DeepAI AI Chat
Log In Sign Up

Communication Communities in MOOCs

by   Nabeel Gillani, et al.
University of Oxford

Massive Open Online Courses (MOOCs) bring together thousands of people from different geographies and demographic backgrounds -- but to date, little is known about how they learn or communicate. We introduce a new content-analysed MOOC dataset and use Bayesian Non-negative Matrix Factorization (BNMF) to extract communities of learners based on the nature of their online forum posts. We see that BNMF yields a superior probabilistic generative model for online discussions when compared to other models, and that the communities it learns are differentiated by their composite students' demographic and course performance indicators. These findings suggest that computationally efficient probabilistic generative modelling of MOOCs can reveal important insights for educational researchers and practitioners and help to develop more intelligent and responsive online learning environments.


page 1

page 2

page 3

page 4


Tracking Behavioral Patterns among Students in an Online Educational System

Analysis of log data generated by online educational systems is an essen...

Why do people participate in small online communities?

Many benefits of online communities—such as obtaining new information, o...

Inferring learners' affinities from course interaction data

A data-driven model where individual learning behavior is a linear combi...

Online Prediction of Dyadic Data with Heterogeneous Matrix Factorization

Dyadic Data Prediction (DDP) is an important problem in many research ar...

Tracing Forum Posts to MOOC Content using Topic Analysis

Massive Open Online Courses are educational programs that are open and a...

Exploring Bayesian Deep Learning for Urgent Instructor Intervention Need in MOOC Forums

Massive Open Online Courses (MOOCs) have become a popular choice for e-l...

Scalable Bayesian Non-Negative Tensor Factorization for Massive Count Data

We present a Bayesian non-negative tensor factorization model for count-...