Adventures in Technology Enhanced Learning @ UoP

Tag: experience (Page 1 of 3)

Guest Blogger: Tom Langston – How ChatGPT Revolutionized My Writing Process – The AI version

(Co-writer: ChatGPT)

This version was generated after feeding in my attempt at writing this blog post and asking ChatGPT to ‘shorten this text into a blog post’.

I recently discovered the incredible potential of ChatGPT, and it completely revolutionized the way I approached my writing. As a student pursuing a Professional Doctorate in Education, I often struggled with crafting cohesive and focused assignments. My writing style was scattered and verbose, making it difficult for readers to follow my train of thought. Enter ChatGPT, a powerful AI language model that became my secret weapon in developing a well-structured research proposal.

Initially, I sought human help from my project supervisor, Stephen Webb, who pointed out that my writing relied too heavily on vague terms like “this” and “it.” While I understood the meaning behind my words, Stephen reminded me that readers might not share the same clarity. Armed with his feedback, I set out to improve my proposal.

When I completed the next draft, I thought I was finished. However, the word count was far too high, so I turned to ChatGPT for assistance in condensing my writing. It did the job, but the result lacked my personal touch and voice as a writer. I realized I would have to manually trim down the content to achieve the desired outcome.

During this editing process, I discovered the true power of ChatGPT. I started using it to check sentences that I struggled to articulate clearly. When I asked for grammar assistance, ChatGPT not only provided corrections but also suggested ways to enhance sentence structure and improve readability. This iterative process allowed me to refine my writing, discarding extraneous thoughts and rearranging sentences for better flow. It became evident that if a particular text no longer fit within the new leaner version, despite my attachment to it, it had to be eliminated. This experience epitomized the essence of editing.

As I continued to utilize ChatGPT, I encountered questions of ethics. While it proved immensely useful in reducing my word count, I couldn’t help but feel uneasy about presenting the AI-generated content as my own. The ethical implications of using AI in writing remain a divisive topic, with differing perspectives on its appropriateness and boundaries. To navigate this issue, some suggest referencing AI tools in an appendix, detailing their specific use and purpose in the writing process. However, this raises questions about the extent to which we should acknowledge AI contributions and how that compares to other forms of assistance, such as spell checkers or language tools like Grammarly.

One important consideration is whether AI tools are always correct. While they excel at constructing language, they may strip away the author’s voice and inadvertently introduce errors. In my experience, Grammarly sometimes made corrections to the text generated by ChatGPT, highlighting the need for human judgment in refining the output.

In conclusion, ChatGPT became a game-changer for me, transforming my writing process in ways I had never imagined. I believe it should be embraced as a valuable resource for students to tighten their drafts before seeking extensive academic support. By incorporating AI tools, we can alleviate the burden on educators, who can then focus on reviewing more polished submissions requiring minimal intervention. However, it is crucial to strike a balance and ensure that AI enhances our own voices rather than overshadowing them. AI is undoubtedly here to stay, and by harnessing its power thoughtfully, we can elevate our writing while preserving our unique identities as authors.

Thoughts from the Proofreader:

I was asked to proofread Tom’s blog post here and have a look at ChatGPT’s version too. Comparing the two, I definitely found Tom’s writing much more personable – I could imagine him speaking as I read through it. ChatGPT’s version presented the information efficiently and effectively, and I found nothing to correct. However, in its response to the prompt, it had taken away everything that made Tom sound like Tom!

This experience also really made me realise how many misconceptions I have about AI tools. I’d assumed that ChatGPT would have a very grammatical approach to its interpretation of language – rather like I’ve been told I have! However, when Tom asked it about the difference between ‘that allowed’ and ‘allowing’, ChatGPT talked with authority about implications and potential meanings. This answer was a long way from my interpretation, which attributed the difference to the grammar of relative clauses (X refers to one thing, Y refers to another). As Tom demonstrated with his irony example, it’s worth being cautious with how far we trust its responses. And I think we can be confident that human input will still be needed for a few years (or at least months) yet. 

