Please use this identifier to cite or link to this item: https://doi.org/3415-3421
Title: Using discourse signals for robust instructor intervention prediction
Authors: Chandrasekaran, MK
Epp, CD
Kan, MY 
Litman, D
Issue Date: 1-Jan-2017
Citation: Chandrasekaran, MK, Epp, CD, Kan, MY, Litman, D (2017-01-01). Using discourse signals for robust instructor intervention prediction. Chandrasekaran, MK, Epp, CD, Kan, MY, Litman, D (2017-01-01). Using discourse signals for robust instructor intervention prediction : 3415-3421. ScholarBank@NUS Repository. (Chandrasekaran, MK, Epp, CD, Kan, MY, Litman, D (2017-01-01). Using discourse signals for robust instructor intervention prediction : 3415-3421. ScholarBank@NUS Repository.) : 3415-3421. ScholarBank@NUS Repository. https://doi.org/3415-3421
Abstract: We tackle the prediction of instructor intervention in student posts from discussion forums in Massive Open Online Courses (MOOCs). Our key finding is that using automatically obtained discourse relations improves the prediction of when instructors intervene in student discussions, when compared with a state-of-the-art, feature-rich baseline. Our supervised classifier makes use of an automatic discourse parser which outputs Penn Discourse Treebank (PDTB) tags that represent in-post discourse features. We show PDTB relationbased features increase the robustness of the classifier and complement baseline features in recalling more diverse instructor intervention patterns. In comprehensive experiments over 14 MOOC offerings from several disciplines, the PDTB discourse features improve performance on average. The resultant models are less dependent on domain-specific vocabulary, allowing them to better generalize to new courses.
Source Title: Chandrasekaran, MK, Epp, CD, Kan, MY, Litman, D (2017-01-01). Using discourse signals for robust instructor intervention prediction : 3415-3421. ScholarBank@NUS Repository.
URI: https://scholarbank.nus.edu.sg/handle/10635/229628
DOI: 3415-3421
Appears in Collections:Staff Publications
Elements

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
aaai17.pdf203.59 kBAdobe PDF

OPEN

Post-printView/Download

Page view(s)

24
checked on Sep 29, 2022

Download(s)

3
checked on Sep 29, 2022

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.