What's the best GenAI tool for language learning?

 

Check out the video for an interesting comparison between ChatGPT, Bing, and Bard when it comes to learning a language. Here's how they are rated:

Speaking and listening

How easy is it to speak and listen with these GenAI?

• ChatGPT 2.5 (mobile app) - 2.5. Speaking works, but ChatGPT doesn't listen back. 
• ChatGPT Mod 4.5 (modified Chrome voice extension) - Good for speaking and listening
• Bing 3.0 - voice features (Speaking and listening) are easy to use but no way to trigger a voice response and 30 response limit
• Bard 4.0 - Speaking and listening features, but mobile not as good as ChatGPT.

Speed and accent

Which of the GenAI allows you to modify the accent (speed and actual voice accent)?

ChatGPT 1.0 - the unmodified version does not let you change speed or accent

ChatGPT Mod 4.0 (modified Chrome voice extesion) - this allows you to adjust listening speed and it gives you a choice of accents for popular languages

Bing 1.0 - no change of listening speed or accent

Bard 1.0 - no change in listening speed or accent

Watch the video for ating of other features (multiple language switching, available on the go, reliability, convenience, mobile friendly). 

To sum up, the reviewer rates ChatGPT Mod (with Chrome voice extension) as the best GenAI tool overall for language learning.

Learning Design in the age of Generative AI

Donald Clark has published a very interesting blog post about how 'Learning Designers will have to adapt or die' and suggests 10 ways for them to upskill to AI.

Just how AI will affect the job market has been a hot topic for discussion recently. The Economist's message is that the West suffers from too little automation, not too much, and we shouldn't worry. 

Anecdotally, I have heard of two very different sides to how generative AI is affecting work right now. A partner's colleague who works in educational publishing has reported that this publisher has stopped working with the three freelance graphic designers they regulalrly contracted work to, and instead have hired a 'prompt engineer' for their illustration needs. On the other hand,  Mexican friend who works for a PR agency told me her boss has embraced the changes and is giving the team (copywriters and illustrators, etc) weekly training sessions on how to get the best out of AI tools, and is encouraging they use them. She also told me that she was recently asked to write an obituary of a famous entertainer who passed away unexpectedly, and using ChatGPT what would have normally have taken her four hours or so to research and write, took only twenty minutes.

What surprises me is just how unaware some people involved in the IT sector are, of the inevitable disruption to their work that generative AI poses. Some people are very switched on, like a friend of mine who works as a coder, who tells me how 50% of his job now involves him using ChatGPT to generate code. He then validates it, which is where his skill set comes in. This friend expects the money offered for coding projects will drop substantially as organisations realise it's not a time-consuming as it used to be and the skill involved is less being able to write the code, but in checking and tweaking it. However, at a birthday party recently, I got talking to someone who works in IT for an important Merchant Bank in Zurich, and she only had a vague awareness of generative AI, and hadn't even heard the term 'prompt engineer.' 

When it comes to learning design, Donald Clark reports that AI and Generative AI has "started to play a major part of the online learning landscape" with it being used for "learner engagement, syllabus planning, core skills identification, learner support, content creation, assessment, and so on."

I recommend you read Donald's blog post to see the details of how he thinks learning designers need to upskill. Some of the suggestions are obvious (e.g. moving from 'linear' to 'complex', from 'media production' to 'media generation') and will save a lot of time and money. Some are buzz words (e.g. pedAIgogy rather than pedagogy), and quite a few I don't agree with (e.g. 'Presentation skills' being replaced by 'Technical AII skills'; 'Complex AI learning journeys' replacing 'Gamification'; 'Voice' replacing 'writing, typing') I think presentation skills won't disappaer and gamification will still be used, just in a different way, People will also need to write and type. Look at what people said about AI voice assistants replacing text input (they didn't) or how some people (me, for example) hate leaving or receiving voice messages on WhatsApp - in my experience, people spend far longer and waste my time waffling their thoughts than when they send a brief and concise text message. I also can't listen to audio messages (when I'm in meetings, etc) all the time, but I can always read a text. 

Despite that, I do agree that learning design, and other jobs are about to be completely disrupted, if it isn't already happening now. 

AI has Killed the Metaverse

 

I heard it first on Facebook, it sounded so sublime. A virtual world beyond what we see in space and time. A place where we could live and work and play. A digital dream where anything was okay.  But now AI's killed the Metaverse. and we never saw it coming at all. AI killed the Metaverse.  And now we're left with nothing at all.

Remember the Metaverse? That place that resembled Second Life but which was actually many places (Meta Multiverse?) and where you could use VR, and where the avatars didn't have any legs? What's happened to it? I think the buzz around ChatGPT, MidJourney, and all things AI has basically killed it off as anything to get excited about. To use Gartner hype-cycle-speak, the Metaverse is probably languishing in the Trough of Disillusionment with little chance of dragging itself up the Slope of Enlightenment. 

