ChatGPT to address faculty burnout

A nightcafe AI image creation using the prompt: A professor dealing with digital burnout and attempting to address it.
NightCafe: Professor dealing with Digital Burnout

 It seems like I am operating in Greek Time for #etmooc2 😅. This is a post for the second session of #etmooc which dealt with ethical issues around AI in education (and maybe AI broadly).  Since the third session record has not been posted yet, I'll make the argument that I am still "on time" for some commentary on this 😂. This post has been in my drafts for 2 weeks now.  With the end of the term upon us, I guess I have a little more time to process some thoughts.

In any case, when I started to put together this blog post a couple of weeks ago, I was signed up for a symposium (or mini-conference?) hosted by a notable LMS provider, and of course, AI was the hot topic du jour.  One of the sessions that I attended was hosted by instructional designers, using ChatGPT, to assist in getting started with course development. Especially if that course development came at the 11th hour when an adjunct finds out that they are teaching a course next week! eek!

In this scenario, an adjunct is asked to create an "INTRO101" course that starts in 2 weeks. As an adjunct, you need to create a syllabus, rubric, discussion, lecture notes, and quizzes. It's noted in this case that this course design may be on top of your current full-time work, so time is at a premium (as is probably the case with most adjuncts).  As someone who's worked as an instructional designer, I appreciate the "let's make the best of it" kind of approach to this, but using generative AI (gAI) to ameliorate a busted system is really problematic! It's also instructional design 101! As part of a needs analysis, faculty don't necessarily need a faster/more efficient way to course design, but rather they need the systematic issues to be addressed.  For example:

1) If the course is an INTRO101 course (not an actual course, just a placeholder for a common course, required of majors, and usually taught by many instructors), the adjuncts should not need to scramble to put together course materials for this course.  The readings, activities, assessments, and rubrics for such a course should already exist, and an instructor should walk in and "turn on the lights" metaphorically.  They should be free to adjust the settings and the materials, but ultimately these should be minor tweaks, not major development work!

2) Hiring for upcoming semesters should not be a "shit's going down in two weeks! Let's roll!" kind of moment. Adjuncts should know at least a few months in advance if they are likely to have a course, and they should be compensated for any additional training required, and any prep they do outside of their contractual period.

3) Faculty are hired as subject experts.  Assuming that someone is hired for their specific subject knowledge (and they're not just another warm body), having gAI create outcomes, course outlines, and assignments (the entire skeleton of a course) really takes away from that subject expertise and starts to frame a course in a way that takes away human agency.  Humans fill in the gaps in what the gAI produces but don't necessarily question it. How do I know?  We see this already with publisher-provided course materials.  I've had more than one professor in my time as a learner that basically used the slides from Publisher, and structured the modules around the textbook, and basically used assignments around the text. Throw in products like My___Lab, and you've removed agency from a human but making it convenient to just go with it.

4) Finally, the material that a gAI produces aren't that great. I have downloaded some ChatGPT outcomes and activities for a class I used to teach (future post), but for this one I'll focus on an experiment I ran with ByteAI. I asked it to give me eight learning objectives for a course titled "Artificial Intelligence in Human Education, Development, and Society." This is what it produced: 
  • Understand the basic concepts and principles of artificial intelligence and its applications in human education, development, and society.
  • Analyze the ethical and social implications of using artificial intelligence in education, development, and society.
  • Evaluate the potential benefits and limitations of using artificial intelligence in education, development, and society.
  • Develop critical thinking skills to assess the impact of artificial intelligence on human learning, development, and society.
  • Explore the different types of artificial intelligence technologies and their applications in education, development, and society.
  • Identify the challenges and opportunities of integrating artificial intelligence into educational and developmental practices.
  • Develop practical skills in designing and implementing artificial intelligence-based educational and developmental interventions.
  • Collaborate with peers to design and present a project that demonstrates the use of artificial intelligence in education, development, and society.