Credit Image: Photo by Bram Naus on Unsplash

Guest Blogger: Tom Langston – Last Night ChatGPT Saved My Life…

The classic line from Indeep’s 1982 post-disco hit “Last Night a DJ Saved My Life” serves as the basis of my title. As ChatGPT did – not literally, but figuratively – save my life.

I am currently studying for the university’s Professional Doctorate in Education and, since February, have been completing my final taught assignment entitled “Research Proposal”.

It takes me a while to write, as I don’t find it easy, and I am not that good at it. My approach to writing is best described as little and often, frequently getting distracted and losing focus on the task at hand. If you have ever seen Dave Gorman’s “Googlewhack Adventure”, you will understand my problem: his book and stage show outlined how he was meant to write a fictional novel and ended up writing and performing about his experiences of Googlewhacks (Googlewhacking?) instead. He got distracted by less important but much more fun endeavours. 

The other problem is that I don’t get to the point. I write a verbose mess of unconnected thoughts. So with that in mind, I am going to explain how the rise of the machines (we are not far away from ChatGPT working out it wants to be Skynet) assisted me in writing my “research proposal” assignment. 

First Drafts

To start with, I had human help. Stephen Webb, as my project supervisor, read a draft I had written. He demonstrated that a lot of my writing relied on small words to, as he put it “do the heavy lifting”. Using ‘this…’ and ‘it…’ frequently because I understood what I was trying to say –  he pointed out that the reader might not. The only reason he could even start to understand my work was because he knew me and the context of my subject. 

From his extensive feedback, I redrafted, edited and tried to improve my proposal. 

After completing the next draft, I thought I’m done. However, I was well over the word count, so I put sections into ChatGPT and told it to re-write it within my word limit. It only bloomin’ did it! The problem was it was very sterile; it lost all sense of who I am as a writer. This meant I was going to have to manually get the word count down. 

After another version, I asked Stephen for some clarification on some of his earlier feedback. His reply was:

“In the section you sent through, there are still individual sentences that are hard to parse. The initial word of a sentence or clause primes the reader to think in a certain way; if the sentence or clause doesn’t deliver, then confusion arises. You really should pass this through a grammar checker, Tom.”

Not being a confident writer, I already knew that my writing needed work. What this feedback demonstrated to me was that I lacked cohesion and structure. My train of thought constantly jumping around the entire document is a by-product, I guess, of writing in such short unfocussed bursts. 

I wrote a heading titled “Introduction” but did not actually introduce anything. As Stephen had pointed out, I had poorly communicated my narrative. What this meant was that readers were getting lost in my disconnected thoughts. I could now see that certain sections felt shoe-horned in because I liked what I had written. Realistically, those “gems” made no sense to the reader as they were not connected with the text surrounding them. 

I tried to use ChatGPT to see if it could make sense of it, but there was too much there for it to tell me how to rearrange it. The system did not accept the entirety of the text and could not provide clarity to the sections I had written. ChatGPT could not offer clear guidance for how best to rework and rearrange it.

A Quick Aside

At this point, on re-reading the above section, I think it nicely illustrates the problem I was talking about. I have said the same thing here in three different ways. 

  1. I tried to use ChatGPT to see if it could make sense of it, but there was too much there for it to tell me how to rearrange it. 
  2. The system did not accept the entirety of the text and could not provide clarity to the sections I had written. 
  3. ChatGPT could not offer clear guidance for how best to rework and rearrange it.

I only need to use one. In the past, Stephen had raised this issue with me, but it is a hard thing to change. What I am going to discuss next is my recent experiences of using ChatGPT as a tool to develop the parts in my writing I would not have picked up on myself. Heck, as I go back through this blog, I’m sure I’ll find more. I just won’t mention anything I’ve changed, so you’ll never know… 

Editing with ChatGPT

As I worked my way through the editing process, I started to use ChatGPT to check sentences I wanted to keep but was struggling to make coherent. They were either too long, or the idea I was trying to convey was not coming through clearly enough. 

An example of this would be when I asked ChatGPT to “check the grammar”:

My original question:

My situation should be made clear to the participants, allowing them to have fully informed consent, but to also highlight that if they perceive issues in the current hybrid environments I am hoping to act on their concerns and not silence their voices.