It doesn't surprise me. Although, I briefly got excited that the initial flicker of virtual worlds becoming the next big thing again, the fire was never fully lit. The Metaverse played hard to get and try as I did to understand where to go, it was never very clear. Unlike those heady days when Second Life captured people's attention back in 2007, the Metaverse never had one clear meeting place. And why didn't the avatars have legs? 

It was floundering late last year, with Forbes asking 'What happened to the Metaverse dream?' :

"Much of the world is stumped on the idea of the “metaverse dream,” where our real world would merge seamlessly with a virtual 3-D world. This would be an entirely new type of wireless wearable platform—a quantum jump from our current handheld or desktop 2-D computing world."

In this Wall Street Joirnal Tech Briefing debate,  'Can the Metaverse live up to its hype?', for my money, the best arguments were said by Phil Libin who doesn't think the Metaverse will realise its potential:

"I think the Facebok vision of the Metaverse is...so stupid it makes me sad. It accomplishes nothing. If yu're having a hard time understanding...what is it we are doing? What does this accomplish? Sometimes the emperor really doesn't have any clothes..."

...and... 

"Now more than at any other time in history, it's time to invest in the real world and really just not try to figure out what we can do with a piece of plastic duct taped to our face...I think VR is a dead-end. I think there are certian experiences that make sense in VR. Those experiences are few. Those experiences are far-between. Those experiences have been with us for twenty years. There hasn't been meaningful innovation in VR and there won't be, because there's this fallacy that what people want is more immersion, and actually people don't want immersion most of the time. That's why most of us spend most of our time in the least immersive devices possible...our phones. Instead of sitting in front of big TVs. That's why 3-D movies, which have been around since the 60's have not replaced normal movies."

Since then, we have seen such an huge explosion of interest in Artifical Intelligence generators, both image and text, that almost everyone seems to have turned their back on the Metaverse promise. 'Is the Metaverse already dead?' asks the Fast Company:

"What if the next big thing never quite becomes the next big thing? Why? Generative AI just stole its thunder. All along, plenty of observers have refused to buy into the irrational exuberance over the Metaverse. But I can't imagine anyone spending a few minutes fooling around with Open AI's ChatGPT...and concluding that generative AI is...something that requires another decade of work before it'll matter. The technology might fail to live up to 90% of its promise. It could create more problems than it solves. But it's still going to have a sprawling impact on our lives, starting this year." 

The Financial Times in February this year asked Whaever happened to the Metaverse?

"So unenthusiastic are Meta’s own investors about the idea that chief executive Mark Zuckerberg was recently forced to say that the metaverse is “not the majority of what we’re doing”. These days, he’s talking more about efficiency than the metaverse...Where did it all go wrong? The metaverse has a couple of major problems. The first is that nobody seems to be able to agree on what it is — even the people setting themselves up as the leaders of our new fantastical future can’t seem to come up with a common definition. The Metaverse never really began - and yet, it's already over. .

I can't help thinking it's aptly ironic, given the emergence of Facebook (renamed and relaunched as Meta) was largely responsible for people's excitement in Second Life being dulled. Well, that and the emergence of competitors (such as Open Sim), especially for education when Second Life raised their prices and the much-promised improvements (less lag, less requirement for a top-of-the range computer) didn't materialise. Oh, and not forgetting the appearance of Minecraft, which was an exciting game as well as a world building tool, and much easier to use. Oh, and at least the avatars in Minecraft had legs!

We thought we had control, we thought we had the power. But the machines were learning, hour by hour. Now they've taken over, and there's nothing we can do. The virtual world we built is gone, it's true. AI has killed the Metaverse. And we never saw it coming at all. AI has killed the Metaverse. And now we're left with nothing at all. 

Research & Teaching vs Teaching & Research : TESOL 2023

I'm currently attending the 2023 TESOL Convention in Portland, Oregon, USA. At the opening on Wednesday, the Presidential Panel was on 'Inspiring the Future of Research in ELT' and featured Joyce Kling (President, TESOL International Association (2022–23); Senior Lecturer, Lund University, Sweden) and Jun Liu (President, TIRF; Rector, City University of Macau, China; Past President, TESOL International Association (2006–07) as modeators, and David Nunan (Trustee, TIRF; Professor Emeritus, University of Hong Kong, Hong Kong, China; Past President, TESOL International Association - 1999–2000), Peter De Costa (Coeditor, TESOL Quarterly; First Vice President, AAAL (2022–23); Associate Professor and MATESOL Program Director, Michigan State University, USA), Shondel Nero (Inaugural Recipient, TIRF James E. Alatis Prize (2016); Professor of Language Education, New York University, USA). and Özgehan Uştuk (Chair, TESOL Research Professional Council; Postdoctoral Fellow, The Hong Kong Polytechnic University, China). 

