ETEC 511: Tipping Point: A Critical Case Study of the LMS replacing websites

Dating back to the early use of the world wide web to produce websites, academic institutions provided space and access to servers to faculty. Naturally this early exploration of the space included a number of uses –personal spaces, spaces dedicated to research, community and academic teaching. The archive.org McMaster University archive goes back to 1997, however I know that website use for teaching purposes existed prior to 1997 and went back as far as 1994 (Cuneo et al, 2000). Outside of a brief resurgence of website use in 2010 (while the on-premises LMS solution Blackboard installation was besieged with technical issues) the decline has continued to the present day.

One challenge in providing proof of this decline is that there is no comprehensive way to catalog and decipher each department and faculty approaches to personal webhosting for academic faculty and no standard approach to naming and hosting. To this end, I did encounter a deep archive of links for the faculty of Humanities websites.

In a sampling of pages that I could find archived for the Languages and Linguistics department within the faculty of Humanities (out of the 26 courses listed) (Department of Modern Languages and Linguistics, 2001) – there were 4 courses with individual webpages, and a further 16 courses with course outlines linked from the page. Some of the courses with web presences beyond a course outline were last archived in 2005, however the last successful archiving of an actual active course was 2003. (Solo Testo, 2003). The later archives were of a redirect to the Faculty of Humanities homepage likely as a result of a restructuring of the website.

By 2004, as the proliferation of WebCT and First Class (known locally as Learn Link) at McMaster became more prevalent, use of websites for teaching started to decline. It makes some sense that this trend starts to appear at this point – historically the Learning Technologies Resource Centre (LTRC) began to support central LMS tools around this time, and nearly a decade after the technology started to be used at McMaster, there are likely to be some combination of the maturity of the tools and a convergence as commercial software begins to become commonplace at higher education institutions. At McMaster, while there was some standardization of tools provided by the university to faculty at no additional charge, there was also no mandate to use the centrally supported tools. In fact, the only mention of LMS like systems were Learn Link (First Class) and WebCT in the Central IT report for 2005 was a mention for both systems’ server requirements as part of the LTRC inventory (Barret, 2005, p.187) Alternatively, there was no mention of hosting websites as a service across any of the independent or central IT units at the time. Further to this idea, the archives I could find on the Wayback Machine for McMaster all seem to indicate websites were not to be used for teaching, rather it seems the commonplace use of websites were for communication. It is reasonable to say website hosting for the purposes of teaching was far less used than the central LMS’s during this first decade of the World Wide Web. If we look back at one of the first major commercial LMS, WebCT, it was designed initially by Murray Goldberg in the mid-90’s as a way to supplement his in-person lectures. (Chan, 2005) Most web-based LMS systems replicate the functionality of WebCT – certainly most of the ones used in higher education (Blackboard, D2L’s Brightspace, Canvas and Moodle) – and so a system of software based on the experiences and design of an instructor who was looking to improve grades in courses rooted in a lecture based approach has become the defacto location for teaching to happen in an online environment.

While websites as a course site was not a priority of the university, it is likely that the impetus for this displacement in teaching tools came from several different areas, in addition to the lack of support from the university, converging slowly in the mid-2000’s to the present day:

  1. Instructors were increasingly becoming sessional and labour to build one’s own site is not compensated. The LMS is provided (although not necessarily the simplest for all).
  2. Using an LMS is easier than managing your own website for teaching as much of the infrastructure is provided by someone else.
  3. Some instructors who are interested in using the LMS for teaching were early adopters and acted as champions for the tool.
  4. Instructors who moved from institutions who have mandated LMS use to McMaster, brought along that practice, expecting McMaster to also have mandated the use of the LMS.
  5. Students who experienced LMS use in secondary school have now graduated into higher education and expected the use of an LMS to provide materials and activities.
  6. Faculties and departments each have suggested over the years tool use based on their own experiences and desire to introduce efficiencies which the LMS can provide.
  7. Educational institutions being interested in reducing paper in the name of sustainability.
  8. Vendors of LMS products convinced institutions of the efficiency, redundancy, and security of the LMS.

While each of those individual claims, can be discussed at length, this transition has definitely re-entrenched the transmission model of teaching and learning. The LMS reinforces the transmission model by having a roles that allows certain members in the system more or less power to control other users. For instance, an instructor role could be designed to allow for posting of materials, whereas a student role could view those materials. In some LMS systems these are determined by the local system administrators (often with the help of the vendor) while others have these archetypes predefined. While a vendor might argue it is up to the institution to configure the system how they wish, the archetypal uses of the system are designed around fundamental assumptions of what an instructor might be. Very rarely are LMS structures built with features that promote constructive sense-making, and as such, they are often designed for behaviourist approaches to teaching. This is an example of what Woolgar (1990) might describe as configuring the user, especially when considering the history of the development of the LMS being from a limited perspective and for a limited purpose.

This shift from a more open website to a closed, more secure but also more deterministic LMS does not necessarily negatively impact teaching per se, it does make it more challenging to use a LMS with certain pedagogical approaches. For instance, if you are teaching in a constructivist manner, it is difficult to have people   If at every turn it is difficult and time-consuming to make the LMS do what you want to do pedagogically, and the education system is rewarding certain choices you make with your labour, it becomes even more challenging to teach in ways that might be more constructivist, so you might come to believe that it is impossible to teach in that way through the LMS. While it is true it is more difficult, and might make the LMS itself unusable, it might be impractical, or more time-consuming to teach in that way. In those scenarios, a stand-alone website would probably be a superior choice.

