Humans and machines together

Improving characterization of large scale online discussions through dynamic interrelated post and thread categorization (DIPTiC)

Yi Cui, Wan Qi Jin, Alyssa Wise

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents a thread characterization method that compares categorization results for thread starters and replies made by a previously-developed natural language model, using human judgment to resolve discrepancies. In an example application using the complete discussion forum data from a MOOC on medical statistics, the method increased the estimation of classification accuracy from .81 to .88 with the addition of a minimal number of human hours.

Original languageEnglish (US)
Title of host publicationL@S 2017 - Proceedings of the 4th (2017) ACM Conference on Learning at Scale
PublisherAssociation for Computing Machinery, Inc
Pages217-219
Number of pages3
ISBN (Electronic)9781450344500
DOIs
StatePublished - Apr 12 2017
Event4th Annual ACM Conference on Learning at Scale, L@S 2017 - Cambridge, United States
Duration: Apr 20 2017Apr 21 2017

Other

Other4th Annual ACM Conference on Learning at Scale, L@S 2017
CountryUnited States
CityCambridge
Period4/20/174/21/17

Fingerprint

Starters
Statistics
statistics
language

Keywords

  • Discussion forum
  • Massive open online courses
  • Thread categorization

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Education
  • Software
  • Computer Science Applications

Cite this

Cui, Y., Jin, W. Q., & Wise, A. (2017). Humans and machines together: Improving characterization of large scale online discussions through dynamic interrelated post and thread categorization (DIPTiC). In L@S 2017 - Proceedings of the 4th (2017) ACM Conference on Learning at Scale (pp. 217-219). Association for Computing Machinery, Inc. https://doi.org/10.1145/3051457.3053989

Humans and machines together : Improving characterization of large scale online discussions through dynamic interrelated post and thread categorization (DIPTiC). / Cui, Yi; Jin, Wan Qi; Wise, Alyssa.

L@S 2017 - Proceedings of the 4th (2017) ACM Conference on Learning at Scale. Association for Computing Machinery, Inc, 2017. p. 217-219.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Cui, Y, Jin, WQ & Wise, A 2017, Humans and machines together: Improving characterization of large scale online discussions through dynamic interrelated post and thread categorization (DIPTiC). in L@S 2017 - Proceedings of the 4th (2017) ACM Conference on Learning at Scale. Association for Computing Machinery, Inc, pp. 217-219, 4th Annual ACM Conference on Learning at Scale, L@S 2017, Cambridge, United States, 4/20/17. https://doi.org/10.1145/3051457.3053989
Cui Y, Jin WQ, Wise A. Humans and machines together: Improving characterization of large scale online discussions through dynamic interrelated post and thread categorization (DIPTiC). In L@S 2017 - Proceedings of the 4th (2017) ACM Conference on Learning at Scale. Association for Computing Machinery, Inc. 2017. p. 217-219 https://doi.org/10.1145/3051457.3053989
Cui, Yi ; Jin, Wan Qi ; Wise, Alyssa. / Humans and machines together : Improving characterization of large scale online discussions through dynamic interrelated post and thread categorization (DIPTiC). L@S 2017 - Proceedings of the 4th (2017) ACM Conference on Learning at Scale. Association for Computing Machinery, Inc, 2017. pp. 217-219
@inproceedings{ea99208c92a54aa8993f68a0614b043a,
title = "Humans and machines together: Improving characterization of large scale online discussions through dynamic interrelated post and thread categorization (DIPTiC)",
abstract = "This paper presents a thread characterization method that compares categorization results for thread starters and replies made by a previously-developed natural language model, using human judgment to resolve discrepancies. In an example application using the complete discussion forum data from a MOOC on medical statistics, the method increased the estimation of classification accuracy from .81 to .88 with the addition of a minimal number of human hours.",
keywords = "Discussion forum, Massive open online courses, Thread categorization",
author = "Yi Cui and Jin, {Wan Qi} and Alyssa Wise",
year = "2017",
month = "4",
day = "12",
doi = "10.1145/3051457.3053989",
language = "English (US)",
pages = "217--219",
booktitle = "L@S 2017 - Proceedings of the 4th (2017) ACM Conference on Learning at Scale",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Humans and machines together

T2 - Improving characterization of large scale online discussions through dynamic interrelated post and thread categorization (DIPTiC)

AU - Cui, Yi

AU - Jin, Wan Qi

AU - Wise, Alyssa

PY - 2017/4/12

Y1 - 2017/4/12

N2 - This paper presents a thread characterization method that compares categorization results for thread starters and replies made by a previously-developed natural language model, using human judgment to resolve discrepancies. In an example application using the complete discussion forum data from a MOOC on medical statistics, the method increased the estimation of classification accuracy from .81 to .88 with the addition of a minimal number of human hours.

AB - This paper presents a thread characterization method that compares categorization results for thread starters and replies made by a previously-developed natural language model, using human judgment to resolve discrepancies. In an example application using the complete discussion forum data from a MOOC on medical statistics, the method increased the estimation of classification accuracy from .81 to .88 with the addition of a minimal number of human hours.

KW - Discussion forum

KW - Massive open online courses

KW - Thread categorization

UR - http://www.scopus.com/inward/record.url?scp=85018392940&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018392940&partnerID=8YFLogxK

U2 - 10.1145/3051457.3053989

DO - 10.1145/3051457.3053989

M3 - Conference contribution

SP - 217

EP - 219

BT - L@S 2017 - Proceedings of the 4th (2017) ACM Conference on Learning at Scale

PB - Association for Computing Machinery, Inc

ER -