ChatGPTs reply:

The grammar of the provided text is correct. However, there are a few suggestions for improving clarity and readability:

“My situation should be made clear to the participants, enabling them to provide fully informed consent. Moreover, it is important to emphasise that if they perceive any issues in the current hybrid environments, I am committed to addressing their concerns and not silencing their voices.”

In this revised version, I made a few adjustments to enhance the sentence structure and clarify the message.

It was this repeated process that helped me (despite, at times, slowing me down) as I kept re-reading the submission each time, trying to tighten up my writing. Finding new thoughts that were slightly out and attempting to move them to the correct place. It became a good rule of thumb that, if the text I wrote did not fit in the new, leaner version, despite how much I wanted to keep it, it was gone. (Well done Tom – you just discovered the true meaning of editing!)

Below is an example of how I started to use ChatGPT to my advantage so I could improve my writing. 

My question to ChatGPT:

Should it be “that allowed” or “allowing” in the following text – 

Before the pandemic only the most confident teaching staff employed interactive tools (Nearpod, Mentimeter, etc.) within a lecture space that allowed students the ability to creatively engage with the material (Tan et al., 2020).

ChatGPTs reply:

Both “that allowed” and “allowing” are grammatically correct in the given sentence. However, the choice between them depends on the intended meaning and emphasis.

“That allowed”

Using “that allowed” suggests that the interactive tools were specifically designed or configured in a way that granted students the ability to creatively engage with the material. It implies that the tools had a built-in functionality or feature enabling such engagement.

“Allowing”

Using “allowing” suggests that the interactive tools, in a general sense, provided the opportunity or capability for students to creatively engage with the material. It implies that the tools had the potential or capacity to facilitate such engagement.

Both options are valid, but if you want to emphasize that the interactive tools had a specific functionality designed to enable creative engagement, “that allowed” would be more suitable. If you want to convey a more general sense of opportunity or capability, “allowing” would be a better choice.

As you can see, ChatGPT helped to explain how the slight difference in the sentence structure changed the meaning of what I was writing. I was able to consider what it was I’m trying to say and use the most appropriate version. 

Through all my previous doctoral assignments, I had a different tutor who helped me with my drafts. They told me they liked my writing style, which gave me the impression I was good at it. I can’t say what they specifically liked about my writing. I can make an educated guess that, because it was a level 8 assessment, my mistakes were forgiven. The marker was able to interpret the little words “that are doing the heavy lifting” (as Stephen had pointed out) more easily than your ‘average’ reader. Stephen helped me understand that it is one thing to have an interesting voice running through your text but is quite something else to actually be good at writing. 

The ethics of using AI

When I got ChatGPT to reduce my word count, I spoke with Stephen about the ethics of it and (ignoring the sanitisation of the output) it felt like a great way for a writer to do this. However, it felt wrong to take what ChatGPT had created as my own.

There is going to be an ethical divide between those who see using any form of AI as wrong and those who see it as a tool for improvement. The problem (as always) lies in the grey area and the boundaries of where people choose to deploy it, for example how far the tool is shaping their work beyond what would have been possible by them alone. While knowing it might be unethical, some will use it due to other commitments (work, family, etc). This scenario is a foreseeable eventuality, much like those who copied other work or paid essay mills for their work. But perhaps AI may feel slightly more ethical? As I am about to discuss, maybe a strong referencing code is what is required. But people (I was going to put students, but felt that unfair as we all have a personal line we move and adjust depending on the subject) will always push and flex the boundaries of fairness.

Referencing AI

In a recent ALT mailing list post, the question was asked about referencing when AI was used to  support work. The reply pointed to Boston University’s faculty of computing and data science guidance “Using generative AI in coursework”. The post highlighted this text:

“When using AI tools on assignments, add an appendix showing

(a) the entire exchange, highlighting the most relevant sections;

(b) a description of precisely which AI tools were used (e.g. ChatGPT private subscription version or DALL-E free version),

(c) an explanation of how the AI tools were used (e.g. to generate ideas, turns of phrase, elements of text, long stretches of text, lines of argument, pieces of evidence, maps of conceptual territory, illustrations of key concepts, etc.);

(d) an account of why AI tools were used (e.g. to save time, to surmount writer’s block, to stimulate thinking, to handle mounting stress, to clarify prose, to translate text, to experiment for fun, etc.).”

