The increasing utilization of massive open online courses has significantly expanded global access to formal education. Despite the technology's promising future, student interaction on MOOCs is still a relatively under-explored and poorly understood topic. This work proposes a multi-level pattern discovery through hierarchical discriminative tensor factorization. We formulate the problem as a hierarchical discriminant subspace learning problem, where the goal is to discover the shared and discriminative patterns with a hierarchical structure. The discovered patterns enable a more effective exploration of the contrasting behaviors of two performance groups. We conduct extensive experiments on several real-world MOOC datasets to demonstrate the effectiveness of our proposed approach. Our study advances the current predictive modeling in MOOCs by providing more interpretable behavioral patterns and linking their relationships with the performance outcome.
Beschreibung
Iterative Discriminant Tensor Factorization for Behavior Comparison in Massive Open Online Courses
%0 Conference Paper
%1 Wen:2019:IDT:3308558.3313713
%A Wen, Xidao
%A Lin, Yu-Ru
%A Liu, Xi
%A Brusilovsky, Peter
%A Barr\ A-a Pineda, Jordan
%B The World Wide Web Conference
%C New York, NY, USA
%D 2019
%I ACM
%K behavior-analysis behavior-patterns myown tensors
%P 2068--2079
%R 10.1145/3308558.3313713
%T Iterative Discriminant Tensor Factorization for Behavior Comparison in Massive Open Online Courses
%U http://doi.acm.org/10.1145/3308558.3313713
%X The increasing utilization of massive open online courses has significantly expanded global access to formal education. Despite the technology's promising future, student interaction on MOOCs is still a relatively under-explored and poorly understood topic. This work proposes a multi-level pattern discovery through hierarchical discriminative tensor factorization. We formulate the problem as a hierarchical discriminant subspace learning problem, where the goal is to discover the shared and discriminative patterns with a hierarchical structure. The discovered patterns enable a more effective exploration of the contrasting behaviors of two performance groups. We conduct extensive experiments on several real-world MOOC datasets to demonstrate the effectiveness of our proposed approach. Our study advances the current predictive modeling in MOOCs by providing more interpretable behavioral patterns and linking their relationships with the performance outcome.
%@ 978-1-4503-6674-8
@inproceedings{Wen:2019:IDT:3308558.3313713,
abstract = {The increasing utilization of massive open online courses has significantly expanded global access to formal education. Despite the technology's promising future, student interaction on MOOCs is still a relatively under-explored and poorly understood topic. This work proposes a multi-level pattern discovery through hierarchical discriminative tensor factorization. We formulate the problem as a hierarchical discriminant subspace learning problem, where the goal is to discover the shared and discriminative patterns with a hierarchical structure. The discovered patterns enable a more effective exploration of the contrasting behaviors of two performance groups. We conduct extensive experiments on several real-world MOOC datasets to demonstrate the effectiveness of our proposed approach. Our study advances the current predictive modeling in MOOCs by providing more interpretable behavioral patterns and linking their relationships with the performance outcome.},
acmid = {3313713},
added-at = {2019-05-23T19:56:59.000+0200},
address = {New York, NY, USA},
author = {Wen, Xidao and Lin, Yu-Ru and Liu, Xi and Brusilovsky, Peter and Barr\ {A}-a Pineda, Jordan},
biburl = {https://www.bibsonomy.org/bibtex/2aca8f406a913badfa55cb2448c48263e/brusilovsky},
booktitle = {The World Wide Web Conference},
description = {Iterative Discriminant Tensor Factorization for Behavior Comparison in Massive Open Online Courses},
doi = {10.1145/3308558.3313713},
interhash = {328bc7163fbacad52803f1819c94a046},
intrahash = {aca8f406a913badfa55cb2448c48263e},
isbn = {978-1-4503-6674-8},
keywords = {behavior-analysis behavior-patterns myown tensors},
location = {San Francisco, CA, USA},
numpages = {12},
pages = {2068--2079},
publisher = {ACM},
series = {WWW '19},
timestamp = {2019-05-23T19:56:59.000+0200},
title = {Iterative Discriminant Tensor Factorization for Behavior Comparison in Massive Open Online Courses},
url = {http://doi.acm.org/10.1145/3308558.3313713},
year = 2019
}