Kelli McGraw

The AI future for lesson plans is already here


Another of our intermittent blogs during the #AARE2022 conference
If you want to cover a session at the conference or want to respond to something you’ve heard, please email jenna@aare.edu.au to check in. Thanks!

George Siemens gave the 2022 AARE conference keynote speech yesterday morning and the takeaway was this: artificial intelligence (AI) is already changing education in Australia whether we’re ready for it or not. He went on to suggest that unless we’re mindful we, as researchers and teacher educators, may not have a seat at the table in deciding what the future of education will look like. This blog post is about the future of AI-generated lesson plans and how we might think about this development today and into the future. Think of it as a concrete case study of exactly what George was talking about this morning where the conclusions might apply to other areas of education

What do today’s AI-generated lesson plans look like?

AI-generated lesson plans are already better than many people realise. Here’s an example generated through the GPT-3 deep learning language model:

Prompt: A lesson plan for English for teaching 16 year old students about the idea of “juxtaposition” within Romeo and Juliet.

Output from GPT-3 (verbatim, with formatting provided by the algorithm):

Background

Juxtaposition is the act of placing two things side by side, often for contrast. In literature, authors often use juxtaposition to create a certain mood or atmosphere, or to emphasize certain qualities of a character or situation.

 In Romeo and Juliet, Shakespeare uses juxtaposition extensively to contrast the two lovers and their families, the Montagues and the Capulets. He also uses juxtaposition to contrast the tragic events of the play with the light-hearted moments.

 Objectives

 By the end of the lesson, students will be able to:

 – Understand the concept of juxtaposition

– Identify examples of juxtaposition in Romeo and Juliet

– Explain how juxtaposition is used to create mood and atmosphere in the play

 Materials

 – A copy of Romeo and Juliet

– A whiteboard and markers

– A teacher-created handout with examples of juxtaposition from the play (optional)

 Procedure

 1. Introduce the concept of juxtaposition to the class. Explain that authors often use this literary device to create contrast and emphasize certain qualities.

 2. Ask the students to think of an example of two things that are often juxtaposed. Write some of their responses on the board.

 3. Tell the students that they are going to be looking for examples of juxtaposition in Romeo and Juliet. Explain that they should pay attention to how the contrast created by the juxtaposition contributes to the mood and atmosphere of the play.

 4. Give the students time to read through the play, or assigned sections of the play if time is limited. As they are reading, they should be looking for examples of juxtaposition.

 5. Once the students have finished reading, ask them to share the examples of juxtaposition that they found. Write these examples on the board.

 6. Finally, ask the students to explain how the juxtaposition affected the mood and atmosphere of the play. What did it emphasize about the characters or the situation?

 Extension Activity

 Have the students find additional examples of juxtaposition in other works of literature, or in everyday life. They can share their examples with the class and explain how the contrast created by the juxtaposition contributes to the overall effect.

Imagine that you’d set a task for a class of second year Bachelor of Education students to create a lesson plan with that same prompt. How do you think the AI response would compare to some of your students?

Anybody can generate their own lesson plans for a year level, subject area, and topic that interests them with a similar prompt: https://beta.openai.com/playground

Some concerns

It is trivially easy to generate useful lesson plans using this technique. One obvious upshot is that setting assessment tasks for any students in initial teacher education that involve them creating lesson plans isn’t a great idea any more—it’s too simple for them to generate one. Yet there are new opportunities that arise:

  • Why not get students to generate a few lesson plans, look at the patterns, and write something about the essential structure of this thing that we call a ‘lesson plan’?
  • Why not get them to take a generated lesson plan and improve it, annotating the reasons why their changes have made it better?

Another legitimate concern that arises is that inservice teachers might start to use the next generation of AI-generated lesson plans (which will undoubtedly be an order of magnitude more powerful) without critique—or worse, that some jurisdictions might actually request that teachers use such an approach in future.

A word that we need to look to is “design”

The issues raised by AI regarding lesson plans and in many places in education too can be addressed by consideration of design. When design in education is done well (whether that’s learning by design, design thinking, co-design, or within the subject area named “design”) it always places an emphasis on two things:

  1. Authentic problems: such that the learner must always construct an interpretation of the problem before they can address it
  2. Process and rationale such that the output that the student produces is impressive only if their process and rationale support what they’ve done.

