The UBC Learning Analytics Hackathon is a yearly gathering that unites students, researchers, and educators to develop innovative, data-driven learning analytics tools and techniques aimed at improving the teaching and learning experience at UBC. On October 19, now in its tenth edition, the Hackathon included UBC students from diverse fields and backgrounds coming together for a day full of collaboration and creativity.
Unleashing the power of Canvas discussion boards
Unlike last year’s edition where students were given a variety of data sets, this year, all students shared the challenge of working with discussions in Canvas, UBC’s Learning Management System. CTLT’s Programmer Analyst Alison Myers and the Learning Analytics team challenged participants to focus on this year.
“One part of the Canvas Application Programming Interface (API) is the discussion API. With it, students can access their data and their peers’ discussion boards. A lot of information can be found and used to develop interesting tools.”
Students could explore beyond the Discussions API for the project, but the idea was for groups to have the same initial focus point as a starting goal. From then on, students were given eight hours to come up with creative ideas to make the most out of the data provided to them.
Using Learning Analytics to uncover engaging topics
One of the many benefits of Learning Analytics is that it can be used to sort through vast amounts of students’ learning activities data to improve the teaching and learning experience. It can help to show instructors how students learn best, understand what is working in a course and what needs to be addressed, as well as gathering students’ learning patterns to make adjustments that would help them study more effectively. More broadly, it has the potential to help institutions like UBC make informed decisions on what programs, resources, or support services are needed to help students succeed. This data, combined with resources like GenAI as well as programming languages, can be used to build sentiment analysis, plagiarism checkers, or even discussions analysis tools for students and instructors, if you know where to look.
The discussion feature is a great way for students and instructors to interact with one another outside of class. However, when participation in discussion boards is mandatory, there can be variations in the quality of the interactions posted. “We are building a tool that looks at discussions from a class lecture,” explains one of the groups who participated in the hackathon to challenge themselves by working on a project within a short amount of time. The tool looks at the list of discussions posted on the board and identifies main topics and course elements that student found interesting. The objective is to share this data with instructors so they can increase student engagement both in their class and on discussion boards.”
During last year’s hackathon, participants were already using GenAI tools to help analyze and build their projects, incorporating them to build useful features. This year, these tools were once again front and center. “We are building an AI bot that analyses response rates within discussion boards in order to identify interesting conversation topics, and recommend other topics of discussions,” explains another group who welcomed the opportunity to work with real Canvas data for the hackathon. “We found that when instructors require students to comment or participate in a discussion, responses can sometimes be vague. With our project, we hope to build an AI bot that can sort through it all and find constructive topics so that students can think deeper about a topic or a course.”
Showcasing tools to enhance the UBC teaching and learning experience
At the end of the day, each of the 13 teams presented their project to a panel of judges who evaluated them based on their impact on teaching and learning, technical excellence, and wildest idea. Students also voted on the project that resonated with them the most.
For project most relevant to teaching and learning, the panel recognized the project from the Team HAX group, who wanted to promote discussions that were aligned with learning outcomes and to reduce the number of “spams,” or disengaged posts. They proposed dashboards for instructors and students to help address this challenge.
For technical excellence, the panel recognized Team Five Guys, whose project tackled the meaningful problem of more engaged discussions about Ketchup. The team demonstrated their working which promoted reinforced learning and deeper discussions.
For wildest idea, the panel recognized the Data Wizard group, whose project proposed turning discussions into a more engaging experience by generating animations based on the discussion.
“All the presentations this year were incredibly well done,” Alison explains. “The students showcased all the amazing efforts they put in their projects, and we are always grateful for everyone’s time and enthusiasm, especially on a weekend.”
The Learning Analytics Hackathon took place on October 19, 2024 in the Sauder Learning Labs, a space designed to facilitate teams in using critical thinking and analytical decision making to solve real-world problems. The event was hosted by the UBC Learning Analytics project, LAVA (Learning Analytics, Visual Analytics), and Sauder Learning Services, with staff volunteers from the Centre for Teaching, Learning and Technology.
