Tutorbot Corpus: Evidence of Human-Agent Verbal Alignment in Second Language Learner Dialogues

Arabella Sinclair; Katherine McCurdy; Christopher Lucas; Adam Lopez; Dragan Gasevic

Tutorbot Corpus: Evidence of Human-Agent Verbal Alignment in Second Language Learner Dialogues

Arabella Sinclair, Katherine McCurdy, Christopher Lucas, Adam Lopez, Dragan Gasevic

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

Abstract / Description of output

Prior research has shown that, under certain conditions, Human-Agent (H-A) alignment exists to a stronger degree than that found in Human-Human (H-H) communication. In an H-H Second Language (L2) setting, evidence of alignment has been linked to learning and teaching strategy. We present a novel analysis of H-A and H-H L2 learner dialogues using automated metrics of alignment. Our contributions are twofold: firstly we replicated the reported H-A alignment within an educational context, finding L2 students align to an automated tutor. Secondly, we performed an exploratory comparison of the alignment present in comparable H-A and H-H L2 learner corpora using Bayesian Gaussian Mixture Models (GMMs), finding preliminary evidence that students in H-A L2 dialogues showed greater variability in engagement.

Original language	English
Title of host publication	Proceedings of the 12th International Conference on Educational Data Mining
Subtitle of host publication	July 2nd − 5th 2019 Montreal Canada
Editors	Collin F Lynch, Agathe Merceron, Michel Desmarais, Roger Nkambou
Pages	414-419
Number of pages	6
ISBN (Electronic)	978-1-7336736-0-0
Publication status	Published - 5 Jul 2019
Event	Educational Data Mining 2019 - Montreal, Canada Duration: 2 Jul 2019 → 5 Jul 2019 http://educationaldatamining.org/edm2019/

Conference

Conference	Educational Data Mining 2019
Abbreviated title	EDM 2019
Country/Territory	Canada
City	Montreal
Period	2/07/19 → 5/07/19
Internet address	http://educationaldatamining.org/edm2019/

Access to Document

https://drive.google.com/file/d/1W45FZh2ywIzcxaxs_RjYV6v7tdlV67gw/viewLicence: All Rights Reserved
https://drive.google.com/file/d/1vptlF7O5MpVfPTMEHcQPacN0zhJk6u54/viewLicence: All Rights Reserved

Cite this

Sinclair, A., McCurdy, K., Lucas, C., Lopez, A., & Gasevic, D. (2019). Tutorbot Corpus: Evidence of Human-Agent Verbal Alignment in Second Language Learner Dialogues. In C. F. Lynch, A. Merceron, M. Desmarais, & R. Nkambou (Eds.), Proceedings of the 12th International Conference on Educational Data Mining: July 2nd − 5th 2019 Montreal Canada (pp. 414-419) https://drive.google.com/file/d/1W45FZh2ywIzcxaxs_RjYV6v7tdlV67gw/view

Sinclair, Arabella ; McCurdy, Katherine ; Lucas, Christopher et al. / Tutorbot Corpus: Evidence of Human-Agent Verbal Alignment in Second Language Learner Dialogues. Proceedings of the 12th International Conference on Educational Data Mining: July 2nd − 5th 2019 Montreal Canada. editor / Collin F Lynch ; Agathe Merceron ; Michel Desmarais ; Roger Nkambou. 2019. pp. 414-419

@inproceedings{37e736efb39d46b5a54fc9086fc32980,

title = "Tutorbot Corpus: Evidence of Human-Agent Verbal Alignment in Second Language Learner Dialogues",

abstract = "Prior research has shown that, under certain conditions, Human-Agent (H-A) alignment exists to a stronger degree than that found in Human-Human (H-H) communication. In an H-H Second Language (L2) setting, evidence of alignment has been linked to learning and teaching strategy. We present a novel analysis of H-A and H-H L2 learner dialogues using automated metrics of alignment. Our contributions are twofold: firstly we replicated the reported H-A alignment within an educational context, finding L2 students align to an automated tutor. Secondly, we performed an exploratory comparison of the alignment present in comparable H-A and H-H L2 learner corpora using Bayesian Gaussian Mixture Models (GMMs), finding preliminary evidence that students in H-A L2 dialogues showed greater variability in engagement.",