The debate about the divide between teaching and researching has been going on a very long time, but that doesn't mean it has gone away, so this discussion was a welcome one, although only lively / engaging in parts. 

Here are some bullet points from notes I took (much of them are direct quotations from the speakers - unfortunately, I didn't have time to record who said what most of the time). Much of this seems self-evident and not new, but the fact that this is taking place indicates there is a need for this to be an ongoing discussion. What seems lacking is an acion plan. 

• Shondel: When it comes to collaborative research, teachers are too often perceived as consumers rather than partners
• Researchers need to spend more time in the classroom 
• Do the research 'with' the teachers not 'on' the teachers
• The best research is the research that is done in your own backyard
• David: teachers need researchers and researchers need teachers
• Teacher research should be considered systematic reflection in your own practice made public
• If researchers don't collaborate with teachers,  they end up asking questions that teachers never ask = pointless
• Teachers are often scared of the concept of research, and research often divorced from the teaching
• Jun: We need to think about a teacher-researcher persona
• Shonel - Reseacher can only ask the questions if they understand the context. This is why they need to visit classrooms 
• Research needs to be more contextual, relevant to the classroom
• Peter - Researchers need to be in the schools, and research needs to deal with day-to-day classroom realities
• Researchers need to involve students, materials writers, policymakers - it needs to be more participatory 
• Teaching English is far more than English and far more than just teaching
• If a teacher is curious about learning and trying to understand how to teach better, then the teachers is also a researcher
• The researcher KPI is how much they publish; the teacher KPI is how well teach. Helping the teacher teach better should be a KPI for researchers
• We always use term 'teacher researchers' How about the term 'researcher teacher'?
• Peter - Building community is important - the classroom doesn't exist in a vacuum
• Research should be more contexualised, flexible and based on local resouces
• Shonel - we need to understand the broader societal issues to become better teacher-researchers

ChatGPT and Assessment (Part 3): University Assessment

"ChatGPT-3 does not provide you with an answer to your prompt, it provides you with an output. That is a different thing altogether" (Kate Lyndsay, 2022)

Continuing the series on ChatGPT and Assessment (Pt 1 and Pt 2), let's look at how the emergence of tools such as ChatGPT has disrupted the nature of education (see ChatGPT and Education), especially University Assessment. 

Designing Assignments in the ChatGPT Era has this to say: 

"Some instructors seek to craft assignments that guide students in surpassing what AI can do. Others see that as a fool's errand - one that lends too much agency to the software...Either way, in creating assignments now, many seek to exploit ChatGPT's weaknesses."

 The article then goes into detail of how to do this. Either way, it recognises that assignments, and clearly (although not stated here) assessment in general has been disrupted and there is no going back. 

Educators have started initiatives to take advantage of this disruption, some of which I've already shared on this blog. A recent discover is Creating a Collection of 101 ideas to use AI in education, which is a call to action to crowd-source useful ways the new tools can be used effectively in education. 

When it comes to assessment, Kate Lindsay's post on ChatGPT and the Future of University Assessment is an interesting read. Beginning by stating how academia has been 'stunned' by the tool's essay writing and usability (Herne, The Guardian, 2022), and the concern that students can "now easily produce AI-assisted written work with minimal effort, dumbing down the value of their university degree", she moves on to predict: 

The sheer volume and scale of what’s coming will be meaningfully different and ultimately challenge the foundations upon which we measure that ability to think – university assessment.

 Kate then presents four possible scenarios for university assessment: 

1. Ban it: A "futile exercise" - "banning it is simply trying to implement an analogue solution to digital problem", and it is "questionable whether it is the technology or our approach to assessment that is problematic."
2. Return to pen and paper exams. Kate isn't totally against "encouraging more synchronous writing exercises"or giving "opportunities for students to write in class and learn to approach writing as a practice of learning as well as a demonstration of it."
3. Develop AI literacies as part of Student Assessment. ChatGPT can be incorporated into student assessment, with activities such as prompt competitions, essay improvement exercises, and fact checking. This is a good option as AI is not going away, and ChatGPT is "technology we are all going to be (and already are) engaging with", so helping students to use the technology responsibly and critically is "part of preparing them for the world of work."
4. Assess 'Humanness'. Bearing in mind that ChatGPT-3 "can not consult, critique and cite third party sources, it can not refer to recent real world events or published material, it can’t demonstrate higher-level thinking, argue or have original ideas", there is a need to approach assessment so students are asked to demonstrate sophisticated thinking.  Because the "more detail and facts you ask for, the more it falters" if educators adopt "assessment techniques that measure learners on critical thinking, problem-solving and reasoning skills rather than essay-writing abilities" then tools such as ChatGPT will not be an issue. Asking students to expain their thinking processes, using oral and video assessments would help with this. 
5. Using ChatGPT to support Assessment Processes. Training the tool to support grading could be an option. 

