Problem solving, domain expertise and learning: ground-truth performance results for math data corpus

Sharon Oviatt

doi:10.1145/2522848.2533791

Problem solving, domain expertise and learning: ground-truth performance results for math data corpus

Sharon Oviatt

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

19 Citations (Scopus)

Abstract

Problem solving, domain expertise, and learning are analyzed for the Math Data Corpus, which involves multimodal data on collaborating student groups as they solve math problems together across sessions. Compared with non-expert students, domain experts contributed more group solutions, solved more problems correctly and took less time. These differences between experts and non-experts were accentuated on harder problems. A cumulative expertise metric validated that expert and non-expert students represented distinct non overlapping populations, a finding that replicated across sessions. Group performance also improved 9.4% across sessions, due mainly to learning by expert students. These findings satisfy ground-truth conditions for developing prediction techniques that aim to identify expertise based on multimodal communication and behavior patterns. Together with the Math Data Corpus, these results contribute valuable resources for supporting data-driven grand challenges on multimodal learning analytics, which aim to develop new techniques for predicting expertise early, reliably, and objectively. as well as learning-oriented precursors.

Original language	English
Title of host publication	ICMI'13 - Proceedings of the 15th ACM on International conference on multimodal interaction
Place of Publication	New York NY USA
Publisher	Association for Computing Machinery (ACM)
Pages	569-574
Number of pages	6
ISBN (Print)	9781450321297
DOIs	https://doi.org/10.1145/2522848.2533791
Publication status	Published - 2013
Externally published	Yes
Event	International Conference on Multimodal Interfaces 2013 - Coogee Bay Hotel, Sydney, Australia Duration: 9 Dec 2013 → 13 Dec 2013 Conference number: 15th https://icmi.acm.org/2013/ (Conference website) https://dl.acm.org/citation.cfm?id=2522848&picked=prox (ACM proceedings)

Conference

Conference	International Conference on Multimodal Interfaces 2013
Abbreviated title	ICMI 2013
Country/Territory	Australia
City	Sydney
Period	9/12/13 → 13/12/13
Internet address	https://icmi.acm.org/2013/ (Conference website) https://dl.acm.org/citation.cfm?id=2522848&picked=prox (ACM proceedings)

Keywords

collaborative problem solving
data resources & ground-truth coding
digital pen
domain expertise
images
math data corpus
multimodal learning analytics
speech

Access to Document

10.1145/2522848.2533791

Cite this

@inproceedings{7cc9ef5be546465580e87d8400c0c0b9,

title = "Problem solving, domain expertise and learning: ground-truth performance results for math data corpus",

abstract = "Problem solving, domain expertise, and learning are analyzed for the Math Data Corpus, which involves multimodal data on collaborating student groups as they solve math problems together across sessions. Compared with non-expert students, domain experts contributed more group solutions, solved more problems correctly and took less time. These differences between experts and non-experts were accentuated on harder problems. A cumulative expertise metric validated that expert and non-expert students represented distinct non overlapping populations, a finding that replicated across sessions. Group performance also improved 9.4% across sessions, due mainly to learning by expert students. These findings satisfy ground-truth conditions for developing prediction techniques that aim to identify expertise based on multimodal communication and behavior patterns. Together with the Math Data Corpus, these results contribute valuable resources for supporting data-driven grand challenges on multimodal learning analytics, which aim to develop new techniques for predicting expertise early, reliably, and objectively. as well as learning-oriented precursors.",

keywords = "collaborative problem solving, data resources & ground-truth coding, digital pen, domain expertise, images, math data corpus, multimodal learning analytics, speech",

author = "Sharon Oviatt",

year = "2013",

doi = "10.1145/2522848.2533791",

language = "English",

isbn = "9781450321297",

pages = "569--574",

booktitle = "ICMI'13 - Proceedings of the 15th ACM on International conference on multimodal interaction",

publisher = "Association for Computing Machinery (ACM)",

address = "United States of America",

note = "International Conference on Multimodal Interfaces 2013, ICMI 2013 ; Conference date: 09-12-2013 Through 13-12-2013",

url = "https://icmi.acm.org/2013/, https://dl.acm.org/citation.cfm?id=2522848&picked=prox",

}

Oviatt, S 2013, Problem solving, domain expertise and learning: ground-truth performance results for math data corpus. in ICMI'13 - Proceedings of the 15th ACM on International conference on multimodal interaction. Association for Computing Machinery (ACM), New York NY USA, pp. 569-574, International Conference on Multimodal Interfaces 2013, Sydney, New South Wales, Australia, 9/12/13. https://doi.org/10.1145/2522848.2533791

Problem solving, domain expertise and learning: ground-truth performance results for math data corpus. / Oviatt, Sharon.
ICMI'13 - Proceedings of the 15th ACM on International conference on multimodal interaction. New York NY USA: Association for Computing Machinery (ACM), 2013. p. 569-574.

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

TY - GEN

T1 - Problem solving, domain expertise and learning

T2 - International Conference on Multimodal Interfaces 2013

AU - Oviatt, Sharon

N1 - Conference code: 15th

PY - 2013

Y1 - 2013

N2 - Problem solving, domain expertise, and learning are analyzed for the Math Data Corpus, which involves multimodal data on collaborating student groups as they solve math problems together across sessions. Compared with non-expert students, domain experts contributed more group solutions, solved more problems correctly and took less time. These differences between experts and non-experts were accentuated on harder problems. A cumulative expertise metric validated that expert and non-expert students represented distinct non overlapping populations, a finding that replicated across sessions. Group performance also improved 9.4% across sessions, due mainly to learning by expert students. These findings satisfy ground-truth conditions for developing prediction techniques that aim to identify expertise based on multimodal communication and behavior patterns. Together with the Math Data Corpus, these results contribute valuable resources for supporting data-driven grand challenges on multimodal learning analytics, which aim to develop new techniques for predicting expertise early, reliably, and objectively. as well as learning-oriented precursors.

AB - Problem solving, domain expertise, and learning are analyzed for the Math Data Corpus, which involves multimodal data on collaborating student groups as they solve math problems together across sessions. Compared with non-expert students, domain experts contributed more group solutions, solved more problems correctly and took less time. These differences between experts and non-experts were accentuated on harder problems. A cumulative expertise metric validated that expert and non-expert students represented distinct non overlapping populations, a finding that replicated across sessions. Group performance also improved 9.4% across sessions, due mainly to learning by expert students. These findings satisfy ground-truth conditions for developing prediction techniques that aim to identify expertise based on multimodal communication and behavior patterns. Together with the Math Data Corpus, these results contribute valuable resources for supporting data-driven grand challenges on multimodal learning analytics, which aim to develop new techniques for predicting expertise early, reliably, and objectively. as well as learning-oriented precursors.

KW - collaborative problem solving

KW - data resources & ground-truth coding

KW - digital pen

KW - domain expertise

KW - images

KW - math data corpus

KW - multimodal learning analytics

KW - speech

UR - http://www.scopus.com/inward/record.url?scp=84892593282&partnerID=8YFLogxK

U2 - 10.1145/2522848.2533791

DO - 10.1145/2522848.2533791

M3 - Conference Paper

AN - SCOPUS:84892593282

SN - 9781450321297

SP - 569

EP - 574

BT - ICMI'13 - Proceedings of the 15th ACM on International conference on multimodal interaction

PB - Association for Computing Machinery (ACM)

CY - New York NY USA

Y2 - 9 December 2013 through 13 December 2013

ER -

Problem solving, domain expertise and learning: ground-truth performance results for math data corpus

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this