author = "Arabella Sinclair and Katherine McCurdy and Christopher Lucas and Adam Lopez and Dragan Gasevic",

year = "2019",

month = jul,

day = "5",

language = "English",

pages = "414--419",

editor = "Lynch, {Collin F} and Agathe Merceron and Michel Desmarais and Roger Nkambou",

booktitle = "Proceedings of the 12th International Conference on Educational Data Mining",

note = "Educational Data Mining 2019, EDM 2019 ; Conference date: 02-07-2019 Through 05-07-2019",

url = "http://educationaldatamining.org/edm2019/",

}

Sinclair, A, McCurdy, K, Lucas, C , Lopez, A & Gasevic, D 2019, Tutorbot Corpus: Evidence of Human-Agent Verbal Alignment in Second Language Learner Dialogues. in CF Lynch, A Merceron, M Desmarais & R Nkambou (eds), Proceedings of the 12th International Conference on Educational Data Mining: July 2nd − 5th 2019 Montreal Canada. pp. 414-419, Educational Data Mining 2019, Montreal, Quebec, Canada, 2/07/19. <https://drive.google.com/file/d/1W45FZh2ywIzcxaxs_RjYV6v7tdlV67gw/view>

Tutorbot Corpus: Evidence of Human-Agent Verbal Alignment in Second Language Learner Dialogues. / Sinclair, Arabella; McCurdy, Katherine; Lucas, Christopher et al.
Proceedings of the 12th International Conference on Educational Data Mining: July 2nd − 5th 2019 Montreal Canada. ed. / Collin F Lynch; Agathe Merceron; Michel Desmarais; Roger Nkambou. 2019. p. 414-419.

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

TY - GEN

T1 - Tutorbot Corpus: Evidence of Human-Agent Verbal Alignment in Second Language Learner Dialogues

AU - Sinclair, Arabella

AU - McCurdy, Katherine

AU - Lucas, Christopher

AU - Lopez, Adam

AU - Gasevic, Dragan

PY - 2019/7/5

Y1 - 2019/7/5

N2 - Prior research has shown that, under certain conditions, Human-Agent (H-A) alignment exists to a stronger degree than that found in Human-Human (H-H) communication. In an H-H Second Language (L2) setting, evidence of alignment has been linked to learning and teaching strategy. We present a novel analysis of H-A and H-H L2 learner dialogues using automated metrics of alignment. Our contributions are twofold: firstly we replicated the reported H-A alignment within an educational context, finding L2 students align to an automated tutor. Secondly, we performed an exploratory comparison of the alignment present in comparable H-A and H-H L2 learner corpora using Bayesian Gaussian Mixture Models (GMMs), finding preliminary evidence that students in H-A L2 dialogues showed greater variability in engagement.

AB - Prior research has shown that, under certain conditions, Human-Agent (H-A) alignment exists to a stronger degree than that found in Human-Human (H-H) communication. In an H-H Second Language (L2) setting, evidence of alignment has been linked to learning and teaching strategy. We present a novel analysis of H-A and H-H L2 learner dialogues using automated metrics of alignment. Our contributions are twofold: firstly we replicated the reported H-A alignment within an educational context, finding L2 students align to an automated tutor. Secondly, we performed an exploratory comparison of the alignment present in comparable H-A and H-H L2 learner corpora using Bayesian Gaussian Mixture Models (GMMs), finding preliminary evidence that students in H-A L2 dialogues showed greater variability in engagement.

UR - http://educationaldatamining.org/edm2019/proceedings/

M3 - Conference contribution

SP - 414

EP - 419

BT - Proceedings of the 12th International Conference on Educational Data Mining

A2 - Lynch, Collin F

A2 - Merceron, Agathe

A2 - Desmarais, Michel

A2 - Nkambou, Roger

T2 - Educational Data Mining 2019

Y2 - 2 July 2019 through 5 July 2019

ER -

Tutorbot Corpus: Evidence of Human-Agent Verbal Alignment in Second Language Learner Dialogues

Abstract / Description of output

Conference

Access to Document

Other files and links

Fingerprint

Cite this