In our class readings, there is a similar issue with labour being reduced by choice being taken away by making the undesirable behaviour more costly for the worker to do. This was raised in Crawford (2021) with Amazon workers being restricted in unauthorized actions, one such example of unauthorized actions being too many breaks. (p. 53) By the design (and in many ways the usability) of the LMS rewarding efficiency and punishing inefficiency, there is a pervasive enforcement of “traditional” teaching methods. Individually designed and constructed websites have no preconceived notions of what teaching is, and in fact if the teacher is the designer of the site themselves, it can accurately reflect their pedagogy in as much as they can use HTML, CSS and Javascript to bring that reflection to life. While the course’s content is clearly about digital labour, one of the underlying currents of that module is about how digital labour is often not done by machines but by humans in often inhumane conditions. In much the same ways humans are doing the mechanical turk work or ghost work (Gray and Suri, 2019), the work being done to build courses in LMS systems are often not done by the instructor themselves, but by unseen labour. It might be offloaded to a teaching assistant, or an instructional designer or someone hired from outside the institution delivering the course to design a course virtually on-demand. Ghost work typically involves moving the production of labour to countries that have less labour costs than in western countries, this does happen in educational institutions where labour shifts from full-time, tenured and senior professors, to teaching assistants and lower paid members of the department or faculty.  In an institution it is entirely possible for some teachers to teach courses designed by someone else and built by yet another different person. While this undoubtedly happened with the people who were using websites to teach as well; getting a TA or instructional designer (or learning technologist) to build a website that the teacher could use to deliver content. Even in those cases, more design choices, more personalization would happen would require at least some input on those choices from the teacher and thus the system used to teach would also be closely designed by the teacher. With frequency, the labour for putting courses into the LMS have become the responsibility of teaching assistants. In 2021, McMaster and CUPE (the union for Teaching Assistants) agreed to paid training on various teaching related topics, including a module on the LMS use (An Introduction to Avenue to Learn). (McMaster University, 2021, p.2) While this labour previously might have gone uncompensated, and the teaching assistant may have had to learn this on their own or attend training, clearly the recognition from the university is that this activity is no longer in the realm of teachers alone.

Another aspect of LMS use is the ease of recycling course materials from semester-to-semester. While this is not a practice of all teachers using LMS’s, there are sessional instructors who are not compensated for the development of courses. If a fellow instructor or teacher chooses to share their content, and intellectual property, then the recipient is lucky. If the sessional instructor does not have access to content from a prior taught course, they are often designing the course as it goes, which does not provide an ideal learning experience. This is essentially a labour issue. As the university lowers the number of full-time and secure jobs to teaching faculty, it also creates a precarious market for labour, with faculty becoming sessional. If one can separate the course from the individual, and keep the course in a centrally maintained place, then that labour can be passed on without care for the individual who designed it. I am not saying that was the explicit goal of McMaster in instituting the LMS, but it is possible to separate the labour of creating a course with delivery of a course using an LMS, which makes it easier to retain beyond the employment of the developer.

            While the shift from open websites to a more closed LMS system also mirror the academic labour changes over the last two decades, in some ways both developments have been symbiotic – allowing for teaching to become more prescriptive, and the culture of teaching to be more limited.

References

Barret, D. (2005). University Technology Strategy. McMaster University. https://www.mcmaster.ca/cio/UTSMar05.pdf

Chan, L. (2005) WebCT Revolutionized E-Learning. UBC News. https://news.ubc.ca/2005/07/07/archive-ubcreports-2005-05jul07-webct/

Crawford, K. (2021). Atlas of AI. Yale University Press.

Gray, M. L. & Suri, S. (2019). Ghost work : How to stop silicon valley from building a new global underclass. Houghton Mifflin Harcourt.

McMaster University (2001). Department of Modern Languages and Linguistics @ McMaster University. Wayback Machine. https://web.archive.org/web/20010214022946/http://www.humanities.mcmaster.ca/~modlang/mlhome.htm

McMaster University (2003). Solo Testo. Wayback Machine. https://web.archive.org/web/20030928012724fw_/http://www.humanities.mcmaster.ca/~gargann/text.htm

McMaster University. (2021) McMaster University CUPE Local 3906, Unit 1 Mandatory Training Frequently Asked Questions. https://hr.mcmaster.ca/app/uploads/2021/08/Mosaic-TA-Training-Module-FAQs_FINAL.pdf

Woolgar, S. (1990) Configuring the user: The case of usability trials. The Sociological Review, 38(1, Suppl.), S58-S99.

AI Writing

So I saw some tech-guru on Twitter pontificating about how awesome AI writing assists were and I thought, let’s give that try. So, I signed up for a demo of a product, and it’s pretty slick. (HASHTAG NOT AN AD #notsponsored). The thing that I used is called Moonbeam which is aimed at helping you become a better writer (and yes, it does help with the blank page syndrome).

My initial though is: slick, but not quite there yet for niche interests (which holds out hope for teaching (more on that in a minute).

I gave it the prompt “The Disasterous Choice to Teach Using an LMS”.

It then provided me with a fleshed-out draft – three arguments against, three arguments for and a conclusion. I edited the three arguments for out and generated this:

The Disasterous Choice to Teach Using an LMS

Introduction: Discuss the reasons why some instructors choose to use an LMS, or learning management system, to teach their students and how this negatively impacts learning.

Some instructors choose to use an LMS because it is a convenient way to deliver course content and track student progress. While this may be appealing at first, using an LMS can have negative consequences for learning. For example, a more passive learning environment can create difficulty for students in accessing and understanding the material. Additionally, using an LMS can limit instructor creativity and flexibility in designing and delivering instruction. As a result, the choice to use an LMS should be based on what will best meet the needs of the instructor and the students.

There are several potential disadvantages to using an LMS, including the following:

There are several potential disadvantages to using an LMS, including the following:

Increased potential for cheating: With an LMS, it is easier for students to find and copy answers from each other, which can lead to decreased grades and a loss of learning.

Limited interaction with instructors: If problems arise or clarification is needed, students may have difficulty getting in touch with their instructors in a timely manner through an LMS.

Technical difficulties: An LMS can be prone to glitches and crashes, which can interfere with classes and disrupt learning.

High cost: Some LMSs can be expensive for schools or individual teachers to implement and maintain.

a) It can be difficult to keep track of all the different features and functions of an LMS.