When assessments follow these two ingredients then educators can give students free rein to use whatever tools they have at their disposal. The adoption of AI stops being a concern. When students are being assessed through their process rather than their output, students can use whatever tools are available. The challenge is integrating use of such tools into solving problems through collaboration, critical thinking, cultural understanding, and creativity.

Design as a response to “what should be taught”

George Siemens concluded his presentation by suggesting a list (controversially) of what should be taught in the context of an AI future. A summary/interpretation of his key points of what we should be teaching is:

  • Beingness: what it means to be human in the world, the interconnectedness of all things
  • Systems thinking: how systems change and what complexity is about
  • Technology and how to use it: machine learning and data literacy, computational thinking, collaborating with non-human intelligences

Increasingly, design has become a part of education: design for learning, learning by design, thinking, and so on. The epistemic fluency to design using computational tools in a way that enriches material life and human culture is at the root of all three of these areas. 

For any subject area, teaching using a design approach shifts the focus from knowing content to knowing process. It becomes less about how to get from A to B in a straight line and more about knowing how to frame problems, use tools, and communicate outcomes. More design in education provides one way of responding to this increase presence of AI in education, whether we’re ready for it or not.

It might even provide a response to George’s provocation about McKinsey, Deloitte, or Microsoft trying to get in on a slice of the education sector. Education conceived as design—process rather than output—prioritises the humans involved in the enterprise and makes it harder to sideline educators.

Dr Nick Kelly is a Senior Lecturer in Interaction Design at the Queensland University of Technology, in the School of Design. He is a genuinely cross-disciplinary researcher spanning the fields of Design and Education. He conducts research into design cognition (how designers think), metacognition in learning (how teachers and learners develop their metacognitive abilities), and places where these two things come together (design pedagogy, design for learning, learning by design, design of learning technologies). His specialisation is in the design, facilitation, and analysis of online communities.

Dr Kelli McGraw is a Lecturer in the Faculty of Creative Industries, Education Social Justice at QUT. Currently teaching units in Secondary English curriculum, pedagogy and assessment, her prior experience includes teaching high school English and debating in Southwest Sydney, NSW. Kelli researches the fields of English curriculum studies, secondary school assessment, teacher identity, digital literacy, popular culture and new media texts.

21 simple design elements that will make any School Assessment Task sheet accessible

If you have a child in secondary school in Australia, you are probably familiar with assessment task sheets. They outline the task a student has to complete and how it will be assessed. The criteria and standards that will be used to evaluate the performance are included. Often the task sheet will also aim to excite and motivate students to engage with a real-world problem or life-like performance that is relevant and meaningful to them.

Assessment task sheets are really invitations for students to create a performance to show others what they know.

Yet for many students these days, the complexity of the invitation can lead them to give up before they even start. It is a growing problem as assessment task sheets become increasingly complicated documents.

They often now contain a lot of information only intended for adult audiences because they can be used to help justify assessment decisions to parents, and can serve accountability purposes by providing evidence that the teacher has complied with the requirements of a syllabus. So they could feature technical terms from the syllabus and more information than is necessary for student understanding.

For students with language and attentional difficulties, these multiple purposes and the complexity of tasks can present barriers that prevent them from successfully participating in the assessment. Complex assessment task sheets can therefore be unfair.

We believe it is possible to design assessment tasks and write up accompanying assessment task sheets that allow more students to participate than is currently the case. Our research shows design techniques that support teachers to do this.

Currently many teachers spend precious time retrospectively adjusting tasks and rewriting task sheets to give access to students experiencing difficulties. It is a practice that is time-consuming for busy teachers and so is typically only done for students with severe disabilities.

In Australia, however, it is a federally legislated requirement for reasonable adjustments to be made to support all students with disability to access their education on the same basis as students without disability, as described in the Disability Standards for Education.

So we see our work in this field as being relevant to all teachers in every subject and at every level, whenever they are designing and writing an assessment task for their students. If the task is designed and written in an accessible way, students with language and attentional difficulties can do the same task using the same task sheet and teachers will no longer need to create other versions, readjust or rewrite for these students.

But… could this give some students an unfair advantage?

