Discriminating between second language learning text-types

Scott A. Crossley; Philip M. McCarthy; Danielle S. McNamara

Discriminating between second language learning text-types

Scott A. Crossley, Philip M. McCarthy, Danielle S. McNamara

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Text classification remains one of the major fields of research in natural language processing. This paper evaluates the use of the computational tool Coh-Metrix as a means to distinguish between seemingly similar text-types. Using a discriminant analysis on a corpus of second language reading texts, this paper demonstrates that Coh-Metrix is able to significantly distinguish authentic text-types from ones that have been specifically simplified for second language readers. This paper offers important findings for text classification research and for second language reading materials developers and second language teachers by demonstrating that moderate, shallow, textual changes can affect discourse structures.

Original language	English (US)
Title of host publication	Proceedings of the Twentieth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2007
Pages	205-210
Number of pages	6
State	Published - Dec 28 2007
Externally published	Yes
Event	20th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2007 - Key West, FL, United States Duration: May 7 2007 → May 9 2007

Publication series

Name	Proceedings of the Twentieth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2007

Other

Other	20th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2007
Country/Territory	United States
City	Key West, FL
Period	5/7/07 → 5/9/07

ASJC Scopus subject areas

Artificial Intelligence
Software

Cite this

Crossley, S. A., McCarthy, P. M., & McNamara, D. S. (2007). Discriminating between second language learning text-types. In Proceedings of the Twentieth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2007 (pp. 205-210). (Proceedings of the Twentieth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2007).

Discriminating between second language learning text-types. / Crossley, Scott A.; McCarthy, Philip M.; McNamara, Danielle S.
Proceedings of the Twentieth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2007. 2007. p. 205-210 (Proceedings of the Twentieth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2007).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Crossley, SA, McCarthy, PM & McNamara, DS 2007, Discriminating between second language learning text-types. in Proceedings of the Twentieth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2007. Proceedings of the Twentieth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2007, pp. 205-210, 20th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2007, Key West, FL, United States, 5/7/07.

Crossley, Scott A. ; McCarthy, Philip M. ; McNamara, Danielle S. / Discriminating between second language learning text-types. Proceedings of the Twentieth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2007. 2007. pp. 205-210 (Proceedings of the Twentieth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2007).

@inproceedings{ad23000fa58745caaebe841eb79b6f46,

title = "Discriminating between second language learning text-types",

abstract = "Text classification remains one of the major fields of research in natural language processing. This paper evaluates the use of the computational tool Coh-Metrix as a means to distinguish between seemingly similar text-types. Using a discriminant analysis on a corpus of second language reading texts, this paper demonstrates that Coh-Metrix is able to significantly distinguish authentic text-types from ones that have been specifically simplified for second language readers. This paper offers important findings for text classification research and for second language reading materials developers and second language teachers by demonstrating that moderate, shallow, textual changes can affect discourse structures.",

author = "Crossley, {Scott A.} and McCarthy, {Philip M.} and McNamara, {Danielle S.}",

year = "2007",

month = dec,

day = "28",

language = "English (US)",

isbn = "1577353196",

series = "Proceedings of the Twentieth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2007",

pages = "205--210",

booktitle = "Proceedings of the Twentieth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2007",

note = "20th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2007 ; Conference date: 07-05-2007 Through 09-05-2007",

}

TY - GEN

T1 - Discriminating between second language learning text-types

AU - Crossley, Scott A.

AU - McCarthy, Philip M.

AU - McNamara, Danielle S.

PY - 2007/12/28

Y1 - 2007/12/28

N2 - Text classification remains one of the major fields of research in natural language processing. This paper evaluates the use of the computational tool Coh-Metrix as a means to distinguish between seemingly similar text-types. Using a discriminant analysis on a corpus of second language reading texts, this paper demonstrates that Coh-Metrix is able to significantly distinguish authentic text-types from ones that have been specifically simplified for second language readers. This paper offers important findings for text classification research and for second language reading materials developers and second language teachers by demonstrating that moderate, shallow, textual changes can affect discourse structures.

AB - Text classification remains one of the major fields of research in natural language processing. This paper evaluates the use of the computational tool Coh-Metrix as a means to distinguish between seemingly similar text-types. Using a discriminant analysis on a corpus of second language reading texts, this paper demonstrates that Coh-Metrix is able to significantly distinguish authentic text-types from ones that have been specifically simplified for second language readers. This paper offers important findings for text classification research and for second language reading materials developers and second language teachers by demonstrating that moderate, shallow, textual changes can affect discourse structures.

UR - http://www.scopus.com/inward/record.url?scp=37349104229&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=37349104229&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:37349104229

SN - 1577353196

SN - 9781577353195

T3 - Proceedings of the Twentieth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2007

SP - 205

EP - 210

BT - Proceedings of the Twentieth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2007

T2 - 20th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2007

Y2 - 7 May 2007 through 9 May 2007

ER -

Discriminating between second language learning text-types

Abstract

Publication series

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this