Adventures in Technology Enhanced Learning @ UoP

Tag: ChapGPT

AI and Higher Education: Is it time to rethink teaching and assessment?

On 22 February I took part in a roundtable debate on the topic “AI and Higher Education: Is it time to rethink teaching and assessment?”, the event being organised and facilitated by Graide, a UK-based Ed Tech company that uses AI to provide improved feedback in STEM subjects. (I dislike the term ‘artificial intelligence’ in this context, but I think I am fighting a losing battle here. In the interests of clarity, I’ll use the term AI in this blog post.) 

Given the recent furore around generative AI, and its ability to create human-like outputs, Graide thought it would be timely to bring together a variety of voices – senior managers, academics, developers, students – to discuss the potential impact of this new technology on higher education. I was joined on the panel by Bradley Cable (student at Birmingham University); Alison Davenport (Professor of Corrosion Science at Birmingham University); Ian Dunn (Provost of Coventry University); Manjinder Kainth (CEO of Graide); Tom Moule (Senior AI Specialist at Jisc); and Luis Ponce Cuspinera (Director of Teaching and Learning at Sussex University).     

It was fascinating to hear the range of opinions held by the panel members and by the 400+ people who attended the event (and who could interact via polls and via chat). If you are interested in my opinion of the technology then you might want to watch a recording of the debate; alternatively, in the paragraphs below, I’ll attempt to summarise my feelings about Bing, ChatGPT, and similar programs.

* * *

It is easy to see why there should be fears about this technology, particularly around assessment: students might pass off AI-generated content as their own. Critics of the technology have numerous other, entirely valid, concerns: the models might produce biased outputs (after all, they have been trained on the internet!); companies will presumably start to charge for access to AI, which raises questions of equity and digital poverty; the output of these models is often factually incorrect; and so on and so on.

But this technology also possesses the clear potential to help students learn more deeply and lecturers teach more effectively. 

I believe that if we embrace this technology, understand it, and use it wisely we might be able to provide personalised learning for students; design learning experiences that suit a student’s capabilities and preferences; and provide continuous assessment and feedback to enable students themselves to identify areas where they need to improve. The potential is there to provide at scale the sort of education that was once reserved for the elite. 

Note the emboldened if in the paragraph above. To obtain the outcome we desire we need to embrace and explore this technology. We need to understand that the output of large language models relies on statistical relationships between tokens; it does not produce meaning – only humans generate meaning. And we need to use this technology wisely and ethically. It is not clear at this point whether these conditions will be met. Instead, some people seem to want to shut down the technology or at least pretend that it will have no impact on them.

I have heard numerous academics respond to this technology by demanding a return to in-person, handwritten exams. (Would it not be better to rethink and redesign assessment, with this new technology in mind?) I have even heard some lecturers call for a complete ban on this technology in education. (Is that possible? Even if it were, would it be fair to shield students from tools they will have to use when they enter the workforce?) 

* * *

Fear of new technology dates back millennia. Plato, in the Phaedrus, a work composed about 370 BCE, has Socrates argue against the use of writing: 

“It will implant forgetfulness in their [the readers] souls. They will cease to exercise memory because they rely on that which is written, calling things to remembrance no longer from within themselves, but by means of external marks.”

Ironically, we only know about Plato’s argument against writing because it was written down.

More recently, some critics argued that the introduction of calculators would impair students’ mathematical ability. (The research is clear: children’s maths skills are not harmed by using calculators – so long as the devices are introduced into the curriculum in an integrated way.)  Even more recently, some people argued that spellcheckers would impair students’ ability to spell correctly. (It seems the reverse might be the case: students are getting immediate feedback on spelling errors and this is improving their spelling.)

Perhaps it is a natural human response to fear any new technology. And in the case of generative AI there are legitimate reasons for us to be fearful – or at least to be wary of adopting the technology.

But the technology is not going to go away. Indeed, it will almost certainly improve and become more powerful. I believe that if we are thoughtful in how we introduce AI into the curriculum; if we focus on how AI can support people to achieve their goals rather than replace people; if we produce a generation of students that use the technology effectively, ethically, and safely – well, we could transform education for the better.  

Credit Image: Photo by Stable Diffusion 2.1

TEL in ’22 – and looking forward to ’23

(Co-writer: ChatGPT)

In 2022 the TEL team said “goodbye” to some valued colleagues, who moved to take up different roles within the University, and we said “hello” to new colleagues who joined us. Chris, Jo, and Mike have already introduced themselves on TEL Tales, so I would like to use this end-of-year post to discuss a couple of work-related highlights: our implementation of Moodle 4.0 and, regarding the key area of assessment and feedback, our pilot of the WiseFlow end-to-end assessment platform.

