Skip to content

Enabling Technologies

LearnLab Enabling Technologies include permanent, on-going tasks (such as LearnSphere based on DataShop) and an evolving collection of tool-development projects of finite duration. See the full suite of learning science tools here and the Open Learning Initiative here.

LearnSphere is a community software infrastructure that supports sharing, analysis and collaboration across a wide variety of educational data. LearnSphere supports researchers as they improve their understanding of human learning. It also helps course developers and instructors improve teaching and learning through data-driven course redesign. The goal is to transform learning science and engineering through a large, distributed data infrastructure and develop the capacity for course developers, instructors, and learning engineers to make use of.

Sharing in LearnSpere: Study Report. Below is an example of LearnSphere in action.

The image is an example workflow with several components. A tab-delimited data file is transformed both to filter missing values and then discretize those values before passing the data to the Search component which searches for causal explanations represented by directed graphs.

DataShop

The LearnLab DataShop is the world’s largest repository of learning interaction data as well as a web application for learning science researchers. It provides secure data storage as well as an array of analysis and visualization tools available through a web-based interface.

An introduction to using DataShop for exploratory analysis

It provides two main services to the learning science community. It is a central repository to secure and store research data and provides a set of analysis and reporting tools.

Researchers can rapidly access standard reports such as learning curves, as well as browse data using the interactive web application. To support other analyses, DataShop can export data to a tab-delimited format compatible with statistical software and other analysis packages.

This is a taste of one of the many analysis tools – learning curves – identify when students are learning or not.  Course developers can modify courses accordingly. 

Other analyses predict student performance.

http://ctat.pact.cs.cmu.edu/

The Cognitive Tutor Authoring Tools (CTAT) are a key LearnLab enabling technology. This suite of authoring tools facilitates the development of computer-based tutors for use in real-world situations for learning science experiments. CTAT tutors are especially suited to serve as the basis for experiments in the LearnLabs since they allow for the systematic administration of different instructional treatments and they integrate with the logging and analysis facilities of the LearnLab DataShop.

Currently, CTAT supports the development and delivery (including web delivery) of two types of tutors: problem-specific Example-Tracing Tutors, which are easy to build, and Cognitive Tutors, which are harder to build but are more general, having a cognitive model of a competent student’s skills.

Cognitive Tutors have a long and successful history that pre-dates CTAT: tutors for high-school math (developed prior to the creation of CTAT) have been shown to be very effective in raising students’ test scores (Koedinger, Anderson, Hadley, & Mark, 1997; Koedinger, Corbett, Ritter, & Shapiro, 2000) and have been used by hundreds of thousands of students (see Carnegie Learning). So far, CTAT has been used considerably outside of the LearnLab context, in research projects, graduate courses, and summer schools. It is beginning to be used within the LearnLab (see below). We are developing extensions necessary for sustained use within LearnLab, namely:

  • Further develop and improve the tools for authoring cognitive models.
  • Extend a “round trip” facility for bootstrapping the development of tutoring capabilities from an existing problem-solving environment, using log data of interactions that students had with this environment.
  • Improve and extend the ways in which tutors can be delivered on the web.
  • Add capabilities for more conveniently delivering different instructional interventions within CTAT-based tutors.
  • Develop facilities for generalization of Pseudo Tutors that will make them re-usable across a range of problems (rather than single problems).
  • Incorporate further extensions prompted by LearnLab researchers and course developers who are using CTAT in their LearnLab courses.

For more information, visit the CTAT website.