Using natural language processing to analyze tutorial dialogue corpora across domains modalities

Diane Litman; Johanna D. Moore; Myroslava O. Dzikovska; Elaine Farrow

doi:10.3233/978-1-60750-028-5-149

Using natural language processing to analyze tutorial dialogue corpora across domains modalities

Diane Litman, Johanna D. Moore, Myroslava O. Dzikovska, Elaine Farrow

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

27 Citations (Scopus)

Abstract

Our research goal is to investigate whether previous findings and methods in the area of tutorial dialogue can be generalized across dialogue corpora that differ in domain (mechanics versus electricity in physics), modality (spoken versus typed), and tutor type (computer versus human). We first present methods for unifying our prior coding and analysis methods. We then show that many of our prior findings regarding student dialogue behaviors and learning not only generalize across corpora, but that our methodology yields additional new findings. Finally, we show that natural language processing can be used to automate some of these analyses.

Original language	English
Title of host publication	Proceeding of the 2009 Conference on Artificial Intelligence in Education
Subtitle of host publication	Building Learning Systems that Care: From Knowledge Representation to Affective Modelling
Editors	Vania Dimitrova, Riichiro Mizoguchi, Benedict du Boulay, Art Graesser
Place of Publication	Amsterdam, The Netherlands, The Netherlands
Publisher	IOS Press
Pages	149-156
Number of pages	8
ISBN (Electronic)	978-1-60750-028-5
DOIs	https://doi.org/10.3233/978-1-60750-028-5-149
Publication status	Published - Jul 2009
Event	14th International Conference on Artificial Intelligence in Education - Brighton, United Kingdom Duration: 6 Jul 2009 → 10 Jul 2009

Conference

Conference	14th International Conference on Artificial Intelligence in Education
Country/Territory	United Kingdom
City	Brighton
Period	6/07/09 → 10/07/09

Access to Document

10.3233/978-1-60750-028-5-149

http://www.cs.pitt.edu/~litman/paper_125.pdf

Cite this

Litman, D., Moore, J. D., Dzikovska, M. O., & Farrow, E. (2009). Using natural language processing to analyze tutorial dialogue corpora across domains modalities. In V. Dimitrova, R. Mizoguchi, B. du Boulay, & A. Graesser (Eds.), Proceeding of the 2009 Conference on Artificial Intelligence in Education: Building Learning Systems that Care: From Knowledge Representation to Affective Modelling (pp. 149-156). IOS Press. https://doi.org/10.3233/978-1-60750-028-5-149

Litman, Diane ; Moore, Johanna D. ; Dzikovska, Myroslava O. et al. / Using natural language processing to analyze tutorial dialogue corpora across domains modalities. Proceeding of the 2009 Conference on Artificial Intelligence in Education: Building Learning Systems that Care: From Knowledge Representation to Affective Modelling. editor / Vania Dimitrova ; Riichiro Mizoguchi ; Benedict du Boulay ; Art Graesser. Amsterdam, The Netherlands, The Netherlands : IOS Press, 2009. pp. 149-156

@inproceedings{a0f7d499c60c431ba2f480ee21c375f4,

title = "Using natural language processing to analyze tutorial dialogue corpora across domains modalities",

abstract = "Our research goal is to investigate whether previous findings and methods in the area of tutorial dialogue can be generalized across dialogue corpora that differ in domain (mechanics versus electricity in physics), modality (spoken versus typed), and tutor type (computer versus human). We first present methods for unifying our prior coding and analysis methods. We then show that many of our prior findings regarding student dialogue behaviors and learning not only generalize across corpora, but that our methodology yields additional new findings. Finally, we show that natural language processing can be used to automate some of these analyses.",

author = "Diane Litman and Moore, {Johanna D.} and Dzikovska, {Myroslava O.} and Elaine Farrow",

year = "2009",

month = jul,

doi = "10.3233/978-1-60750-028-5-149",

language = "English",

pages = "149--156",

editor = "Vania Dimitrova and Riichiro Mizoguchi and {du Boulay}, Benedict and Art Graesser",

booktitle = "Proceeding of the 2009 Conference on Artificial Intelligence in Education",

publisher = "IOS Press",

address = "Netherlands",

note = "14th International Conference on Artificial Intelligence in Education ; Conference date: 06-07-2009 Through 10-07-2009",