This almost feels as if there are too many barriers to use for a subject (or level) where you may be writing assignments of 6000+ words. Especially if you have to reference every section of text AI helped with. The follow-up question is then do you have to highlight every time spellcheck made a correction? Do you have to disclose that you used a service like Grammarly to make minor amendments? That is of course hyperbole. I think that if you get AI to generate starting paragraphs or change substantial amounts of your work, yes, this should be explained in an appendix. For re-writing a sentence and making grammatical choices, then no. That raises another question, how many sentences constitute a substantive change? 

Are AI tools always correct?

The final point relates to whether they are always correct. Now I know these tools are better than me at the construction of language. I have always been better at face-to-face conversations as a form of communication. During a conversation I can see when people don’t understand me, so adapt how and what I say accordingly. Writing does not afford the writer or reader the same luxury. So why do I ask if they are correct? As I have already mentioned, ChatGPT sterilised my voice. When asked to reduce the word count, it did what it was supposed to do but it strips out the humanity of the author (unsurprising being that it is a computer).

Another example (inside a paragraph that starts “The final point”, I do get the irony) is that Grammarly made corrections to the generated text from ChatGPT. 

This is a screenshot of a reply from ChatGPT placed within a box saying 'Both "that allowed" and "allowing" are grammatically correct in the given sentence. This box appears on the lefthand side of the screen on the righthand side is a box created by Grammarly. Grammarly has written Formality, then says to engage with the material creatively. The to-infinitive to engage has been split by the modifier creatively. Avoiding split infinitives can help your writing sounds more formal.
Another “another example” of a final point is: I put the above paragraph into ChatGPT to ask if I had used irony correctly. This is what it said:

Yes, the use of the word “irony” in this context is correct. Irony is a literary device that involves a contrast between expectations and reality. In your statement, you are highlighting the irony in two situations:

The first example of irony is that despite recognizing that language generation tools like ChatGPT are better than you at constructing language, you also acknowledge that you excel at face-to-face conversations where you can adapt and clarify your communication based on people’s reactions. The irony lies in the contrast between the effectiveness of these tools in writing and your personal strength in face-to-face communication.

The second example of irony is that Grammarly, a tool designed to enhance writing and make corrections, ends up making corrections to the text generated by ChatGPT. Here, the irony arises from the fact that a tool meant to improve the quality of the text is itself making changes to the output of another tool that is supposed to assist in generating text.

Overall, both examples demonstrate a contrast between expectations and reality, highlighting the ironic situations in your statement.

The system had not understood how I had used irony in the sentence but said that the overarching point I was making was ironic.

This image is of a person standing, with their eyes focusing as if they're looking at someone else who might be sitting down, because their chin is tilted down a little. The wording across the top of the image reads: I am still none the wiser if I used irony correctly in the parenthesis when I keep adding examples to a final point. The wording along the bottom of the image reads: And at this point I'm too afraid to ask.

Conclusion

In conclusion, ChatGPT ‘saved my life’ by allowing me to interrogate my writing in a way I have never been able to before. We should promote ChatGPT to students as a resource that can help tighten up their drafts before needing academic support. It should be utilised to alleviate the burden on academics, who are often asked to critique early drafts of work. Academics should hopefully then only see much more polished versions of submissions that require less input from them. 

As a final example, I didn’t like my last sentence. ChatGPT gave me another version:

It should be used to relieve the burden on academics who are frequently asked to critique early drafts. Ideally, academics would primarily review more polished submissions that require minimal input.

I didn’t like that version either. Maybe then I should just delete it? That is where the human side wins out over AI, your sense of self and how you want to sound when writing.

AI is here to stay (and take over the world if the Terminator documentaries are anything to go by), but actually, that is alright (AI being here as a tool, not taking over the world). At levels 4 and 5, we need to find creative ways to incorporate AI tools into the assessment process (which may mean fewer essays). Levels 6, 7 and 8, it’s about using AI to help improve our own voice but not lose it. 