It can be difficult for educators to keep track of all the different features and functions of an LMS. This can lead to frustration and confusion for both teachers and students. An LMS can also be expensive, and many school districts cannot afford to purchase one. There is also a lack of research on the effectiveness of using an LMS in the classroom. Some educators believe that an LMS can actually hinder learning rather than promote it.

b) An LMS can be time-consuming to set up and maintain.

An LMS can be time-consuming to set up and maintain, which can take away from time that could be spent teaching.

An LMS can be difficult to use, which can lead to frustration for both teachers and students.

An LMS can be expensive, which can limit its use to only those who can afford it.

An LMS can be inflexible, which can make it difficult to adapt to changing needs or requirements.

c) Some students may find it difficult to navigate an LMS due to design of the course or the LMS itself.

Some students may find it difficult to navigate an LMS due to its design or the LMS itself, leading to frustration and a feeling of being overwhelmed. This can impact their ability to learn effectively.

An LMS that is designed with user-friendliness in mind can help alleviate some of these issues. Additionally, providing support and training for students on how to use an LMS can also be beneficial.

Ultimately, it is important to consider the needs of all students when choosing to use an LMS for teaching purposes.

Lack of control over the learning environment, dependence on technology, and limited interaction with students are some of the challenges that arise when using an LMS for instruction. These issues require significant investment of time and resources if they are going to be overcome.

Ineffective for certain types of learners is another potential downside of using an LMS for teaching purposes; however, this can be remedied by taking into account the specific needs of each student group before designing a course content strategy around an LMS platform

Now that’s not a bad starting point. I could flesh that out and expand on the points. And that’s the value that Moonbeam proposes – giving folks an option to edit all the way through (which likely improves their AI model). If I were generating content as a content provider, I definitely would be using this as a way to flesh out ideas and keep things a little more focused while working rapidly.

Now if I were a niche content producer (oh say, talking about educational technologies) then the downside to this is you’re not providing much additional value over a Google search as I’m sure the AI is using scraped data for one of it’s source, and so the niche stuff which doesn’t have a lot of linkage, or doesn’t have a lot of major traction, like most of the educational technology focused blogs, then it probably won’t deliver anything but a surface understanding of the subject. I can’t imagine the wrongness of something about punk (actually I can, because I generated a blog post about how 1982 is the best year for punk – it included the sentence: 1984 was a crucial year for punk music, as it saw the rise of crossover poppunk and hardcore metal.)

The testimonials on the front page of the site, well, they tell you that (if you’re an educator) your students are already using the tool. A quick social media search shows that is true as well. If it’s on Twitter, chances are there’s thousands more on private Discord servers and SnapChat.

The hope for education? Well, it’s the same argument we had about the web destroying education – access to all the information in the world does not provide the context one needs to form a deep understanding of the subject. Instead of rehashed, crappy essays (and please, can we get away from essays) and going towards more participatory ways of demonstrating learning I’m sure higher education will simply try to outlaw these things and adhere to stricter more surveillancy kinds of approaches to solving the problem. The problem is that more participatory ways of demonstrating learning is that they aren’t easily scalable – or are they? One thing that MOOCs taught me is that with a large enough bank of assessments, it is totally possible to demonstrate learning at scale (now assessing… that’s a different matter). Look at the DS106 Assignment Bank. It’s got clear assignments linked to loose themes (which could be your learning outcomes if that’s how you roll) that students can select from. I suspect that these would be difficult to do through AI. Another strategy might be to use the AI and show how you’d improve that output as part of the essay building process.

Will we get there though? The labour costs of doing the DS106 assignment bank is huge – and the assessment of 600+ students (thinking about first year folks) would be considerable. Maybe there’s ways around it, I’m sure that people could come up with clever ways to assess at scale – but anything offloading assessment to students or peers is a band-aid on the way higher education is running.

ETEC 511: Tipping Point, A Critical Case Study Proposal

One of the observations I have made over the years, and particularly over the last decade at McMaster University, is that the LMS has mostly displaced the use of personal websites for teaching. The reasons for this are multifaceted and contextual to individual institutions, however, at McMaster, I have observed that it is most likely related to the course themes of Digital Labour (once in the LMS, it is easier, and less labourious to keep using the LMS and the labour of using the LMS can be offloaded to teaching assistants) and Attention (student preference is to have all learning in one place). However, there are secondary contributing factors, which would fall under Algorithms (enhanced ability to track and observe course activity) and Sustainability (not from an environmental standpoint, but a course sustainability practice). There is also a factor of culturalization – since 2011, LMS use has not been mandaked. The makeup of faculty has skewed younger and with that pre-LMS teaching has faded from institutional memory. In many cases, no one even thinks that teaching outside institutional systems is possible or even desirable.

ETEC 511: Project Proposal

Checking UDL and Accessibility: A Checklist for Educators.

Most countries have adopted disability legislation that requires legally compliant interventions at the organizational level, including businesses, services, and educators, to accommodate the broadest possible range of human experience (Doyle, 2020).  We are proposing a Universal Design for Learning (UDL) checklist tool intended to help adult educators in any context examine learning materials that they develop to address accessibility and neurodivergent users. 

This tool will function in a branching decision tree to help educators determine if their learning objects have the affordances they need to accommodate all learners. The decision points will be supported with an explanation of how to employ UDL principles for that criteria and a rationale for why it is essential to support that factor, including some examples of specific (dis)abilities the factor supports.

Intended Users

This tool is designed for educators (designers, teachers, trainers, consultants) who create learning materials (digital or physical) for adult learners.

Setting Adult Learners Up for Success

We aim to enable adult educators to create learning materials that accommodate all facets of UDL, so the educational experience can be inclusive and accommodating to all learners.