A key barrier to accessible assessment is the fear that reasonable adjustments could lead to a ‘dumbing down’ of the assessment or that they provide an unfair advantage to students with a disability. However, this would only be true if the benefit were not universal or if the main aim of the assessment was to test students’ ability to interpret assessment task sheets.

If accessible assessment tasks are proactively planned and provided to all students, then the benefit is universal. And, if the assessment task focuses on the knowledge or skill being assessed (the first order priority of assessment), then it is still a valid and fair assessment.

Importantly, as Joy Cumming and Graham Maxwell have previously pointed out, when second-order priorities (such as the accountability purposes of assessment) complicate assessment purposes to the extent that the assessment task itself creates barriers to student access and participation, then the result is not a true reflection of that student’s response to the (first-order) purpose of the assessment and the assessment is therefore inequitable.

The challenge is to design assessment that is accessible from the outset of planning, so that teachers can maximise opportunities for all learners to have access to assessment tasks.

Challenges of access that students must overcome

We analysed a typical Year 8 English task sheet and considered the visual, procedural and linguistic complexity of the task sheet design to highlight how some assessment practices may inadvertently affect access and therefore equity.

There are three considerable challenges students must face to correctly interpret an assessment task and successfully demonstrate their learning. These are: –

  • Comprehending what the task is about
  • Working out what has to be done
  • Understanding the parameters in which to do it

Access can be made easier or more difficult depending on the way the assessment task is presented; both in terms of visual presentation and in terms of the language used. The number and type of procedures required can also differentially affect students’ successful completion of the task.

This approach to analysis helped us to produce a list of recommended design elements that will be useful to teachers as they plan and write up their assessment tasks.

Design elements that support making assessment tasks accessible

Visual accessibility

The layout of the task sheet helps the students access the important elements of the task

  • The most important information is easy to find
  • White space is used to separate sections
  • Text size aids readability (11 or 12 point font with 1.5 line spacing)
  • Margins are left-justified
  • Visual cues direct student attention
  • Information that is irrelevant to students is not included

Procedural accessibility

Consistency and clarity of instructions

  • Authentic context is relevant
  • Common access barriers have been addressed in the design
  • The task, objectives and criteria align
  • Students are able to respond within the prescribed conditions
  • Enough space and resources are provided for responses
  • The assessment is scheduled to give students the best opportunity for success
  • Processes for evaluating quality are clear
  • Authentication strategies are included
  • Student feedback on the draft task was sought
  • Teacher peer feedback on draft task was sought

Linguistic accessibility

Directions are clear

  • Instructions are clear and direct
  • Sentences are short and simply structured
  • The language is free of bias
  • Specialist language is defined using student-friendly terms
  • Information is stated once only and if it needs to be referenced more than once, consistent terminology is used

Encouraging results from using these recommendations

We used an accessibility checklist based on these recommendations to support teachers in their assessment design work in two secondary schools participating in our research.

Significantly, teachers who participated in this research reported that students who had not previously found success were able to demonstrate their learning with new levels of confidence.

We believe proactive accessible assessment design has the potential to increase the assessment participation and success of all students, especially those with language and attentional difficulties.

An added bonus is that designing for accessibility from the outset promises to reduce teacher workload due to fewer requests for clarification from students and less need for retrospective adjustments.

 

More in our open access paper Designing out barriers to student access and participation in secondary school assessment

 

Haley Tancredi is a Master of Philosophy (Education) candidate at QUT. A certified practicing speech pathologist, Haley also presently works for Brisbane Catholic Education. Haley’s research and clinical interests are adolescents with language disorder, student voice and teacher/speech pathologist collaboration in inclusive classrooms. Haley is also an active #WeSpeechie on Twitter @HaleyTanc.

