NaviGator Analytics Guide

NaviGator analytics is an instructor facing tool accessible to every official instructor for a credit bearing course at UF. The tool presents historical Canvas LMS, student evaluation, and official final grade data for a specific course that you were officially assigned as a UF instructor. The purpose of this view is to allow official instructors to see how current versus past students have performed. If you were an instructor and were not formally assigned by UF as an instructor to a course, you will not see any data.

The instructor can activate the tool by logging into a specific Canvas course and clicking on the bottom left-hand navigation “Settings” after going to https://elearning.ufl.edu/ and logging into Canvas. After clicking “Settings”, the instructor will see a tab named “Navigation”.  After clicking on “Navigation”, the instructor will need to drag the “NaviGator AI Analytics” tab to the active items of navigation and click “Save” on the bottom of the page.  The instructor should now have access to the NaviGator AI Analytics tab on the left side navigation.  After clicking the “NaviGator AI Analytics” tab, the instructor will need to authorize the service.  No ticket or request is necessary for access to the tool.

Security, Privacy, Data Classification Usage Guidelines

UF provides this service to allow you to leverage AI in analyzing institutional data and uncover insights using different language models while keeping those data sets secure within UF servers and contracted vendors.  At this time, UF permits the usage of restricted or sensitive data with models deployed on UF HiPerGator. The usage of restricted or sensitive data is not permitted with cloud models. Users only have access to their own datasets and conversation history. When interacting with models hosted by vendors, your messages and subsets of your documents will be sent to a LLM instance provided by Microsoft, Amazon, or Google.  All data handled in this fashion is covered by our existing agreements with Microsoft. Amazon, and Google.  None of this data contributes to training the large language model. 

 

User Guide and FAQ

The tool presents historical Canvas LMS, student evaluation, and official final grade data for a specific course that you were officially assigned as a UF instructor. The purpose of this view is to allow official instructors to see how current versus past students have performed. If you were an instructor and were not formally assigned by UF as an instructor to a course, you will not see any data. For a video walkthrough, visit https://app.screencast.com/l6jqVrX9bqcbL
 

  • Whose data is this?
    This data is only data for courses you have been assigned to as an official instructor. If you have taught the course in Canvas at least once as an official instructor, you will see historical data. If you have student evaluations from previous terms for this specific course, you will see a summary of only your student evaluations.
  • Who has access to these data summaries, graphs, and raw data?
    The instructor is the only person with access to any of the data presented. No department chair, administrator, or colleague has access to your data. The data views are secured via official UF login security protocols. Every instructor already has access to the data presented in the tool except that the tool brings the data together in one easy to use location.
  • Is my data secure? I’m especially worried about the Large Language Model (LLM) chatbot available.
    All data is stored on UF secured and controlled databases. The LLM chatbot is housed by UFIT on UFIT servers. Instructor questions and interactions with the LLM are not shared with any outside party within or outside of UF.
  • Who can I contact if I have questions or issues with the job aid?
    Please contact the UFIT Data Science Team at dpa-data-science@ad.ufl.edu.
  • What are the terms of service?
    https://policy.ufl.edu/policy/acceptable-use-policy/
  • What is the privacy policy?
    https://policy.ufl.edu/policy/online-internet-privacy-statement/