Personalization of learning paths in online communities of creators

Document Type

Conference Proceeding

Publication Date

1-1-2016

Abstract

In massive online communities of creators (OCOCs), one of the core challenges is to encourage users to learn to create original contents using basic components. Recommending the right learning components at the right time is critical for improving user engagement and has not been fully studied due to the unstructured nature of online communities. To address the problem, we propose in this paper a novel recommendation model which integrates Cox’s survival analysis and collaborative filtering. Our model can incorporate factors such as user learning history and social engagements, which provides us insights in improving the personalized service. We apply our method to the user data from Scratch online platform and demonstrate the performance of the model.

Publication Source (Journal or Book title)

Proceedings of the 9th International Conference on Educational Data Mining, EDM 2016

First Page

513

Last Page

516

This document is currently not available here.

Share

COinS