If you'll notice, the objectives are basically like fill-in-the-blanks.  The same starting text can be used for any kind of course. As an aside, it would be interesting to see what it does with other course titles, so I might feed ByteAI some course titles from various university courses. Maybe subject to further experimentation.

Next, I asked ByteAI to provide me with three substantive graduate class assignments for a course titled "Artificial Intelligence in Human Education, Development, and Society." This is what it gave me: 
  • Research Paper: Students will be required to write a research paper on a topic related to the use of artificial intelligence in human education, development, and society. The paper should be based on a critical analysis of the literature and should include a discussion of the ethical and social implications of using artificial intelligence in these contexts.
  • Case Study Analysis: Students will be required to analyze a case study that involves the use of artificial intelligence in human education, development, and society. The case study should be selected from a list of examples provided by the instructor or chosen by the student with instructor's approval. Students will be required to analyze the case study from multiple perspectives, including ethical, social, and practical considerations.
  • Project Proposal: Students will be required to develop a project proposal that involves the use of artificial intelligence in human education, development, and society. The proposal should include a detailed description of the project, including its goals, methods, and expected outcomes. Students will be required to present their proposals to the class and receive feedback from their peers and the instructor.
Again, this is very much a magnetic poetry/fill-in-the-blank kind of output IMO. This kind of output can apply to any class.  Just change "Artificial Intelligence in Human Education, Development, and Society" to your course title 🙄

Anyway, that's what I have for session 2 of #etmooc2. If I have the energy, I'll go through the output of ChatGPT to see what it thinks about what my Intro to Instructional Design & Educational Technology should be ;-)

Comments

Post a Comment

Popular posts from this blog

Latour: Third Source of Uncertainty - Objects have agency too!

Image
Continuing on my exploration of ANT, and asynchronous and indirect dialogue with Latour - this blog post will cover the third source of uncertainty, which according to Latour, is that Objects have agency too! As with the previous blog posts, I've pulled out quotes from the book that seemed interesting, or that I reacted to in some way, and I am responding to them here. no tie can be said to be durable and made of social stuff (p. 66) This quote seems to continue Latour's assertion that there is no such thing as "social" or "social stuff" and that "social", or the meaning of needs to be negotiated and better understood.  It also continues the thought that social can only be seen from the actions of its actors, the traces they leave behind, and that these bonds are not durable because they need continuous reinforcement. I guess Social is a perishable item. Left to its own devices, a power relationship that mobilizes nothing but social skil
Read more

MOOC participation - open door policy and analytics

The other day I was reading ZML Didaktik on the topic of MOOC participants. In MOOCs, one of the big questions is why are people lurking and not participating? If more than 500 people join a MOOC, why are only 10% contributing with any amount of regularity?  On the same blog, in a previous blog post, I had commented (it was an open stream of thought really) that perhaps there should be an open enrollment period, and then if the system sees that certain participants are bellow a threshold of activity, the system may give them the option to self-identify as a lurker, or un-register from the class. This line of thought went along a view that compared to the traditional classroom; in a traditional classroom students register for the course, they can attend classes for a week and then decide whether or not they want to stay with the course or not. If they do stay with the course they know that there is a certain amount of "lurking" that they can get away with, but they do have
Read more

You've been punk'd! However, that was an educational experience

Image
It's now the end of Teaching Goes Massive: New Skills Required (aka #massiveteaching) on coursera. Well, almost, we still have a couple of days left. I guess that the lesson here is that we were (the "learners") were punk'd† by Paul-Olivier Dehaye of the Univerisity of Zurich. After that last blog post (and subsequent pickup of the post by George Siemens and others) Inside Higher Education and the Chronicle wanted to chat with me about this MOOC experience. I only had time for one of the two before things went to press, so my 15 minutes of fame went to IHE.  Both IHE and the C hronicle have written about the topic, and have received some information from Coursera on the incident.  Others have also written about it (see here , here and here ) It's surprising to me that the University, and Coursera, waited until after this thing was a big issue in order to respond in the class, and clue people into what was happening. On Wednesday (day 3 of Week 3/3 of the
Read more