One in five people has a neuro-difference, such as dyslexia, ADHD, autism, or anxiety disorders (Doyle, 2020). According to Statistics Canada, in a 2017 study, 14% of Canadians aged 25 to 64 with disabilities reported having at least a university qualification, compared with 27% of those without disabilities (Statistics Canada, 2019). These disabilities included neurodevelopmental condition(s) (NDC), a mental health condition (MHC), or both. These are diagnosed conditions, so the number of undiagnosed people is likely far higher. Those adults with undiagnosed learning (dis)abilities have multiple barriers to learning in place and often must look for accommodations in the workplace or post-secondary education. In fact, 43% of employees with (dis)abilities (and neuro-differences) do not feel comfortable approaching their employer to ask for accommodation (Business Disability Forum, 2020). We want to create a tool that supports educators when creating learning materials for all learners, regardless of ability, and mitigating the need for after-the-fact learning accommodations.

There are increasing resources for UDL principles; however, educators need to learn how to apply them in an organized, straightforward manner to determine whether their learning object/module/course meets UDL guidelines.

“The UDL framework is grounded in three principles:

●      Multiple means of representation – using various methods to present information and provide a range of means to support.

●      Multiple means of action and expression – providing learners with alternative ways to act skilfully and demonstrate what they know.

●  Multiple means of engagement – tapping into learners’ interests by offering choices of content and tools; motivating learners by offering adjustable levels of challenge.” (TEAL Center Staff, n.d.)

Our checklist will help educators accommodate the three UDL principles. Other resources list what UDL considers but do not provide the depth or breadth required for someone to design learning materials with all the principles in mind. Given that UDL is a newer approach, many educators are unfamiliar with its benefits and drawbacks. There is a lack of resources that provide this sort of support and an easy-to-access and use tool that provides guidance and awareness on the full range of learner abilities, particularly those with unrealized and unacknowledged learning disabilities. This tool will be helpful for new instructional designers and educators to acclimate them to UDL principles.

Creating an Interactive Decision Tree

We believe Twine will allow us to create branches for different aspects of UDL, be accessible to all educators and be easy to use. If there is an overlap between resources or rationale, we can link to the same resources without having to create them twice. Twine allows for the inclusion of videos and links to web resources, which allows us to address the multimodal framing of UDL within our design.

Our tool configures its users by determining what can be checked. Our project group selects what is essential from a UDL lens to be incorporated into learning materials, focusing on adults with unacknowledged learning disabilities. We aim to provide educators and designers with an easy-to-use tool that helps all adult learners, regardless of barriers or learning abilities.

UDL Checklist Items

In our tool considerations, we would like to include factors such as:

●  What devices might learners be using and what are their technical capabilities?

●  Have you considered different (dis)ability needs?

●  By making it accessible for one group, are you making it less accessible for others?

●  Have you considered inclusivity (language, font style and size, colour palette, etc.)?

●  Does the approach have an alternative method of delivery?

●  Does it provide appropriate and sufficient cognitive support (organizing clues, background information, scaffolding)?

●  Does this approach comply with ACR standards? Are there additional provincial compliance requirements?

●  Does the mode of assessment consider necessities and fairness (time constraints, presentation method, learner option, authenticity, supporting resources)?

Using Inclusion to Necessitate Usability

This tool is a checklist. One of the limiting factors of checklists is that we will have to determine what is included in the list and how that list is sequenced. Woolgar (1996) would consider this an element of configuring the user. This limitation makes the tool more usable and less overwhelming for practitioners new to UDL principles. Gee (2005) states that we learn best when we understand how things fit into a larger meaningful whole.  By reducing the broad scope of UDL to more manageable subtopics, it becomes easier to digest and learn about the benefits of UDL. Chunks have long been proposed as a basic organizational unit for human memory (Laird et al., 1984). Chunking is an essential strategy for learning complex subjects. Laird et al. (1984) demonstrate that a practice mechanism based on chunking can speed up task performance and may be capable of leading to more exciting forms of learning than just simply improving the speed of acquisition.

The output of Twine creates accessible objects delivered on the web. It requires low bandwidth and does not require significant computer processing power to operate, allowing people to access this tool from a desktop or mobile device regardless of location or operating bandwidth.

Determining Usability and Success

Using the usability specifications (as defined by Issa and Isaiah, p. 34) we will examine performance measures such as the responsiveness of the completed site (is there a significant delay from clicking on an item?) and preference measures from a target audience focus group to examine whether this checklist tool improves their understanding of UDL. If time allowed, a longitudinal study could be conducted to see how the covered UDL principles were recalled one year after the user introduced the checklist.

  

References

Are Mental Health and Neurodevelopmental Conditions Barriers to Postsecondary Access? (2019, February 19). Retrieved October 9, 2022, from https://www150.statcan.gc.ca/n1/pub/11f0019m/11f0019m2019005-eng.htm

Business Disability Forum. (2020). The great big workplace adjustment survey: Exploring the experience and outcomes of workplace adjustments in 2019-20. Retrieved October 13, 2022, from https://businessdisabilityforum.org.uk/policy/the-great-big-workplace-adjustments-survey-2019-20/

Doyle, N. (2020). Neurodiversity at work: a biopsychosocial model and the impact on working adults. British Medical Bulletin. 135(1), 108-125. https://doi.org/10.1093/bmb/ldaa021

Gee, J. P. (2005). Learning by design: Good video games as learning machines. E-learning and Digital Media, 2(1), 5-16. https://doi.org/10.2304/elea.2005.2.1.5

Initiative, W. W. A. (n.d.). WCAG 2 Overview. Web Accessibility Initiative (WAI). Retrieved October 15, 2022, from https://www.w3.org/WAI/standards-guidelines/wcag/

Issa, T., & Isaias, P. (2015). Usability and Human Computer Interaction (HCI). Sustainable Design, 19–36. https://doi.org/10.1007/978-1-4471-6753-2_2

Laird, J. E., Rosenbloom, P. S., & Newell, A. (1984, August). Towards Chunking as a General Learning Mechanism. In AAAI (pp. 188-192).