}

Litman, D, Moore, JD, Dzikovska, MO & Farrow, E 2009, Using natural language processing to analyze tutorial dialogue corpora across domains modalities. in V Dimitrova, R Mizoguchi, B du Boulay & A Graesser (eds), Proceeding of the 2009 Conference on Artificial Intelligence in Education: Building Learning Systems that Care: From Knowledge Representation to Affective Modelling. IOS Press, Amsterdam, The Netherlands, The Netherlands, pp. 149-156, 14th International Conference on Artificial Intelligence in Education, Brighton, United Kingdom, 6/07/09. https://doi.org/10.3233/978-1-60750-028-5-149

Using natural language processing to analyze tutorial dialogue corpora across domains modalities. / Litman, Diane; Moore, Johanna D.; Dzikovska, Myroslava O. et al.
Proceeding of the 2009 Conference on Artificial Intelligence in Education: Building Learning Systems that Care: From Knowledge Representation to Affective Modelling. ed. / Vania Dimitrova; Riichiro Mizoguchi; Benedict du Boulay; Art Graesser. Amsterdam, The Netherlands, The Netherlands: IOS Press, 2009. p. 149-156.

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

TY - GEN

T1 - Using natural language processing to analyze tutorial dialogue corpora across domains modalities

AU - Litman, Diane

AU - Moore, Johanna D.

AU - Dzikovska, Myroslava O.

AU - Farrow, Elaine

PY - 2009/7

Y1 - 2009/7

N2 - Our research goal is to investigate whether previous findings and methods in the area of tutorial dialogue can be generalized across dialogue corpora that differ in domain (mechanics versus electricity in physics), modality (spoken versus typed), and tutor type (computer versus human). We first present methods for unifying our prior coding and analysis methods. We then show that many of our prior findings regarding student dialogue behaviors and learning not only generalize across corpora, but that our methodology yields additional new findings. Finally, we show that natural language processing can be used to automate some of these analyses.

AB - Our research goal is to investigate whether previous findings and methods in the area of tutorial dialogue can be generalized across dialogue corpora that differ in domain (mechanics versus electricity in physics), modality (spoken versus typed), and tutor type (computer versus human). We first present methods for unifying our prior coding and analysis methods. We then show that many of our prior findings regarding student dialogue behaviors and learning not only generalize across corpora, but that our methodology yields additional new findings. Finally, we show that natural language processing can be used to automate some of these analyses.

U2 - 10.3233/978-1-60750-028-5-149

DO - 10.3233/978-1-60750-028-5-149

M3 - Conference contribution

SP - 149

EP - 156

BT - Proceeding of the 2009 Conference on Artificial Intelligence in Education

A2 - Dimitrova, Vania

A2 - Mizoguchi, Riichiro

A2 - du Boulay, Benedict

A2 - Graesser, Art

PB - IOS Press

CY - Amsterdam, The Netherlands, The Netherlands

T2 - 14th International Conference on Artificial Intelligence in Education

Y2 - 6 July 2009 through 10 July 2009

ER -

Litman D, Moore JD, Dzikovska MO, Farrow E. Using natural language processing to analyze tutorial dialogue corpora across domains modalities. In Dimitrova V, Mizoguchi R, du Boulay B, Graesser A, editors, Proceeding of the 2009 Conference on Artificial Intelligence in Education: Building Learning Systems that Care: From Knowledge Representation to Affective Modelling. Amsterdam, The Netherlands, The Netherlands: IOS Press. 2009. p. 149-156 doi: 10.3233/978-1-60750-028-5-149

Using natural language processing to analyze tutorial dialogue corpora across domains modalities

Abstract

Conference

Access to Document

Fingerprint

Cite this