 

 

 

Linda Graham is a Professor in the School of Early Childhood and Inclusive Education in the School of Early Childhood and Inclusive Education, Queensland University of Technology (QUT). She coordinates Inclusive Education Theory, Policy and Practice, a core unit in the Faculty of Education’s Master of Inclusive Education. She leads QUT’s Student Engagement, Learning and Behaviour Research Group (@SELB_QUT) and a number of research projects in the area of inclusive education. She can often be found on Twitter: @drlindagraham and at linda.graham@qut.edu.au

 

 

Jill Willis is an assessment researcher and senior lecturer in the Faculty of Education at Queensland University of Technology. She investigates how educators promote learner agency and equity through their everyday assessment practices. You can reach her via Twitter: @JillWteachEd

 

 

 

Kelli McGraw is a lecturer in secondary English curriculum in the Faculty of Education at Queensland University of Technology. Her current research is on the role of social media technologies in engaging first year university students, and the use of online writing for assessment. Previously she worked as a teacher of high school English in South-western Sydney, NSW. Kelli is the Vice President of the English Teachers Association of Queensland. You can reach her via Twitter: @kmcg2375

 

I am a teacher of English teachers and I never want to hear the term “basic skills” ever again

Lecturer in secondary English curriculum in the Faculty of Education at Queensland University of Technology

One cohort at a time, I am doing my bit to erase the misleading, poorly defined, and often destructive term ‘basic skills’ from educational discourse.

I ask my second year student teachers in their first assignment in English Curriculum Studies to explain their philosophy on English teaching and tell me which teaching methods they think are important in 2014.

I warn them, ” If you tell me that you advocate a ‘basic skills’ approach to teaching I will fail your paper.”

I won’t. (I only tell them this afterwards.)

What I am trying to do is make them think deeply about their work as future English teachers. I want them to better articulate what kinds of skills they consider fundamental to living a healthy, happy, literate life.

I believe the discussion and debate this produces is invaluable to their understanding as aspiring teachers in the 21st century.

Why do I bother with this?

The term ‘basic skills’ is an affront to educators like me on many levels.

Firstly, there are the negative connotations of the term ‘basic’. If these skills are so basic, as in ‘boring’ or ‘unintriguing’, we should not be surprised that students don’t flock to master them. Nor should we be surprised when teachers opt not to employ teaching methods that drill students on them, lest they run the risk of boring everyone to death.

Secondly, it belies the complex task of engaging students with learning in areas such as literacy or numeracy. To non-teachers who insist on using the term basic skills I say: if  the job of teaching reading (for example) is so basic, then how about you try it?

I can tell you it involves a lot more than putting sight words up on the wall and setting spelling tests each Friday.

Thirdly, I find when most people talk about basic skills, they do so with very little knowledge of what is currently covered in the Australian Curriculum. ‘Literacy’ and ‘numeracy’ are very clearly listed as two of seven General Capabilities , alongside fields such as ‘critical and creative thinking’ and ‘ICT capability’. This reflects current ideas in education – that the ‘Three-Rs’ alone are not enough to provide a foundation for a productive and meaningful adult life.

Am I just being pedantic?

No, I don’t think so. The terms we use to describe ideas MATTER.

As an English teacher, I know this. I want so desperately for all my students to know this too.

By taking the term “basic skills” away, my students are forced to articulate what it is they actually believe in. If it is indeed literacy and numeracy I wanted them to be able to explain their definition of such terms.

Is it literacy? If so, they can use the wealth of available theory on literate practices and multiliteracies to argue their case.

Is it life skills? If so, the General Capabilities in the Australian Curriculum identify a 21st century set of ‘skills’. These currently underpin Australian schooling and should be explored and debated.

Is it the need for increased rates of adult literacy to promote social justice? If so, then it is time to explore  issues of Indigenous literacy  and global trends .

So what should you do, as one student recently asked, when people insist on using the term “basic skills”?

You could suggest they make a list of basic skills. Most people have no such list in mind (which begs the question – if the skills are so basic, why can’t most people articulate what they are?).

Good bye basic skills!

I know I can’t change the world overnight. But I do hope that by banning the term basic skills from assignments in my own class I can get 100+ students each semester to think deeply about what they might do in their classrooms as qualified Australian English teachers.

And I can tell you there is nothing basic about that.

Kelli

 

Dr Kelli McGraw is a lecturer in secondary English curriculum in the Faculty of Education at Queensland University of Technology. Her current research is on the role of social media technologies in engaging first year university students, and the use of online writing for assessment. Previously she worked as a teacher of high school English in South-western Sydney, NSW. Kelli is the Vice President of the English Teachers Association of Queensland. You can reach her via twitter: @kmcg2375