The ChatGPT re-write: How ChatGPT Revolutionized My Writing Process – The AI version.

Credit Image: Photo by rupixen.com on Unsplash

Image in the text created by T. Langston using imgflip.com

Guest Blogger: Fiona Cook – Isolation Reflections and Co-worker Jealousy

A month ago I posted on LinkedIn, sharing what I’d learnt about working from home after doing so for three weeks. Yesterday, I was asked if my advice would still be the same and I realise that seven weeks of home working, with an unknown number of weeks left, meant it wouldn’t be. 

There are still a few basics that help me. I only work at my desk, in my spare room, so that I can keep a work-life balance and switch off when I’m done for the day. I also have space from my boyfriend so that we can catch up with friends independently, as we would do in the outside world. The rest, however, has evolved a bit since I first shared it.

Two computer screens on and a cat sitting on a chair in front of them looking at the screens

I’m now less fussed about dressing as I would for work every day. Although I’m lucky to have a fairly decent desk set-up it’s not completely optimal, so I have put a bit more value on being comfortable in what I wear. This also helps ensure I have time for a workout at lunch, which is actually something I’ll surprisingly miss when I’m back in the office. And no-one can see my trackies in a video meeting, anyway! 

I drink less hot drinks when the weather is warmer but I’m still making sure I’m taking breaks when I need them. There’s a quote I’ve seen a lot which is “You are not working from home; you are at your home during a crisis trying to work.” This really resonates with me and it’s a great reminder that things aren’t normal right now and we can’t be expected to act as if they were. My boss has been flexible and supportive and I know that it’s okay if I’m not quite with it sometimes. 

Staying in touch with people, both for work and socially, hasn’t been too hard – even with the odd technical glitch. However, last week a lot of people seemed to be getting fatigued with lockdown and I actually felt socially drained. I’ve found that people are reaching out more than usual and whilst it’s great to know that friends want to stay in touch I felt my introverted self wanting to hide after four days of video calls and messages from numerous group chats. My boyfriend and I now make sure one evening a week is a phone-free film night so that we can focus on ourselves and not be glued to screens all the time. I also try not to feel bad about ignoring my phone when I need to switch off, and my friends completely understand when I explain why I’ve gone awol. That being said, despite the anxiety of having video calls with friendship groups for the first time, I arranged a video quiz with friends who I ordinarily might not have seen as a group and it was really wonderful to see their faces. 

I’ve also not gone on many walks lately. As I don’t drive I already had a recurring food delivery pre-lockdown and the deliveries are slowly becoming more reliable so I haven’t often had to go out, which I’m grateful for. Part of me feels like I’m wasting the sunshine and Pompey seafront, but I’m able to work out in my lounge and sit in the garden so I can still get exercise and fresh air. I want to go out, and I imagine I will soon, but I know it’s safer at home so I’m trying not to beat myself up for staying safe when I can. 

It’s not easy, especially as people close to me have to go out to work or deal with difficult employers, but we all need to work out what is best for us and our individual circumstances without comparing everything we do. I’ve only baked twice, I’d already recently started exercising, and I’m not learning any new skills. It’s okay to focus on your wellbeing to get through this and not emerge as a new shiny version of yourself, which is definitely worth remembering during Cat curled up fast asleep on a cover Mental Health Awareness Week. Be kind, to others but also to yourself.

Oh, and I’m also still very jealous of my new colleagues who sleep all day.

 

 

Credit Image: Photo by Mish Vizesi on Unsplash

Education 4.0

On 5 February a group of us met with representatives from Jisc. The main focus of the meeting was to discuss the Jisc Digital Insights service (which allows institutions to better understand the digital experience of staff and students) and the Jisc Discoverer service (which allows staff and students to reflect on their digital capability and, where necessary, access relevant support material). Future blog posts will talk more about how to access these services. In this post, I’d like to reflect briefly on a comment made during the meeting by Stuart Masters, Jisc’s Chief Technology Officer. Steve mentioned that one important focus for him, and for Jisc as an organisation, is to understand what “Education 4.0” might look like.    

