DANCE: Discussion Affordances for Natural Collaborative Exchange


DANCE Talk Series

One goal of the DANCE initiative is to provide a community platform to help researchers in the MOOC/CSCL space interested in contributing to the OpenEdX platform. This page aggregates resources the came out of the DANCE effort as well as related third party tools and artifacts. It is our hope that this can inspire contributions by others and foster discussion among the community of CSCL researchers about possibilities for collaborative tools that can be deployed and tested on platforms such as OpenEdX.

DANCE XBlock Development

The DANCE discussion forum XBlock represents a first step towards improving scripted support for collaboration in MOOCs. The XBlock provides all basic features expected of a forum while augmenting the experience with social recommendation (that as an example recommendation application matches help seekers with help givers). It provides light social awareness and semi-synchronous interaction through a Personal Messaging capability. It also provides the forum data in a source agnostic data infrastructure model using DiscourseDB (see below) that will allow the contextualization and comparison of discourse data from across platforms.

  • The source code and documentation can be found on GitHub.
  • A walkthrough of its functionality can be found here.
  • The features currently on offer from the XBlock as well as planned additions can be found here.
  • The design document detailing the overarching goals and guiding principles behind the development of the XBlock can be found here.


DiscourseDB is an NSF funded data infrustructure project designed to bridge data sources from multiple platforms for hosting those learning experiences. Our vision is to provide a common data model designed to accommodate data from diverse sources including but not limited to Chat, Threaded Discussions, Blogs, Twitter, Wikis, and Text messaging.

We will make available analytics components related to constructs including role taking, help exchange, collaborative knowledge construction, showing openness, taking an authoritative stance, attitudes, confusion, alliance and opposition. In enabling application of such metrics across datasets from multiple platforms, research questions related to the mediating and moderating effect of these process and state measures on information transfer, learning, and attrition can be conducted, building on the earlier research of our team.


Bazaar is a publicly available architecture for orchestrating conversational agent based support for group learning. It is a powerful tool for facilitating research in collaborative learning. It hosts a library of reusable behavioral components that each trigger a simple form of support. More complex supportive interventions are constructed by orchestrating multiple simple behaviors. Its flexibility and simplicity mean it can be used to very rapidly develop platforms for investigating a wide range of important questions within the design space of dynamic support for collaborative learning.

  • The source code is freely available on GitHub.
  • Slides and video recordings of a Bazaar tutorial (May 2016) can be found here
  • You can find additional documentation and links to relevant research papers here.


The open-source LightSide platform, including the machine-learning and feature-extraction core as well as the researcher's workbench UI, has been and continues to be funded in part through Carnegie Mellon University, in particular by grants from the National Science Foundation and the Office of Naval Research. See the full acknowledgements and grant details below!

We make the LightSide research platform freely available for research and education. In exchange, we ask that you provide us with basic information about who you are and how you're making use of LightSide's capabilities.

  • You can download the current LightSide binaries and the user manual here
  • The source code is freely available on GitHub.

Social Recommendation

Massive Open Online Courses have experienced a recent boom in interest. Problems students struggle with in the discussion forums, such as difficultly in finding interesting discussion opportunities or attracting helpers to address posted problems, provide new opportunities for recommender systems.

We developed a social recommendation technology to support help seekers in MOOC discussion forums implemented using a context-aware Matrix Factorization model to predict students' preferences for answering a given question. This recommendation framework allows for this two-way recommendation. The source code is freely available on GitHub.


  • Yang, Diyi, Piergallini, Mario, Howley, Iris and Carolyn Penstein Rose. "Forum thread recommendation for massive open online courses." Educational Data Mining 2014. 2014.
  • Yang, Diyi, David Adamson, and Carolyn Penstein Rose. "Question recommendation with constraints for massive open online courses." Proceedings of the 8th ACM Conference on Recommender systems. ACM, 2014.

Third party XBlocks

EdX courseware is built out of components that are combined hierarchically. These "XBlocks" include components like the video player or compound components like learning sequences. We gather information about XBlocks developed by the community that facilitate collaboration in online learning environment. Whereever possible, we provide a testbed for users to try these components along with links to the original sources.

Find out more on our third party edX resources page.

Links to Additional External Resources

The formalism of a MOOClet provides a Framework for how instructors, engineers, and scientific researchers can conceptualize, design and use technology for digital education. It guides the alignment of instructional improvements in digital educational resources (like lessons, exercises, questions) with the advancement of scientific research on learning technologies. Unhangout

Unhangout is an open source platform for running large-scale, unconferences online. It uses Google Hangouts to create as many small breakout sessions as needed, and help users find others with shared interests.