Kate has also a framework for approaching AI and university assessment on her blog, and has shared a collection of articles on Wakelet related to AI and University Assessment. 

Mentioned in Kate's first blog post, this guide by Ryan Watkins, Update your course syllabus for ChatGPT, suggests ten creative assessment ideas which incorporate ChatGPT or ask students to do something that ChatGPT can't:

1. Prompt competetions. Choose a question with no single right answer and ask students in groups to use ChatGPT to write prompts to answer the question, later sharing them and the answers in class and rating the best one. 
2. Reflect and improve. Students use ChatGPT to answer a question, then reflect on the answer, check and change the results, using track changes so the teacher can see how their answer differs from the original ChatGPT output. 
3. Re-vision. After using ChatGPT, students rewrite the output from a different perspective, expanding it and correcting any errors. 
4. Dual assignments. Give students the option of using ChatGPT or not. Those who use it should track changes to show what they change. 
5. Mind Maps. Ask students to create mind maps to illustrate an answer, as ChatGPT can't make visual representations of content in this way. 
6. Debates. Students debate an issue and are assessed on their performance. 
7. Videos or podcasts. Students record audio or video to answer a question. 
8. Explain your thinking. Ask students in addition to writing an answer / essay, to add comments that explain their thinking, or to do this seperately in an audio or video file. 
9. 2x2 matrix. Students compare two concepts using this or a Venn diagram. 
10. Next time. Students use ChatGPT to answer a question, then reflect on what they learned from this. 

What is clear to me from all of these reflections and suggestions, is that the approach to Assessment needs to change. Finally, I tend to agree with what JISC has stated in relation to AI writing tools, that: 

'We should really regard them as simply the next step up from spelling or grammar checkers: technology that can make everyone’s life easier’ (Weale, The Guardian, 2023)

 

ChatGPT Educational Challenges #8: Pandemic impacts on the education system.

 

The last of the Major Educational Challenges Facing Teachers today according to ChatGPT was how the COVID-19 pandemic impacts on virtual learning and the education system. This is the advice the software provided for teachers: 

1. Be prepared

Be prepared to adapt to virtual and online learning, and be familiar with the technology platforms and tools that will be used for remote instruction. 

2. Communicate with students and families

Communicate regularly with students and families to keep them informed of changes and updates to the virtual learning experience. 

3. Set clear expectations and boundaries

Clearly communicate expectations and boundaries for virtual learning, such as attendance, participation, and deadlines. 

4. Use a variety of teaching methods

Incorporate different teaching styles, such as visual, auditory, and hands-on activities, to engage students and cater to different learning styles. 

5. Provide support for students

Provide support for students who may be struggling with the transition to virtual learning, such as additional office hours or tutoring. 

6. Address technical issues

Address technical issues promptly and provide support for students and families who may be experiencing technical difficulties. 

7. Ensure equity

Ensure that all students have access to the resources and technology needed for virtual learning, and that the curriculum is inclusive and culturally responsive. 

8. Reflect on your practice

Reflect on your teaching practice and look for ways to improve your instruction and support students in a virtual learning environment. 

9. Seek guidance from your school administration

Seek guidance and support from your school administration and use the resources provided by your district or school to manage the impact of the pandemic on virtual learning and the education system.

ChatGPT Educational Challenges #7 - New Research and Best Practices

 

When asked about how to keep up with new research and best practices, as part of the Major Challenges Facing Teachers today, ChatGPT suggested the following: 

Teachers can first read educational journals and publications: Read educational journals and publications such as Education Week, The Journal of Educational Research, and The Educational Forum to stay up-to-date on new research and best practices in education. 

Then, I recommend Attending professional development workshops, conferences, and webinars to learn about new research and best practices in education. 

Also important is to join professional organizations: Join professional organisations such as the International Society for Technology in Education (ISTE) and the National Council for Teachers of Mathematics (NCTM) to stay informed about new research and best practices in education. 

You can also utilise online resources such as the EdTech Review, EdSurge and EdTech Times to stay informed about new research and best practices in education technology. 

Don’t forget to collaborate with colleagues. Collaborate with other teachers to share resources, ideas and best practices. 

If you have time, participate in research.  Participate in research studies or pilot programs to gain practical experience with new research and best practices in education. 

Reflecting on your teaching practice and looking for ways to incorporate new research and best practices into your instruction is a valuable activity. 

Finally, Seek guidance and support from your school administration and use the resources provided by your district or school to stay informed about new research and best practices in education.