You will probably have heard of the phrase “Industry 4.0” – or the closely related phrase “Fourth Industrial Revolution”. This idea refers to a gathering of emerging technologies – AI, biotechnology, cloud computing, internet of things, nanotechnology, quantum computing, robotics, 3D printing, 5G wireless – that blur the distinction between the physical, digital and biological. (For reference, the First Industrial Revolution occurred in the 18th/19th centuries and involved the development of the iron and textile industries, plus steam power; society began to shift from rural to urban, agrarian to industrial. The Second Industrial Revolution is often dated 1870–1914, and saw the creation of new industries – oil, steel, electricity – and the rise of mass production. The Third Industrial Revolution – the change from analog to digital devices – began in the 1980s and we are still living through its consequences.) Some of you, no doubt, will feel there is an element of hype to the phrase “Industry 4.0”; after all, how many times has “the next big thing” turned out to be an unusable piece of kit that people use briefly then throw away once the novelty has worn off? This time, though, there really are indications that this fusion of new technological developments – the Fourth Industrial Revolution – will alter society and the world of work.

If that is the case, how should universities respond? Jisc’s suggestion is that, in order to prepare students for a world transformed by Industry 4.0, we need to be thinking about Education 4.0. That’s fine – but what should Education 4.0 look like?

In a recent blog post on this subject, Sarah Davies of Jisc looked at some tentative steps towards Education 4.0 being taken by institutions. Ensuring that students have strong digital capabilities will of course be important (and, as mentioned above, a future post will discuss work taking place here at Portsmouth in this area) but Sarah also mentioned the importance of:

  • rethinking staff and student roles;
  • reimagining learning environments;
  • giving students the opportunity to create and communicate knowledge; and
  • focusing on student wellbeing.

These are all topics that we might well want to consider in Education 4.0, but Sarah also posts a link to a presentation by Martin Hamilton (Jisc’s resident futurist) to the Education Select Committee Inquiry on Industry 4.0. In that presentation, Martin pointed out that 33% of Key Stage Two pupils fail to meet expected standards of literacy and numeracy; 66% of secondary schools have inadequate digital infrastructure. Delivering Education 4.0 will be made even harder if we can’t even get the basics right.

It’s an interesting question, though. What do you think Education 4.0 should look like?  

Feature image title: Industry_4.0.png by Christoph Roser is licensed under CC BY2.0

 

Guest Blogger: Adrian Sharkey – Digital Capability Discovery Tool

The Digital Capability Discovery Tool is an empowering first step for students and staff to self-assess their digital capabilities and to identify current strengths and areas of development.

What is Digital Capability? 

DIgital capabilities are defined by Jisc as ‘those that fit an individual for living, learning and working in a digital society’. Digital capabilities are more important than ever: they are essential requirements for employability in a digital economy.

According to Jisc’s Digital experience insights survey 2018, only 41% of UK students felt that their course prepared them for the digital workplace. Everyone should be looking to continuously develop these skills and reflect on their own digital capability.

Using the Digital Capability Discovery Tool

Staff and students are encouraged to use the Discovery Tool to self-assess their digital capabilities. For staff, the tool could potentially be used to inform the PDR process. For students, there would be benefit to discussing the results in personal tutoring sessions.

When you log into the Discovery Tool for the first time you will be asked about your role at the University – there are different question sets for new students, current students, teaching staff, and library and learning support staff. It may be that the options don’t fit your role exactly – just choose the nearest match.

Upon completing the questionnaire you will receive a confidential, personalised report showing your results in each area of digital capability and with links to high-quality, tailored resources.

All responses are confidential, so tutors and managers do not have access to them. The University does, however, have access to aggregated, anonymised data – which will help us identify gaps in our digital learning support and improve our provision for both students and staff. This is yet another reason that everyone – staff and students – are encouraged to complete the survey!

Logging on and further support

IS and DCQE provide sessions for staff to find out about digital capabilities in general, and about the Discovery Tool and how to use it. In these sessions we also discuss how to use the Tool with students and colleagues.

For further information, and to access the Tool, go to digitalcapability.port.ac.uk

Guest Blogger: Julian Ingle – Writing Retreats Take Off

“What do you do, sit around writing poetry and novels?” When I say I’m running a writing retreat, most people assume it’s a kind of self-expression fest, paid for by the University. Nothing could be further from the truth.