TEAL Center Staff (n.d.). TEAL Center Fact Sheet No. 2: Fact Sheet: Universal Design for Learning. LINCS. Retrieved from https://lincs.ed.gov/state-resources/federal-initiatives/teal/guide/udl 

Woolgar, S. (1990, May). Configuring the User: The Case of Usability Trials. The Sociological Review, 38(1_suppl), 58–99. https://doi.org/10.1111/j.1467-954x.1990.tb03349.x

ETEC 511 – IP #3: Algorithms

Option I: Content Prioritization

“At a time when state funding for public goods such as universities, schools, libraries, archives, and other important memory institutions is in decline in the US, private corporations are providing products, services and financing on their behalf. With these trade-offs comes an exercising of greater control over the information, which is deeply consequential for those already systematically oppressed…” (Noble, p. 123)

Think and respond to the following questions:

  • Explain in your own words what “content prioritization” (Noble, p. 156) means (give some examples) and how (in lay terms) content prioritization algorithms work. With control over the “largest digital repository in the world” (Noble, p. 187), how have Google’s content prioritization algorithms been “consequential for those already systematically oppressed”? How do they impact your professional life? (give specific examples and briefly discuss)
  • What are some ways PageRank impacts your personal life? (specific examples and briefly discuss) (How) can you impact PageRank? Explain.

Content prioritization essentially is a resorting algorithm based on a myriad of factors. In Google Search, it is based on things like location data, prior search history, demographic information about your account, and other personalization. While this might seem like a good and useful thing, it does often lead one down a rabbit hole. Google Search, like most sites, wants your attention. The more time you spend with it the better. The more searches, means that they can build a better profile of you and what you want to see. I will come back to that in a moment.

When people started figuring out how to improve their own sites search ranking, they started to manipulate link text to manipulate Google’s algorithm for search ranking. This lead to using potential misleading link text (the early internet history’s version of being Rick-Rolled) to mislead users through a process called Google Bombing. As these became passed around early social media, they also caused Google to rank them higher in priority based on the number of searches being run for the search term. The one that might be memorable was during the second Iraq War, anti-war groups made an effort to link “miserable failure” to the White House’s website. Typically, these Google Bombs were not long-lasting, as you can see from Google Search trends for the phrase “miserable failure”. However, their impact was.

The manipulation of search ranking was seen as a strategy from radical right groups (McSwiney in Devries, Bessant & Watts, 2021, p. 25) to access, recruit and radicalize users. The sheer volume of racist propaganda online is almost pervasive. If one of Google’s search algorithm key ranking criteria is based on volume of links, it is no wonder that racist, biased sites get pushed up the rankings. One of Noble’s arguments throughout the book is that while Google builds the algorithm that pushes certain sites to the top of the pile, they are not responsible for it (Noble, 2018). So, it follows when Google autocompletes a search query with a stereotypical response, that has an impact on the viewer – either reinforcing a negative view or potentially introducing self-doubt and the ranking algorithm every time it is clicked.

In my professional work, I often am searching websites for documentation about educational technology products. I am often working on a work account which has little to no demographic information, never search logged in, with no location technology able to be queried. Essentially, my work account is a bit like a burner account. So typically, no, I do not see any evidence of discrimination, however documentation does have discrimination built into it – the types of archetypes used, the images of people describe more about the company than many think. However, from a search perspective, I do not use Google autocomplete ever, I do not use Google as a sole search provider, I move around (Duck Duck Go and Bing are two suitable competitors), so that there isn’t much to give to one provider.

Back to the popularity contest that is PageRank, and attention. While I do not use Google exclusively, PageRank’s algorithm strategy is pretty pervasive amongst search. It is part of what was taught at Udacity’s big “build a search engine” MOOC (I completed this in 2012?) and is what Yandex and Bing use to scrape the web for links, and to count the number of links that point to a site with a set of keywords. It is a common strategy and would like yield common results – except you do not have the ranking algorithm component, but both ranking and link scraping work hand in hand. The first way that PageRank influences daily life is the reliance on what is popular over what is factual. I have seen this over and over, popular misconceptions – and how tales take over the reality of what happened. Sure, we have context for some of that (in that disadvantaged groups often do not get their stories told at all) but Google’s focus on popularity assumed (when PageRank was developed initially) that people are mostly truthful. Instead, 15 years later, it is less about people and more about how many resources can be deployed to increase site ranking, essentially privileging the wealthy (who are disproportionally white, heterosexual and male) and resourceful.

Well, one way to circumvent PageRank is to Google Bomb it to uselessness. Essentially fill it with obfuscated information. However, that only punishes you – because it makes it less useful to you. One other way to make PageRank be influential is to pay less attention to it and SIFT the sources. Go straight to the source rather than Google Search everything (the number of times I have seen someone search for the website, rather than just type the site address is more than I can count in the last decade). Use other search engines. Avoid giving attention to things that are false. Support platforms that do not combine personal data with search results.

References

Devries, M., Bessant, J., & Watts, R. (Eds.). (2021). Rise of the far right : Technologies of recruitment and mobilization. Rowman & Littlefield Publishers.

Noble, S. (2018). Algorithms of Oppression : How Search Engines Reinforce Racism. NYU Press.

ETEC 511 – IP #2: Artificial Intelligence

1. Who were these people, and how did/does each contribute to the development of artificial intelligence? How did/does each think “intelligence” could be identified? (~50 words each)

Alan Turing: In the context of artificial intelligence, Turing is best known for developing Turing’s test – which is a game that a computer and a human answer questions with the interregator trying to determine which is human. While this test of “thinking” is a bit limited especially when you consider a computer could be trained to mimic a human response to questions, it is the first ideas of what kinds of qualifications artificial intelligence might require.