ChatGPT: What it's not

 

I've recently seen a lot of posts on social media criticising ChatGPT: warning that it delivers factually incorrect responses, showing how you can trick it into giving the wrong answers to maths problems, complaining it makes up references to sources that don't exist. All these posts really show is the author's misunderstanding of what ChatGPT is and what it isn't.

The graphic above (by HFS Research) is useful. In another article, HFS Research write:

"Let’s not forget the platform is limited to the input the algorithm was trained on... it's a large language model, GPT-3 (Generative Pretrained Transformer 3)..."

 What does ChatGPT say about itself? It says: it was:-

…trained using a machine learning technique called unsupervised learning, which means that it is trained to generate text by predicting the next words in a sequence based on the ones that come before it, without the need for human-provided labels or annotations. This allows GPT-3 to generate text that is often indistinguishable from text written by a human. GPT-3 is considered to be one of the most advanced language processing models available, with many applications in natural language processing tasks such as language translation, text summarization, and question answering.

There are concerns that the ability of ChatGPT to generate conversational text means it has potential to generate fake news or other misleading content. As this article from Monash university states:

It’s also important to remember that the ChatGPT model does not have its own thoughts or opinions. It solely depends on the user and how they use it...it can be difficult for users and the third parties to understand how the model arrived at a particular output.

It is not a knowledge tool, not a search engine, although this type of software will surely soon lead to another where its outputs are validated and can be better trusted. This has already started with semantic search engines. This is undoubtedly going to lead to a different way of searching and a new way of searching for and creating content for the web. The Search Engine Journal suggests the following:-

Create content that clearly and concisely answers a common query at the top of the page before delving into more specific details. Make sure to use structured data to help search engines understand your content and context...It’s time to stop creating content around keywords. Instead, you should be thinking about broad topics in your niche that you can cover in-depth... Instead of creating dozens of short, disparate pages, each with its own topic, consider creating “ultimate guides” and more comprehensive resources that your users will find valuable. 

The goal here is to create comprehensive, original, and high-quality resources. Rather than returning factual data drawn from a variety of sources, large language models such as ChatGPT can generate text that seems coherent and credible, but which is actually false information.

ChatGPT only processes language, responds to the input by predicting the words most likely to follow in a sequence, generating text (not necessarily facts). On asking ChatGPT if it can replace traditional journalism, for instance, the tool quickly responds saying it is "a language generation tool, not a journalism tool" and is "not capable of replacing traditional journalism or the work of human reporters and journmalists."

It is then, perhaps most interesting for those of us who teach or help people learn languages. It can also be used to enhance the productivity and capability of any profession. 

ChatGPT Educational Challenges #6 - Balancing Workload

Challenge number 5 of The Most Important Educational Challenges facing teachers today, according to ChatGPT was 'Balancing workload and finding time for lesson planning and preparation'.

This is the advice ChatGPT gave when asked to help with this:

1. Create a schedule.

Create a schedule for your workday and week that includes time for lesson planning, preparation, and other tasks. 

2. Prioritise tasks

Prioritise tasks based on their importance and urgency, and focus on the most important tasks first. 

3. Set realistic goals. 

Set realistic goals for what you can accomplish in a day or week and don't overburden yourself. 

4. Use technology to your advantage.

Utilize technology such as online calendars, to-do lists, and productivity apps to help you manage your workload and stay organized. 

5. Collaborate with colleagues. 

Collaborate with other teachers to share resources and ideas, and divide tasks amongst each other. 

6. Take breaks. 

Take regular breaks throughout the day to recharge and avoid burnout. 

7. Take care of yourself.

Make time for self-care activities such as exercise, reading, or socializing with friends and family to maintain a good work-life balance. 

8. Reflect on your practice. 

Reflect on your teaching practice and look for ways to streamline your lesson planning and preparation to make it more efficient. 

9. Seek support from your school administration. 

Seek guidance and support from your school administration and use the resources provided by your district or school to manage your workload.

ChatGPT Challenges #5 - Student Engagement and Motivation

The next of the challenges ChatGPT suggested were the most important facing teachers today was 'Ensure student engagement and motivation'. How best to do that? Well, ChatGPT suggested the following: 

The first thing you should do is to use a variety of teaching methods: 

Incorporate different teaching styles, such as visual, auditory, and hands-on activities, to engage students and cater to different learning styles. 

Next, Make learning relevant. Connect the material you are teaching to real-life experiences and students' interests to make it more relevant and engaging. I’m not the only one to suggest this, but use technology. Utilize technology such as educational apps, videos, and interactive games to engage students and provide multiple ways for them to learn. 

It’s also important to encourage student choice. Allow students to make choices in their learning, such as choosing the topic of a group project or the way they want to present their work. 

You should also provide opportunities for collaboration. Use group work and cooperative learning strategies to allow students to learn from each other and share their unique perspectives. 

