Tutorbot corpus: evidence of Human-Agent verbal alignment in Second Language learner dialogues

Arabella Sinclair; Kate McCurdy; Christopher G. Lucas; Adam Lopez; Dragan Gašević

Tutorbot corpus: evidence of Human-Agent verbal alignment in Second Language learner dialogues

Arabella Sinclair, Kate McCurdy, Christopher G. Lucas, Adam Lopez, Dragan Gašević

Department of Data Science & AI

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

6 Citations (Scopus)

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.

Original language	English
Title of host publication	Proceedings of the 12th International Conference on Educational Data Mining
Editors	Collin F. Lynch, Agathe Merceron, Michel Desmarais, Roger Nkambou
Place of Publication	Montreal Canada
Publisher	Presses De I Universite Du Quebec
Pages	414-419
Number of pages	6
ISBN (Electronic)	9781733673600
Publication status	Published - 2019
Event	Educational Data Mining 2019 - Montreal , Canada Duration: 2 Jul 2019 → 5 Jul 2019 Conference number: 12th 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/

Keywords

Agent
Alignment
Assessment
Chatbot
Dialogue
Language learning
Second language
Student engagement
Tutoring

Access to Document

312060250-oaFinal published version, 329 KB

https://educationaldatamining.org/edm2019/proceedings/

Cite this

Sinclair, A., McCurdy, K., Lucas, C. G., Lopez, A., & Gašević, 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 (pp. 414-419). Article 106 Presses De I Universite Du Quebec. https://educationaldatamining.org/edm2019/proceedings/

Sinclair, Arabella ; McCurdy, Kate ; Lucas, Christopher G. 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. editor / Collin F. Lynch ; Agathe Merceron ; Michel Desmarais ; Roger Nkambou. Montreal Canada : Presses De I Universite Du Quebec, 2019. pp. 414-419

@inproceedings{6efe01d7eca445c8a5676bc93440e2ec,

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.",

keywords = "Agent, Alignment, Assessment, Chatbot, Dialogue, Language learning, Second language, Student engagement, Tutoring",

author = "Arabella Sinclair and Kate McCurdy and Lucas, {Christopher G.} and Adam Lopez and Dragan Ga{\v s}evi{\'c}",

year = "2019",

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",

publisher = "Presses De I Universite Du Quebec",

address = "Canada",

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, CG, Lopez, A & Gašević, 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., 106, Presses De I Universite Du Quebec, Montreal Canada, pp. 414-419, Educational Data Mining 2019, Montreal , Quebec, Canada, 2/07/19. <https://educationaldatamining.org/edm2019/proceedings/>

Tutorbot corpus: evidence of Human-Agent verbal alignment in Second Language learner dialogues. / Sinclair, Arabella; McCurdy, Kate; Lucas, Christopher G. et al.
Proceedings of the 12th International Conference on Educational Data Mining. ed. / Collin F. Lynch; Agathe Merceron; Michel Desmarais; Roger Nkambou. Montreal Canada: Presses De I Universite Du Quebec, 2019. p. 414-419 106.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Tutorbot corpus

T2 - Educational Data Mining 2019

AU - Sinclair, Arabella

AU - McCurdy, Kate

AU - Lucas, Christopher G.

AU - Lopez, Adam

AU - Gašević, Dragan

N1 - Conference code: 12th

PY - 2019

Y1 - 2019

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.

KW - Agent

KW - Alignment

KW - Assessment

KW - Chatbot

KW - Dialogue

KW - Language learning

KW - Second language

KW - Student engagement

KW - Tutoring

UR - http://www.scopus.com/inward/record.url?scp=85085989898&partnerID=8YFLogxK

M3 - Conference Paper

AN - SCOPUS:85085989898

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

PB - Presses De I Universite Du Quebec

CY - Montreal Canada

Y2 - 2 July 2019 through 5 July 2019

ER -

Tutorbot corpus: evidence of Human-Agent verbal alignment in Second Language learner dialogues

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this