John McCarthy: McCarthy is often listed among the parents of the artificial intelligence field. To me, McCarthy is most important for opening up the philosophical problems of AI (McCarthy and Hayes, 1969) and trying to separate intelligence from humanity, and to start to dissect what people mean by intelligence. McCarthy believed that intelligence was the “computational part of the ability to achieve goals in the world”. (McCarthy 1997, in Sutton, 2020)

Herb Simon: Another founding parent of artificial intelligence, Simon drew from his early research into decision making and brought that rationality and requirements for large data to draw an analysis from to the field of artificial intelligence. He was awarded the Nobel Prize in Economics in 1978 for his work on how people make decisions when they have incomplete information.

Marvin Minsky: Minsky in 1960 wrote about how artificial intelligence needed to address problems from multiple perspectives. He viewed artificial intelligence as a complex problem solving divided into five main processes: search, pattern recognition, learning, planning and induction. Minsky believed that when computers were able to take into account each of those aspects, that computers would be considered intelligent.

Timnit Gebru: Gebru was the co-lead of Google’s ethical AI team and was forced out as the result of a paper that suggested that large language models that train AI were often discriminatory. (Hao, 2020) This paper, and the subsequent social media discussion around ethical AI, has ushered in a new dimension to consider when developing AI tools.

2. How do “machine (programming) languages” differ from human (natural) ones? (~100 words).

Harris (2018) writes that the difference between the two languages are that programming languages are completely described, having their own set of rules, and they do not evolve with their usage on their own. I would add two other aspects in that natural language is used to create programming languages, and programming languages need a compiler. Of course, our own natural languages require interpretation (even when using the same natural language).

3. How does “machine (artificial) intelligence” differ from the human version? (~100 words).

If we deem AI intelligence at all, artificial and biological are not comparable. Firstly, artificial intelligence is limited in a myriad of ways that make it overall limited in capacity. Looking at AI art generators – they can function within the programming of the generator. The generator cannot become inspired by another art style. Intelligence is not simply the regurgitation of facts but drawing from different disciplines to develop novel ideas. Secondly, while artificial intelligence operates within parameters with a specific purpose, human intelligence does not. It wanders, it does not simply focus on solving the problem posed to it, but also runs a biological body on top of it.

4. How does “machine learning” differ from human learning? (~100 words) 

Machines do not have the ability to assess the motivation for an author to publish something or discriminate against false information. Essentially because humans can be flawed and discriminatory (or outright racist, sexist or biased) and humans make these algorithms that determine how and on what machines learn, it follows that any bias that might exist in a human programmer, or body of data that trains the machine, would introduce those flaws into the machine. However, a human can correct those flaws (or double down on them) whereas the machine would simply use the programming to “learn” the same facts.

5. And for your LAST challenge, a version of the Turing Test: how do YOUR answers to these questions differ from what a machine could generate? (~200 words)

It all depends? Is the AI trained to draw from the same sources I have drawn (and linked) to? If so, then yes. Is AI likely to draw the same parallels that I see with the power structures that serve as guideposts for society and programming as the guiderails for AI? No. It strikes me that elements of my answers, particularly the answers to question 1, would be easy for a search engine (never mind a paragraph writing AI) to replicate. It might have some issue with the personalization that I tried to provide. In fact, it might give a better answer. Less susceptible to my personal interests in what the author wrote, or what they might have said. The answer to question 5, would probably lead to a variety of interpretations? Or maybe the AI would have a way to answer these sorts of self-examination questions? It reminds me of the Voigt-Kampff test from the movie Blade Runner, which is an empathy test designed to foil AI.

Blade Runner – Voight-Kampff Test

References:

Harris, A. (2018, November 1) Human languages vs programming languages. Medium. https://medium.com/@anaharris/human-languages-vs-programming-languages-c89410f13252

Hao, K. (2020, December 4) We read the paper that forced Timnit Gebru out of Google. Here’s what it says. MIT Technology Review. https://www.technologyreview.com/2020/12/04/1013294/google-ai-ethics-research-paper-forced-out-timnit-gebru

McCarthy, J. and Hayes, P. (1969) Some philosophical problems from the standpoint of artificial intelligence. John McCarthy’s Home Page. http://www-formal.stanford.edu/jmc/mcchay69.pdf

Sutton, R.S. (2020) John McCarthy’s definition of intelligence. Journal of Artificial General Intelligence 11(2), 66-67 http://www.incompleteideas.net/papers/Sutton-JAGI-2020.pdf

The Nobel Prize (1978, October 16) The Prize in Economics 1978. The Nobel Prize. https://www.nobelprize.org/prizes/economic-sciences/1978/press-release/

ETEC 511 – IP #1: Users, Uses and Usability

1. Formulate a conception of usability (based on the Issa and Isaias (2015) chapter on HCI and Usability). Use what you’ve learned about usability from that chapter—but you are not summarizing or repeating their ideas. Rather, you are setting out the idea of ‘usability’ you have put together from reading that chapter. Do NOT overly rely on quotes. And remember to use proper citation practices. If you are using text that is not your own, quote and cite it, including page numbers.

HCI (Human Computing Interaction) is essentially a translation service, in that it attempts to communicate between a machine and a human the purpose of the machine. Usability is the measurement of the success of that translation. If a piece of software or website is usable, then it is described as intuitive, easy to use, simple. To be usable, a designer must examine the functionality, efficiency, effectiveness of the software and take into consideration the user’s needs, context and satisfaction. (Issa and Isaias, 2015, p. 30) While this article was written only seven years ago, it seems like the authors only consider positive usage of technology and do not consider, or consider deeply, the idea of designing around bad actors. Wiegers contends that you should design around bad actors, and to prevent users from possibly misconstruing the information conveyed – in that usability should factor in not only the positive uses of a system, but also how it can be misused. (Wiegers, 2021)

2. Then, think about what is missing from this conception, from a specifically educational perspective, and on that basis try and patch together a reasonably grounded and defensible conception of educational usability.