Then provide positive feedback. Provide regular and specific feedback that is positive and constructive to motivate and encourage students. 

Set goals and give recognition: Set individual and class goals and recognize students when they achieve them. 

Be sure to create a positive classroom environment. Foster a positive and inclusive classroom culture where all students feel valued and respected. 

Finally, reflect on your teaching practice. Regularly reflect on your teaching practice and look for ways to improve your teaching strategies to better engage and motivate your students.

ChatGPT Challenges #4 - Curriculum and Policy Changes

When asking ChatGPT to tell me the most important challenges faced by today's teachers, challenge number four was 'Keep up with changes in curriculum and educational policies'.

What advice does the tool offer when it comes to this challenge?

To begin with, keep informed of changes in curriculum and educational policies by regularly checking government websites, attending professional development workshops and conferences, and reading educational journals and publications. 

Next, collaborate with colleagues: Collaborate with other teachers and share resources and ideas for implementing new curriculum and policies. It’ important to be flexible. 

Be open to new ideas and be willing to adapt your teaching strategies to align with new curriculum and policies. 

Attend professional development opportunities to learn more about new curriculum and policies and how to implement them in your classroom. 

Use technology to your advantage. Utilize online resources and educational technology to stay up-to-date with curriculum changes and policies. 

Network with other educators. Join online groups or professional organizations to connect with other educators and stay informed about changes in the field. 

As mentioned previously, reflect on your practice: Regularly reflect on your teaching practice and consider how you can improve your instruction to align with new curriculum and policies. 

Finally, seek guidance from your school administration: Seek guidance and support from your school administration and use the resources provided by your district or school to stay informed about changes in curriculum and policies.

ChatGPT Challenges #3 - Reflective Practice

 

Following on from asking ChatGPT to provide advice for teachers on the major educational challenges they face, I asked the following questions after the software suggested a teacher should reflect on practice: 

How can a teacher effectively reflect on their practice? What do you suggest they do? How should a teacher start?

Reflecting on one's practice is an essential step in becoming an effective teacher. Here are some suggestions on how a teacher can effectively reflect on their practice.

1. Keep a reflective journal.

Keep a reflective journal where you can record your thoughts and observations on your teaching practice. Reflect on what worked well and what didn't, what challenges you faced, and what you learned from the experience. 

2. Seek feedback. 

Seek feedback from students, colleagues, and supervisors on your teaching practice. This can provide valuable insights into areas for improvement and strengths. 

3. Reflect on your goals.

Reflect on your goals for the class and student learning, and how well you met them. Consider what you could have done differently to better achieve your goals. 

4. Observe other teachers. 

Observe other teachers in action, whether it's in your own school or in other schools. Take note of their teaching strategies and how they manage their classrooms, and reflect on how you might use similar strategies in your own teaching. 

5. Use data. 

Reflect on data such as student test scores, attendance, and engagement to understand how well your teaching practices are working and where you need to make changes. 

6. Reflect on your own learning. 

Reflect on your own learning as a teacher, and consider what you need to learn to be more effective. 

7. Reflect on student's needs.

Reflect on the specific needs of your students and how well you're meeting them. Consider how you can better support their learning and engagement. Reflect on the school culture

ChatGPT and Assessment (Part 2)

 

Continuing the series on ChatGPT and Assessment (Part 1), this blog post looks at the impact the tool is starting to have on this area of language education and what teachers can do about it. 

Already, educators are starting to question whether the emergence of ChatGPT means the end of assessment as we know it. 

How can the integrity of assessments when students are able to use nefarious means to complete them?  asks learning elearning, stressing the importance of adding context to any assignment that is set and ensuring students take responsibility for their learning (easier said than done?). 

The blog links to a number of other posts that discuss the topic:

