1 / 14

Welcome to SPLICE Workshop 4.0 February 2019

Welcome to SPLICE Workshop 4.0 February 2019. What is SPLICE?. NSF support to project: “Collaborative Research: Community-Building and Infrastructure Design for Data-Intensive Research in Computer Science Education” Ken Koedinger, CMU Peter Brusilovsky , UPitt

marypark
Télécharger la présentation

Welcome to SPLICE Workshop 4.0 February 2019

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Welcome toSPLICE Workshop 4.0February 2019

  2. What is SPLICE? • NSF support to project: “Collaborative Research: Community-Building and Infrastructure Design for Data-Intensive Research in Computer Science Education” • Ken Koedinger, CMU • Peter Brusilovsky, UPitt • Cliff Shaffer and Steve Edwards, Virginia Tech • Grant period: September 1, 2017 – February 29, 2020

  3. Standards, Protocols, and Learning Infrastructure for Computing Education Mission: support the CS Education community by supplying documentation and infrastructure to help with adopting shared standards, protocols, and tools. We promote: • Development and broader re-use of innovative learning content that is instrumented for rich data collection; • Formats and tools for analysis of learner data; and • Best practices to make large collections of learner data and associated analytics available to researchers in the CSE, data science, and learner science communities.

  4. What Have We Accomplished So Far? (1) • Some infrastructure • Website: https://cssplice.github.io • Tutorials: LTI, Caliper • GitHub project • Google Group • Workshops • 1.0: June 2017 in Pittsburg • 2.0: February 2018 in Baltimore • 3.0: August 2018 in Espoo, Finland

  5. What Have We Accomplished So Far? (2) • Working Groups • Small Code Snapshots • Small Coding Exercise Representation • Packaging Curricular Materials • Collaborations!

  6. PART I: Interoperability

  7. Interoperability Issues: Vision • Lots of software artifacts available for use by instructors in a rich network • The artifacts generate learner analytics • The learner analytics data are shared to the various interested parties

  8. Interoperability Issues: Problems • Tools are hard to integrate. (LTI?) • Incompatible learner analytics data (Caliper? Working groups?) • Hard to get analytics to interested parties (Caliper?)

  9. Use Case 1 • An LMS and tools • Hub-and-spokes • LTI pretty well solves basic connection issues, everyone just needs to support • Still have issues with learner analytics (limited data transfer)

  10. Use Case 2 • eTextbook with tools talking to LMS • Examples: OpenDSA, MasteryGrid • eTextbook marshals resources, primes the LMS for access • These resources are other smart content, primarily exercises, like Code Workout, OpenDSA exercises, ACOS exercises, on and on • Can support access to 3rd party tools via LTI • But no delivery of data analytics to any interested members of the network • How to get the data from the exercise (invoked by Canvas) back to the eTextbook? For analysis, and for value-added processing like “late policy”

  11. PART II: Data Formats and Analysis • All of our working groups are more-or-less working on formats • Only a few instances of shared analysis tools?

  12. Part III: Access to Data

  13. Access to Data: Vision • Various tool providers are generating rich data sets • Example: Web-CAT has been collecting data for years • Learning scientists can use data collected by others to test hypotheses

  14. Access to Data: Problems • Even if we solve all issues of data formats and analysis tools, there are issues related to sharing data, due to privacy issues • Clearing with institutions charged with protecting privacy • Sanitizing data while preserving key relationships • Think about sanitizing program source code with comments! • We have a few collaborations sharing data and basic tools for things like anonymization.

More Related