I’m in my sixth month here as Deputy Head of ASK, enjoying the new role. In my previous job at Queen Mary, UoL, I’d run writing retreats for staff and PhD students on a regular basis. This was something I wanted to initiate here at Portsmouth. I’m pleased to say that I’ve just finished running my fourth writing retreat at the University. Hopefully this marks the beginning of regular retreats at Portsmouth and they’ll become part of the fabric.

These retreats are urban rather than residential – in other words we don’t head off and stay in a boutique hotel in the South Downs, but work in a large room on campus and then go home. The plan is to run off-campus one- and two-day retreats for staff and PhD students once I’ve found a good venue. (Being elsewhere does make a difference. As does having a decent lunch that you don’t have to prepare.)

The format of the retreats draws on Rowena Murray’s work, which over the years I’ve developed and refined. Highly structured, intense and very productive, we sit around a large boardroom-style table; we then set a goal or task for the first hour-long writing session, discuss it briefly with a colleague and then begin writing. When the hour is up we talk to our colleague about how it went, set another goal and carry on. To help re-focus, we also do short generative writing activities, such as freewriting. After lunch we spend half an hour peer reviewing someone else’s work, and then carry on writing in one-hour blocks. Sometimes the format varies, depending on time and location. Typically, there are between 12–15 participants from across the faculties – although the boundaries between staff and PhD students are sometimes blurred.

Having run retreats for the last eight years, I know they work. There are lots of reasons why, but key is that they get writing done. Staff workloads, multiple demands, and the general culture in many universities, mean that despite increasing pressure to publish, there is little time allocated or energy left to make time to write. So staff write in their holidays or at weekends. Providing a dedicated time and place, away from everyday demands, email or internet distractions, creates a shared ethos and valued space to do something that is in theory an essential dimension of who we are as teachers, practitioners, researchers, academics…

Building research writing cultures takes time. Writing retreats provide a powerful way to connect staff and PhD students with each other, their research, their thinking and practices, and help build a community of writers. The conversations that take place throughout the day are full of insights (there’s no such thing as a finished writer), so sharing the frustrations, trying something new or learning from others can give direction, confidence and motivation.

Or at least that’s what participants say about writing retreats. Above all they are productive: a frequent comment is that they’ve written more in the day than they’ve written in the last two months. On occasions, the freewriting activities can result in light bulb moments and help move thinking on. At the end of the day we’re tired but most people would like more.

I’m determined that writing retreats will continue at the University and, if we get a good location and good food, they will get better.

If you’d like to take part in a writing retreat, be added to the mailing list, or would like to discuss how they could be tailored to your faculty or students, then please get in touch: Julian Ingle, Deputy Head of ASK, (julian.ingle@port.ac.uk).

Here’s a photo of us hard at work at the first retreat.

People sitting around a table

Image credits: Photo by rawpixel on Unsplash

Thinking about accessibility

I’ve been doing a lot of thinking about accessibility and Moodle recently as we move the Moodle Baseline project into the pilot stage. It’s become clear that many of us don’t make our responsibility to create accessible content a top priority when all that’s needed is a small amount of extra time to ensure a vast improvement in the ability of differently abled users to consume your Moodle content. I’m not going to call any specific Moodle sites out here, but some of the most prevalent bad practice that somewhat surprisingly still seems to exist includes using HTML tables for navigation & layout, and using images for headings or navigation.

Both of these issues become problematic to users who use screen readers. Whilst it is true that screen reader support for tables has improved, they should still not be used for navigation or layout. Every time the screen reader box enters a table cell, the screen reader will tell the user which cell they are in. You can easily see how this is not a good user experience if you have to work your way through a four by five table, with a link (or more than one link) in each cell. Using something more appropriate such as an HTML list for this navigation properly give the nav role in the html, as well as a more streamlined experience, a screen reader can also use this information to offer it’s user the option to skip the navigation and go straight to page content, or not. for some more information on this have a look at the W3 Schools page detailing the nav role.