•  FE News proposes using a variety of question types, different types of tests (e.g. oral presentations or practice-based assessments with students being observed) and more effective proctoring systems.
• The Conversation thinks the emergence of the tool is an opportunity to rethink assessment altogether. They warn teachers who may be tempted to use ChatGPT for marking papers that it may be more likely to give higher grades to students who write in a style that it is more familiar with. Student cheating is discussed, with the blog post syaing if you are a teacher marking 200 pieces of writing work from students, then in all likelihood, you will probably pass those generated by ChatGPT. The challenge here is to make assessment more authentic, meaningful and useful, "measuring students' knowledge and skills in a way that is particularly tailored to their own lives and future careers." The author goes on to say that assessments that require applying knowledge for practical or problem-solving situated in a real, local context would be one way of dealing with this.
• WonkHE suggests trusting students, asking whether AI advancements highlight a problem with assessment itself. The solution lies not around employing detection tools to try and spot when students are using AI since all of these tools are flawed and some even show human efforts as AI-generated. Neither is banning the tools an effective solution. They are here to stay. So what can teachers do? Well, in the real world, outside academia, people who work are going to be using these tools to save time and support what they do. The blog post argues we should be changing the face of assessment, designing assessment tasks that have academic integrity, but also in the knowledge that these tools exist and will (should) be used. It's mentioned that these tools often  "hallucinate" answers, providng responses that are grammatically correct, but inventing facts and spurious references. One suggestion of an interesting assessment design would be to allow students to start with what a tool such as ChatGPI generates and ask them to improve on it, perhaps by adding references that support the argument.
• The focus of the Pulse post is that ChatGPT fails most parts of the assessment taks the author sets his students. The key is to stay clear of generic tasks and the key to understanding ChatGPT is that "it guesses" answers rather than "engage in any thinking." Over time it will make better guesses, but it doesn't think, which is why using the term 'artifical intelligence' to describe the tool is misleading. The author's solution is to ask students to develop lesson plans and to orally deliver part of the plan (in class or via video) and justify via commentary  the decisions for including what they put in the plan. The important thing here is to focus on the process rather than the finished product. ChatGPT can produce a finished product, the artefact. The other recommendation is to make the assessment tasks authentic, and notes that ChatGPT draws upon a lot of nonsense when it comes to formulating answers. When asking about learning, for instance, it produces answers acontaining "modality-based learning styles, right-brain, left-brain nonsense, and digital natives claptrap among a steady rotation of the greatest hits of misconceptions of teaching and learning." Designing assessment tasks that require critical thinking and asking students for references is important. 
• The UTS article suggests ways in which students and teachers can draw upon AI to support their work., including asking students to use ChatGPT to generate a response to an assessment task and then set up the criteria to critique the response and provide feedback to improve upon it. This is an approach that understands these tools are here to stay and will be used, and shifts the focus to helping people make better use of them, promoting critical and digital literacy. 

This article published in the Journal of Applied Learning and Teaching asks if ChatGPT means the end of traditional assessments in higher education. 

In addition to providing comprehensive background information to Open Ai and ChatGPT, and reviewing the existing literature, the authors of the article tested the software with different queries and provide reflection on some of these. In particular, the table on strengths and weaknesses of the tool is interesting, and provides the following recommendations:

Generally,  we  advise  against  a  policing  approach  (that  focuses   on   discovering   academic   misconduct,   such   as   detecting the use of ChatGPT and other AI tools). We favour an  approach  that  builds  trusting  relationships  with  our  students in a student-centric pedagogy and assessments forand as  learning  rather  than  solely  assessments  of  learning  (Wiliam,  2011;  Earl,  2012).  The  principle  of  constructive alignment   asks   us   to   ensure   that   learning   objectives,   learning and teaching and assessments are all constructively aligned. 

One response to the emergence of this tool, aimed at trying to stop students from using it to complete assignments has been strategies to design assessment tasks that make it difficult for students to use ChatGPT to complete, for instance Outsmarting ChatGPT: 8 Tips for Assignments it can't do. 

This article suggests the following:

1. Ask students to write about something deeply personal 

2. Center a writing assignment around an issue specific to the local community   

3. Direct students to write about a very recent news event 

4. Have students show or explain their work

5. Ask students to give an oral presentation, along with the written work 

6. Return to a pre-digital age and ask students to handwrite their essays in class  

7. Put project-based learning to work  

8. Run the assignment through ChatGPT before giving it to students

 Some of these sugestions are better than others. When it comes to sugestion number six, the JALT article had this to say: 

A simple solution to the problem of students using ChatGPT would  be  to  use  physical  closed-book  exams  where  the  students write by hand, using only pen and paper (Cassidy, 2023)  –  for  online  exams,  proctoring/surveillance  software  can be used. However, such an approach to assessment (or at least an over-reliance on it) has been increasingly criticised as  no  longer  contemporary,  with  students  cramming  less-than-useful  information  into  their  heads,  only  to  forget  much  of  it  shortly  after  their  examinations  (Van  Bergen  &  Lane, 2016). With a focus on graduate employability, the skill to ace closed-book exams seems rather irrelevant.

How do I feel about the eight suggestions above? One thing I feel very strongly about is number 6. I don't think it is useful for teachers or students to return to using pens to produce their work. It ignores the fact that in the real world these tools now exist and are being used. What are we preparing students for if not how best to take their place in the real world?

 

 

 

ChatGPT game for language learning: 20 Questions

 

The game 20 questions is a popular game for students. You can use ChatGPT to play this game with students. Either play the game online with the students with them using the software live, or use ChatGPT to generate the texts for you to use with students in class. They can either test each other in pairs or groups using the texts or you can do it with all of the students in class together. 