Moodle 4.0

Moodle 4.0 is the latest version of the Moodle learning management system, and it includes many new features and improvements that aim to enhance the user experience and support better learning outcomes. Some of the key improvements in Moodle 4.0 include:

  • A new and improved user interface: Moodle 4.0 features a redesigned and modern user interface that is more intuitive and user-friendly, and that provides easy access to the most important features and functions.
  • Enhanced learning analytics and reporting: Moodle 4.0 includes improved learning analytics and reporting tools that provide teachers with more detailed and actionable insights on students’ learning, allowing them to track their progress and identify areas for improvement.
  • Improved accessibility and support for mobile devices: Moodle 4.0 has been designed to be more accessible and user-friendly for users with disabilities, and it includes support for mobile devices, allowing students to access their learning materials and activities on the go.
  • More options for personalization and customization: Moodle 4.0 provides teachers and administrators with more options for personalization and customization, allowing them to tailor the learning environment to the specific needs and preferences of their learners.

Overall, Moodle 4.0 is a significant improvement over previous versions of the learning management system, and it offers many new features and enhancements that can support better learning outcomes and a more engaging and effective learning experience.

At this point I would like to ask the reader: did you notice anything unusual about my discussion of Moodle 4.0?

Moving on, another major project for the TEL team has been to support a pilot implementation of the WiseFlow end-to-end assessment platform. Our hope is that a dedicated platform will allow us to improve our practices around assessment and feedback. Let’s explore that idea below in a little more detail.

Assessment and feedback

There are many different ways to assess students, and the best approach will depend on the specific learning goals and objectives, as well as the context and needs of the learners. Some key principles and strategies that can help to ensure effective assessment of students include:

  • Align assessment with learning goals: The assessment of students should be closely aligned with the learning goals and objectives of the course or programme. This will help to ensure that the assessment is focused on the most important and relevant learning outcomes and that it provides valid and reliable information on students’ progress and achievement.
  • Use a variety of assessment methods: Different assessment methods can provide different types of information and insights into students’ learning, and it is important to use a range of methods in order to get a comprehensive picture of their progress and achievement. Some common assessment methods include tests, quizzes, projects, presentations, portfolios, and observations.
  • Provide timely and meaningful feedback: Feedback is an essential component of assessment, and it is important to provide students with timely and meaningful feedback on their progress and performance. This feedback should be clear, specific, and actionable, and it should help students to understand their strengths and weaknesses, and identify areas for improvement.
  • Engage students in the assessment process: Students should be actively involved in the assessment process, and they should be given opportunities to reflect on their own learning, evaluate their progress, and set goals for improvement. This can help to foster a growth mindset and a sense of ownership and responsibility for their own learning.

Overall, effective assessment of students requires careful planning, the use of a variety of assessment methods, timely and meaningful feedback, and student engagement in the assessment process.

Again, at this point I would like to ask the reader: did you notice anything unusual about my discussion of assessment and feedback?

I inserted those italicised questions above because I (Stephen Webb) did not write any of the text in the two subsections. My “co-author” (ChatGPT) wrote the text.

In 2022, GPT3 (Generative Pre-trained Transformer 3) became a mainstream technology. At least a dozen apps are available that can provide clear, comprehensible text-based responses to prompts provided by a user. An app such as ChapGPT can write essays (and poems, and computer code, and much else besides). And many of our students will know this.

Similar technology can generate artwork. The artwork accompanying this blog post is an original by DALL-E, from a prompt I provided. DALL-E is a much better artist than I can ever hope to be.

I hesitate to call this technology Artificial Intelligence because it is neither artificial nor intelligent; I prefer the term Assistive Computation. Whatever we call the technology, though, I believe that in 2023 we need, as educators, to start grappling with its implications. Can we reasonably assess students by setting them essays to write, when apps can spit out the essays for them? What does the technology mean for notions of authorship and plagiarism? (You will notice that I have credited ChatGPT as being the co-author of this blog post; is that reasonable or meaningful?) What are the best strategies for learning with this technology?

Of course, teachers as well as students can use Assistive Computation. As an experiment, recently, an academic asked ChatGPT to generate a question in a particular knowledge domain that could be set for a first-year undergraduate essay. (The question it generated was entirely suitable.) The academic then asked ChatGPT to generate a rubric for the question. (The rubric was acceptable.) Then the academic asked ChatGPT to write an essay based on the question it had set. (The essay showed no insight, made no new points but would have received a passing grade.) Finally, the academic asked ChatGPT to mark the essay according to the rubric. (The feedback, if nothing else, was at least provided in a more timely fashion than human teachers can provide.)

This experiment suggests to me that either (i) we cut out the middlemen (students and teachers) and let AI do whatever it wants; or (ii) we work together – both students and teachers – to understand how to use Assistive Computation to improve teaching and learning. 

There are many questions here. And I believe 2023 is the year we all need to start grappling with them. Another question: should educators be concerned about this technology? I’ll let my co-author answer:

It’s natural for educators to be concerned about the potential impact of technology on their profession. However, it’s important to note that systems like ChatGPT are not capable of replacing the role of a human educator. While they may be able to generate text, they do not have the ability to understand or evaluate the content of that text in the same way that a human can. It’s also worth considering that the use of such systems may actually highlight the importance of critical thinking and analysis skills, which are vital for success in education and beyond. In the end, the role of educators will continue to be important in helping students develop these skills and prepare for the future.

I (the human, not the AI) would like to wish you an enjoyable festive period and a happy New Year!

Credit Image: An original by DALL-E

© 2024 Tel Tales

Theme by Anders NorénUp ↑