Year: 2020
Type: preprint
Abstract: This paper presents several strategies that can improve neural network-based predictive methods for MOOC student course trajectory modeling, applying multiple ideas previously applied to tackle NLP (Natural Language Processing) tasks. In particular, this paper investigates LSTM networks enhanced with two forms of regularization, along with the more recently introduced Transformer architecture.
Source: arXiv (Cornell University)
Authors: Chen, Clarence, Pardos, Zachary
Institution: University of California, Berkeley
Language: English
Subfield: Computer Science Applications
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: green
OpenAlex ID: W3109104459
