Kroll 1990, Weltig 2004). Using a randomly selected manually classified sample as training data, it was determined that there is a positive correlation between the number of samples for each error category and the effectiveness of the model created by applying SVM machine learning to the writings of language learners on the Lang-8 website. It is intended that the classification results will be used to accelerate the manually process classification and increase the amount of training data available for use.

UR - http://www.scopus.com/inward/record.url?scp=84896838700&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896838700&partnerID=8YFLogxK

U2 - 10.3233/978-1-61499-262-2-174

DO - 10.3233/978-1-61499-262-2-174

M3 - Conference contribution

AN - SCOPUS:84896838700

SN - 9781614992615

T3 - Frontiers in Artificial Intelligence and Applications

SP - 174

EP - 183

BT - Intelligent Interactive Multimedia Systems and Services. Proceedings of the 6th International Conference on Intelligent Interactive Multimedia Systems and Services (IIMSS2013)

A2 - Tsihrintzis, George

A2 - Virvou, Maria

A2 - Watanabe, Toyohide

A2 - Jain, Lakhmi

A2 - Howlett, Robert

ER -