While usability is a key concept in designing learning – especially the examination of context, and user/student needs, it is missing two other key components. While Issa and Isaias (2015) suggest that the user factors in HCI include motivation, enjoyment and experience level (p. 28) it does not adequately address cultural factors of the user/student. While culture will contribute to levels of access and equity, these factors are often great indicators of success in an educational context. This framework is very much built on western ways of knowing and draws from behaviourist theories of development. For instance, when the designed system works, the user is rewarded (by receiving information, having the computer complete a task, etc.). There is no real opportunity to design for remediation and it appears to have a very binary approach to solving complex problems.

3. Revisit Woolgar’s (challenging but rewarding!) account of “usability gone wrong,” which demonstrates several ways a usability study ended up configuring ‘users,’ thereby undermining the usefulness of usability. Identify and discuss 2 of Woolgar’s examples.

At the crux of Woolgar’s arguments of configuring the user during usability trials it was particularly interesting how he suggested that physical location of user testing is a factor in the results of the testing. Of course, when conducting research, you try to control those variables, and it is very clear (to me) that usability testing is far less rigorous than controlled, double-blind research. However, Woolgar (1990, p. 78) recounts how recalling computer features at Brunel University was different than when in the Stratus offices. If we take this as a common occurrence across users, then how we interact with computers will be different based on physical location. So, it follows that bringing users into a testing area to gather feedback on usability will be different than if the device were provided in their usual operating environment.

A second instance of configuring the users is the selection of who is eligible to participate in user testing (Woolgar, 1990, p. 83) – in this case it is noted that often early adopters, and people who are predisposed to like the product would be ideal testers. However, it is entirely unlikely that these people would provide you a new user’s perspective, or someone who was predisposed to not like computers, or be unfamiliar with computers. In fact, the opposite would likely be the case – users who were familiar and comfortable with computers. It only follows that someone who was familiar with computers would be at least more capable of using them, having a concept of what to do with them.

4. Finally, discuss the two excerpts quoted at the top of this IP, that have been drawn from your readings for this unit, and discuss differences you see in these 2 positions on the uses of usability.

Issa and Isaias (2015) are suggesting that user testing is a feedback mechanism to further improve software and hardware and Woolgar (1990) is suggesting that user testing is a confirmation mechanism – to confirm the assumptions made in designing software and hardware. I see both of these linked to a philosophical debate as to the role of computers in human’s lives – whether humans control computers, or computers determine the actions of humans – and the truth is somewhere in the middle.  It is dependent on your role with the computer. Computer programmers control what is possible and what is not within a game, or website. Human users subvert those possibilities through speedruns and other bending of the rules that humans put in place in the first place. Usability in the early days of computing would never have envisioned some of the ways people would have used computers.

References

Issa, T., & Isaias, P. (2015). Usability and human computer interaction (HCI) In Sustainable Design (pp. 19-35). Springer.

Woolgar, S. (1990). Configuring the user: The case of usability trials. The Sociological Review38(1, Suppl.), S58-S99.

Wiegars, K. (2021). Designing around bad actors and dangerous actions. UX Collective. https://uxdesign.cc/designing-around-bad-actors-and-dangerous-actions-8fc7984c510d

ETEC 511 – Truth and Reconciliation

The project brief was to find a document and explore how it portrays indigenous and First Nations peoples – and while it might have been easy to pick something historical, where you would judge the historical figure outside of the time, I thought that I would take on something from my lifetime.

The document I chose: People of Native Ancestry, A Resource Guide for the Primary and Junior Divisions (students).

I chose this document for a few reasons. One key reason being that it is a document from my lifetime and I certainly would have experienced the suggestions of this document from 1975 in my early elementary schooling experience (I started kindergarten in 1978). I am curious to understand the thinking of how teachers would have been instructed to teach about indigenous peoples during the time, and how my experience and admittedly limited understanding of the local Six Nations people growing up might have been reflected in this document. I really do not recall any of the lessons, or even if they were delivered.

This document serves two purposes. One, to help teachers understand and teach people with Indigenous ancestry and two, to teach “[a]s all Ontario children grow in their knowledge of native peoples, both native and non-native people will benefit. Tolerance in a multi-cultural society is built upon active participation in the process of learning about cultures other than one’s own.” (p. 8).

In searching the document the following terms were used to describe indigenous people(s):

IndianIndigenousAboriginalFirst NationsNativeNon-Native
619411

Specific Nation Mentions:

Cree: 9

Mohawk: 6

Ojibwe: 10

Algonquin: 1

One strong theme that arose throughout the writing is the othering of indigenous peoples. They were to be recognized as distinct, but the text treats indigenous people as if there was little to no history between indigenous and white people (outside of the foreward by Chief Dan George of the Burrard Indian Reserve, and the Appendix A, which spans 2 and a half pages -with a paragraph of veritable whitewashing of residential schools, which likely some parents might have experienced). How can one attempt to integrate into a “multi-cultural” society without at least a deeper understanding of history, and the injustice of the history which had been happening for (at that time) hundreds of years, is in modern context, unthinkable.

One other theme, and it is probably a key thing to note, this being a government document, it has chosen to use Native rather than any other language. Indian came up as part of a historical quote, or in the context of naming an act of Parliament or group. In fact Native was the most common reference, and when other children were mentioned they were non-Native. The act of constantly comparing, as if non-Native children might not have their own complexities, histories, familial demands, and approaches to learning and authority. There was a subtle, but present, holding up of (ostensibly white male) children as ideal, and Native as other. In many ways, the othering that was done throughout the document, undermines the front-and-centering of indigenous children by acknowledging their indigenousness. It is definitely a subtle thing, but definitely present.

