AI-enhanced live polling


A Long View of Undergraduate Research

A long time ago (in a galaxy far away?), I spent all three summers of my college years in undergraduate research experiences. That first summer I worked on a project that seems quaint now: I built a website for sharing a collection of quotations about mathematics that my mentor, a math professor, had collected. And (I can't believe this) the website is still around! See the Furman University Mathematical Quotations Server for a flashback to mid-90s web design. And, yes, I designed that logo. I'm sorry.

I went on to spend two summers working with a computer science professor on a NASA-funded grant aimed at building a computational model of weather patterns. More specifically, I learned about parallel processing so that I could contribute code that would make that model work a lot faster than it had before. I'm not sure I actually helped much, but I learned a fair amount about partial differential equations and I had the chance to visit the NASA Goddard Space Flight Center with my mentor.

Those summer undergraduate research experiences came to mind when interviewing the authors of the new book A Long View of Undergraduate Research: Alumni Perspectives on Inquiry, Belonging, and Vocation. Kristine Johnson and Michael Rifenburg are both English professors, they both participated in undergraduate research as students, and they both currently mentor undergrad students in research. They wanted to know what elements of an undergrad research experience made a difference post-graduation, so they tracked down alumni who had those experiences as students and asked them.

What they found was fascinating. They learned how important it was to these alumni that they had worked closely with a professor. Going on a trip with a mentor to present one's research (or, say, visit NASA) can have quite an impact on a college student. They also learned how isolating summer undergraduate research can be for students living and working on a mostly deserted campus. I very much related to that! I didn't have any friends who stuck around my alma mater the summer after my first year. Things were different after my sophomore and junior years. And those summers I was part of a student research team, which made a difference.

On this week's episode of Intentional Teaching, I talk with Kristine and Michael about their research. They share some powerful stories of how undergraduate research can help students find a passion and eventually a vocation, even if that vocation doesn't look exactly like the research they conducted as a student. They also provide some very practical advice for mentoring students in these experiences and for expanding access to undergraduate research for more students. If undergraduate research is any part of your professional life, I recommend listening to this interview and checking out their book, A Long View of Undergraduate Research.

You can listen to my interview with Kristine Johnson and Michael Rifenburg here, and you can learn more about their book, which was co-published by Elon University's Center for Engaged Learning, right here.

AI-Enhanced Polling

Back in November 2023, I wrote in my blog about an idea for using generative AI that I picked up from the POD Network conference: What if I could ask my students a free-response polling question and then have an AI assistant read and summarize the students’ responses? The next month, I tried this idea out at a workshop I led for some psychology instructors, using Poll Everywhere to collect responses to an open-ended question and then (after a bunch of clicks on my laptop) having ChatGPT identify themes in those responses. AI-generated thematic analysis isn't rigorous enough for research, but it was perfect for making quick sense of a lot of open-ended responses, enabling me to use those themes to guide subsequent discussion.

I wondered at the time, when will one of the major polling tools used in higher education roll out this feature?

Well, it took longer than I expected, but I learned recently that Mentimeter has indeed added this feature! Thanks to fellow educational developer Tolu Noah for tipping me off to this. When you ask your audience an "open ended" question type on Menti, you'll see an option at the bottom of the screen to use Menti's built-in AI tool to sort the responses into groups. This takes a few seconds, but it's a lot easier than what I was doing with Poll Everywhere (leaving the polling presentation, exporting the response history as a CSV file, copying and pasting the responses into ChatGPT, then giving ChatGPT a prompt that would have it identify themes).

Menti's AI polling enhancements go a little further than my ChatGPT experiments, too. When you click on one of the groups that Menti has identified, you can see all the individual responses that were collected in that group, which is very handy for leading a discussion about the theme represented by that group. You can also right-click on an individual response and quickly move it to a different group if the AI missed the mark in how it categorized the response.

In the two live experiments I've run, the AI did a good but not great job sorting responses into sensible groups. Both times I felt I needed to move a couple of responses around. I haven't tried this feature with more than 20 participants. It might work better (or worse) with larger collections of responses. But, wow, this has a lot of potential for making open-ended polling questions more practical in large classes!

Props to Mentimeter for adding this feature! And I'm still predicting that other polling tools will do something similar soon, since it's such a clear use case for generative AI. (I'm looking at you, Poll Everywhere.)

Thanks for reading!

If you found this newsletter useful, please forward it to a colleague who might like it! That's one of the best ways you can support the work I'm doing here at Intentional Teaching.

Or consider supporting Intentional Teaching through Patreon. For just $3 US per month, you can help defray production costs for the podcast and newsletter and you get access to Patreon-only interviews and bonus clips.

Intentional Teaching with Derek Bruff

Welcome to the Intentional Teaching newsletter! I'm Derek Bruff, educator and author. The name of this newsletter is a reminder that we should be intentional in how we teach, but also in how we develop as teachers over time. I hope this newsletter will be a valuable part of your professional development as an educator.

Read more from Intentional Teaching with Derek Bruff

I was on the fence about reading John Warner’s new book, More Than Words: How to Think about Writing in an Age of AI. It wasn’t that I didn’t respect Warner’s work. No, I had been following his work for years, especially his Just Visiting blog on Inside Higher Ed where he writes about teaching. His was an essential voice for me after ChatGPT launched in late 2022. He had already argued in his book Why They Can’t Write: Killing the Five-Paragraph Essay and Other Necessities that writing...

Take It or Leave It with Liz Norell, Betsy Barre, and Bryan Dewsbury This week on the podcast I once again borrow a format from one of my favorite podcasts and host a Take It or Leave It panel. I invited three colleagues whose work and thinking I admire very much to come on the show and weigh in on several "hot take" essays on teaching and learning in higher ed. For each essay, each panelist had to Take It (that is, agree with the central thesis of the essay) or Leave It (that is, disagree)....

Midjourney image generated from this prompt: an intersection of uncountably many streets with hundreds of traffic lights, some showing red, some showing green, in a near-future sci-fi M.C. Escher style

One of the most frequent requests I get from faculty is to see examples of actual assignments that thoughtfully integrate generative AI. I am very happy to share a new collection of such assignments on the University of Virginia Teaching Hub: "Integrating AI into Assignments to Support Student Learning." In my day job at the University of Virginia, I'm helping to support about 50 faculty fellows who are part of UVA's Faculty AI Guides program. These faculty are exploring the use of generative...