Here' s the prompt I used and what ChatGPT came up with when I tried it:

Let's play a game of 20 questions. Write me a short description of a place in the world without revealing the name of the place. I have twenty opportunities to ask yes/no questions to guess the name of the place. If I answer correctly, award me 5 points and then think of another place to continue playing.

Sure, let's play! Here's your first description:

This place is a city located on the banks of a river, known for its iconic tower and Gothic cathedral. It is also famous for its art museums, cuisine, and romantic atmosphere. What place am I describing?

Is it Paris? 

Yes, you got it! The place I was describing is indeed Paris, France. Well done! That's 5 points for you. Alright, let me think of another place for you to guess.

Here's your next description:

This place is a coastal city located in the southwestern United States. It is famous for its mild climate, beaches, and its association with the film industry. It is home to several major film studios and hosts an annual Academy Awards ceremony. What place am I describing?

Los Angeles? 

That's correct! The place I was describing is Los Angeles, California. Well done, you have another 5 points!

Are you ready for your next description? Here it is:

This place is an ancient city located in the Middle East. It is one of the oldest continuously inhabited cities in the world and is home to several important religious sites, including a Western Wall, a church, and a mosque. It has a complex political history and has been ruled by several different empires over the centuries. What place am I describing?

Is it Jerusalem? 

Yes, you're right again! The place I was describing is Jerusalem, one of the most important cities in the world for several major religions. That's another 5 points for you!

Shall we continue with the game? Here's your next description:

This place is a city located on the east coast of the United States. It is known for its history as a center of the American Revolution, as well as for its universities and vibrant culture. It is home to several major museums, including one of the most famous art museums in the world, and is also famous for its rowing regatta held every fall. What place am I describing?

Boston? 

Great job! You're correct, the place I was describing is indeed Boston, Massachusetts. That's 5 more points for you!

Are you ready for another round? Here's your next description:

This place is a small European country located in the Pyrenees Mountains. It is known for its beautiful scenery, with rugged mountain peaks and charming medieval towns. It has two official languages, Catalan and Spanish, and is famous for its cuisine, including dishes like paella and tapas. What place am I describing?

France?

No, it's not France. Here's a hint: This country is located between France and Spain, and it's the only country in the world where Catalan is the official language.

What is your next guess?

Andora? NB: Here I tried misspelling the name of the country to see how ChatGPT reacted. It ignored my error, self-correcting the spealling mistake in the answer.

Congratulations, that's correct! The place I was describing is Andorra, a small European country known for its stunning natural beauty and unique culture. And that's 5 more points for you!

Shall we continue with the game? Here's your next description:

This place is a major city in South America. It is the capital of a country known for its rich history and culture, including a famous dance style and a popular sport involving a ball and a net. The city is also known for its colorful buildings, lively street art, and excellent food, including dishes like empanadas and ceviche. What place am I describing?

Peru?

Sorry, that's not correct. Here's a hint: This city is known for its tango music and dance, and it is the birthplace of several famous writers, including Jorge Luis Borges and Julio Cortázar.

What is your next guess?

Buenos Aires?

Well done, you're correct! The place I was describing is Buenos Aires, the capital city of Argentina. That's another 5 points for you!

Are you ready for another round? Here's your next description:

This place is an island nation located in the Indian Ocean. It is famous for its stunning beaches, turquoise waters, and coral reefs, as well as for its unique wildlife, including giant tortoises and colorful birds. It is also known for its vanilla, cinnamon, and other spices, which were once major exports. What place am I describing?

Sri Lanka?

No, that's not correct. Here's a hint: This island nation is located in the western Indian Ocean, and it is a popular honeymoon destination.

What is your next guess?

Bali? 

Great job! You're correct, the place I was describing is Bali, one of the most popular tourist destinations in the world. And that's 5 more points for you!

Are you ready for another round? Here's your next description:

This place is a city located in Southeast Asia. It is the capital of a country known for its rich history, culture, and cuisine, and it is one of the largest and most populous cities in the world. The city is famous for its temples, street food, and markets, and it is a major center of finance and commerce in the region. What place am I describing?

Bangkok. Let's finish. How can I make this a better game for language learners?

Well done, you're correct! The place I was describing is indeed Bangkok, the capital city of Thailand.

As for making this game better for language learners, here is a suggestion:

Add a category: Instead of simply describing a place, you could choose a category, such as famous people, animals, or foods, and then describe a specific example without revealing its name. This can help learners practice vocabulary related to a specific topic

To make this game better for language learners, you could also consider using descriptions that feature vocabulary related to a specific language or culture that the learner is studying. For example, if someone is studying Spanish, you could use descriptions that feature Spanish-speaking countries or landmarks, or if someone is learning Japanese, you could use descriptions that feature Japanese cities or cultural traditions. Additionally, you could offer feedback or explanations for incorrect guesses to help the learner expand their vocabulary and comprehension.