ETEC 520 – Planning and Managing eLearning

Taking this course was a mistake. Well, for me it was. You might need the information. There were a few moments of learning, but for me, who plans and manages “elearning” (whatever that means) as a daily activity, the course was frustrating as it lacked the nuance of the day-to-day, it placed the institution at the centre of the planning when in reality, in my experience this is not planned at the institutional level – it requires a grassroots approach for many years before the institution codifies and standardizes it. The assignments were almost too focused on institutional needs (and I understand why they went this route with the design) – but in all likelihood, only a few of your graduates are going to be at that institutional level to influence change and by the time they get there, Tony Bates’ book will be horribly out of date and the lessons learned will not apply. I also never really got into a rhythm with this course. I’d literally read the readings on Monday, then think for four or five days, I’ve got to do the discussion…. Some weeks I couldn’t even do that. This course, for whatever reason broke my spirit. I’m not egotistical enough to suggest I know it all, I don’t. I think I never was able to connect the readings to the assignments, and the things that we were to do in the class didn’t ever really gel for me. Some of the gaps in the content were glaring for me as well.

In one assignment there’s an elearning readiness check – which assumes that the institution wants to engage in elearning at all! They can’t be ready if they don’t want to do it…. Then the tools that we could use to “assess” readiness were outdated and almost laughable. There was no mention of diversity, equity, accessibility or privacy in any of the assessment tools. Security was an afterthought. Interoperability, standards… those were not addressed as well. Cost was reduced to a line-item. Those are requirements in 2022, as in not optionals or nice to have, but as an institution you must look at technology and learning through those lens’. For a course to just skip over these issues is a bit disheartening.

Even if the assessment tools didn’t have those present – it’s easy to build that into the course by redesigning it to instead have the student design the readiness tool (which then releases the faculty from the dating of the material and the readings can be updated without requiring re-writes of the assessments) and build common factors through discussion and then design a “rubric” for assessment. Make that your first assignment. The second assignment is to look at implementation plans that are available. Analyze them for how your rubric might apply. This rubric could also be used for an RFP like scenario outside of the curriculum. Then re-write the rubric to address any gaps seen in implementation plans. Show some other rubrics. Critique the rubric as your final piece. Or have a reflective piece. Then you have a student-driven, student-centred course.

Admittedly I coasted through and put little effort into this. So I did the required minimum, slowly faded from discussions (which I hate when they’re so structured and stilted and non-organic). This wasn’t a fault of the course, it’s well designed, and was delivered by a facilitator that seemed to care (I would write truly cared, but I don’t know if that’s true or not). I, as a student, did not care. And for that I am sorry somewhat, because I should’ve been able to find a moment or a spot to hold up as worthwhile, but I couldn’t find that spot. So in some ways I failed this course, not marks-wise, but failed to be a good contributor. I was really disheartened by the lack of modern resources. I was really disappointed that this class, that I was honestly looking forward to at the beginning, was really frustrating for me. I can taste how close this is to a useful class for the modern context, but it just falls short. In a little bit of hindsight, it’s probably just a course that’s been in need of a refresh and probably is due up for a change shortly (fingers crossed!).

Oh, and to top it all off, I reused an APA cover sheet from a previous course, and the first time I copied it I didn’t know how to spell the facilitator’s name, so I gave it shot – as a placeholder – with the intention of correcting it later. I never did. To compound my utter stupidity, I submitted it, not once but twice, because the second time I just reused the same cover sheet and didn’t even bother checking. I did pull it together for the last submission, and sent off a mea culpa letter to the prof just to let them know I’m an idiot.

Engagement = Coercion?

I started writing this in 2018, and I still struggle with the ideas that I’m trying to express with this idea. Ultimately I’m talking about the power structure in classrooms, or online environments and how those who are uncomfortable with those power structures can do very little with the environments themselves to dilute the power differential.

I’m often troubled by the term engagement. If attention to a thing is the most important commodity in modern capitalism, is engagement worth more than mere attention? We have seen with things like video games that attention is one thing, but engagement is a whole other metric. There’s an emotional component to engagement that isn’t there with mere attention.

And is engagement a coercion strategy? Are we asking students to become invested in something based on the value we think it will add to a student’s learning, even using marks as a lever to get students to do what we want them to do?

PAY ATTENTION!

I totally remember having that yelled at me. The lie that’s embedded in that line is that it’s missing the obvious – to what? In most cases, the missive should read “Pay attention to me!” No wonder I did so mediocre in school – I don’t really react well to that, and I think most of us don’t react well to that sort of pandering. That sort of coercive effort of attention grabbing never worked well for me. Maybe it’s the belief I hold that “good work gets noticed” and as I’ve gotten older I still think that’s true somewhat. But it might be 20 years later, after it’s made the rounds and the artist has died. Or the author. Or the creator. You see that on YouTube now, with someone putting out a video in early 2009, and it comes up in a search and it’s great. And has 234 views. You have a whole algorithm in the way of finding things organically now, and with no real way to control how you are served content (and that’s probably the google killer – having an adjustable algorithm that feeds you not only what you want but how you want) content creators that are successful aren’t successful because of their content per se, it’s that they know how to manipulate the algorithm to get you to see the content.

Which brings us back to metrics and measurements. Modern engagement metrics have shifted language such that really it’s attention, and not engagement, that they’re measuring. It literally took close to four years for me to figure out what bothered me about engagement metrics. Now I know it’s not about engaging with someone, it’s about getting them to pay attention to you. It explains a lot about why modern advertising methods are all about “engagement” which is theoretically deeper than “attention” – but the metrics they use (click-throughs, time on page) really don’t speak to engagement, as it does to attention.

Now when I’m talking about engagement in a classroom that’s likely different than engagement in an online environment – but engagement in an online environment is measured using the same methods that are about attention – which is a bit of a passé way to look at engagement in a classroom. Paying attention to a lecture is different than engaging with a lecture – and paying attention to a post in the LMS is different than engaging with a post in the LMS. Engaging is more associated with doing something in an educational context. So in many ways applying the common way of measuring engagement is not going to elicit much useful information in an educational context. Yet I still see people building courses in such a way to try and leverage attention, rather than engagement.

What do you think will engage people better? A well formed discussion question, or a lengthy video with interactive “engagement” in the form of questions? I would think that a well formed discussion question might linger longer in one’s mind.