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 Friend 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

Publication series

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

Other

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

Keywords

  • Discussion forum
  • Massive open online courses
  • Thread categorization

ASJC Scopus subject areas

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

Fingerprint

Dive into the research topics of 'Humans and machines together: Improving characterization of large scale online discussions through dynamic interrelated post and thread categorization (DIPTiC)'. Together they form a unique fingerprint.

Cite this