Towards Optimization of Macrocognitive Processes: Automating Analysis of the Emergence of Leadership in Ad Hoc Teams
Abstract
An important focus for technical research related to machine learning has been to address not only generalization across sub-community structures within a hierarchical dataset, but also accommodating changes over time in a longitudinal dataset using evolving behavior models. We have two prototype models built and working and are extending that work to make it more scalable to larger datasets. We completed a highly scalable model, being able to be applied to networks with millions of users. We validated the model on 3 different data sets from Massive Open Online Courses and found that the sub-community structure identified by the algorithm was predictive of differences in dropout rate between subsets of students.
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 21, 2014
- Accession Number
- ADA606908
Entities
People
- Andrew Duchon
- Carolyn P. Rose
- Emily Patterson
- Gerry Stahl
- John Carroll
- Marcela Borge
- Sean Goggins
Organizations
- Carnegie Mellon University