Using an image for heading isn’t automatically a terrible thing. If it’s used in conjunction with either HTML alt text, or if at all possible an ARIA attribute to notify to a screen reader how the image is being used. Using CSS to replace a text link with an image, which will also allow the image to be seen by those browsing visually, but also mean the HTML text link is visible to those with a screen reader It just so happens that Bootstrap 4 has an easy way to do this which everyone can use after the Moodle upgrade in August. Bootstrap also offers ways to totally hide elements in your HTML content from everyone except those using screen readers, so you can really go the extra mile to offer content that’s easier to digest audibly.

There are reasons why you’d need to use a custom navigation, there are also times however that the topic jump list should be more than sufficient for navigating between topics on a Moodle site. If you find that this is almost good enough – but not quite – please talk to us and we’ll try and make it totally good enough for you to use. If you’d like to find out more about accessibility I would heartily recommend the Digital Accessibility MOOC on FutureLearn, it really opened my eyes to accessibility issues I’d never considered – it made me realise what I thought I was doing to enable differently abled people to read my content, wasn’t in fact enough.

I’ll leave you with this from our Moodle content guide which will arrived with the new theme after the upgrade in the summer:

Accessibility for Moodle content means that your content is available to be consumed by all users, regardless of their ability. Creating accessible learning content is the responsibility of us all – It’s not something that should be left until later, or for us to think that it’s the responsibility of someone else.

Digital Experience Insights – a community of practice

I gave a talk on 14 November at the launch of JISC’s new Community of Practice in Digital Experience Insights. The JISC Insights service builds on their work with the Student Tracker – a survey of students’ experience of the digital environment. Portsmouth, as one of the initial pilot institutions for the Tracker, has more experience than most in using insights gained from the student survey.  

One of the key take-home messages from the event, at least for me, was that the issues we are grappling with here at Portsmouth are exactly the same issues with which other institutions are grappling. The event also provided a valuable sanity-check: the approaches we are taking are the same approaches that others are either taking, planning to take, or would like to take!

The graphic below shows one example of how the student digital experience at Portsmouth is not dissimilar to the student experience elsewhere. Students were asked to name an app they found particularly useful. The word cloud on the left shows the national response. Once the various types of VLE (Blackboard, Moodle, Canvas) are combined, the three most popular apps are: VLE, Google, YouTube. The word cloud on the right shows the Portsmouth response. The three most popular apps are: VLE, Google, YouTube. It’s the smaller words that carry the institutional flavour – and I think Portsmouth does extremely well in this regard; 93% of our students rate our digital provision as good or better.

Speech Bubbles

Helen Beetham gave one of the most interesting talks of the day. Helen gave an overview of a pilot into the digital experience of teaching staff. There were insufficient responses to publish statistically robust findings, but there were some interesting titbits in there. For example, students are much more positive than teachers about the digital environment. Is this because teachers are more critical? Or perhaps they have higher expectations of what a digital environment should look like? On the other hand, teachers are much more likely than students to want more digital technology in their courses. Are students more conservative when it comes to expectations around learning and teaching?

The majority of responders to the staff survey identified themselves as early adopters – and yet about 50% never search online for resources; 84% of them are unsure of their responsibilities in relation to assistive technologies; 81% are uncertain when it comes to dealing with their own health and well-being in a digital environment; and 13% never update their digital skills. By far the biggest problem staff face in improving their digital teaching is – of course – lack of time to do so.

For the past three years Portsmouth has sought to understand the student experience of the digital environment, and we plan to run the JISC insight service for a fourth year. But we could build a much richer picture by asking teaching staff as well as students. So this year we plan to run the staff-facing digital insights survey. More details to follow in 2019! 

Credit image: Photo by Annie Spratt on Unsplash

Episode 8 – Charles Barker – Presentation Performance

TelTaleBanner
TelTales Podcast
Episode 8 - Charles Barker - Presentation Performance
Loading
/

Copyright Information:

Nowhere Land – Kevin MacLeod (incompetech.com)
Licensed under Creative Commons: By Attribution 3.0 License
http://creativecommons.org/licenses/by/3.0/

« Older posts

© 2024 Tel Tales

Theme by Anders NorénUp ↑