Today is the first official work day of my new doctoral researcher position at Delft University of Technology. After more than two years of laying the ground work, I’m starting out on a new challenge.
I remember sitting outside a Jewel coffee bar in Singapore1 and going over the various options for whatever would be next after shutting down Hubbub. I knew I wanted to delve into the impact of machine learning and data science on interaction design. And largely through process of elimination I felt the best place for me to do so would be inside of academia.
Back in the Netherlands, with help from Ianus Keller, I started making inroads at TU Delft, my first choice for this kind of work. I had visited it on and off over the years, coaching students and doing guest lectures. I’d felt at home right away.
There were quite a few twists and turns along the way but now here we are. Starting this month I am a doctoral candidate at Delft University of Technology’s faculty of Industrial Design Engineering.
Below is a first rough abstract of the research. But in the months to come this is likely to change substantially as I start hammering out a proper research plan. I plan to post the occasional update on my work here, so if you’re interested your best bet is probably to do the old RSS thing. There’s social media too, of course. And I might set up a newsletter at some point. We’ll see.
If any of this resonates, do get in touch. I’d love to start a conversation with as many people as possible about this stuff.
Intelligibility and Transparency of Smart Public Infrastructures: A Design Oriented Approach
This phd will explore how designers, technologists, and citizens can utilize rapid urban manufacturing and IoT technologies for designing urban space that expresses its intelligence from the intersection of people, places, activities and technology, not merely from the presence of cutting-edge technology. The key question is how smart public infrastructure, i.e. data-driven and algorithm-rich public infrastructures, can be understood by lay-people.
The design-oriented research will utilize a ‘research through design’ approach to develop a digital experience around the bridge and the surrounding urban space. During this extended design and making process the phd student will conduct empirical research to investigate design choices and their implications on (1) new forms of participatory data-informed design processes, (2) the technology-mediated experience of urban space, (3) the emerging relationship between residents and “their” bridge, and (4) new forms of data-informed, citizen led governance of public space.
At a recent Tech Solidarity NL meetup we dove into Value Sensitive Design. This approach had been on my radar for a while so when we concluded that for our community it would be useful to talk about how to practice ethical design and development of technology, I figured we should check it out.
Below, I have attempted to pull together the most salient points from what is a rather dense twenty-plus-slides deck. I hope it is of some use to those professional designers and developers who are looking for better ways of building technology that serves the interest of the many, not the few.
The departure point is the observation that “there is a need for an overarching theoretical and methodological framework with which to handle the value dimensions of design work.” In other words, something that accounts for what we already know about how to deal with values in design work in terms of theory and concepts, as well as methods and techniques.
This is of course not a new concern. For example, famed cyberneticist Norbert Wiener argued that technology could help make us better human beings, and create a more just society. But for it to do so, he argued, we have to take control of the technology.
We have to reject the “worshiping [of] the new gadgets which are our own creation as if they were our masters.” (Wiener 1953)
We can find many more similar arguments throughout the history of information technology. Recently such concerns have flared up in industry as well as society at large. (Not always for the right reasons in my opinion, but that is something we will set aside for now.)
To address these concerns, Value Sensitive Design was developed. It is “a theoretically grounded approach to the design of technology that accounts for human values in a principled and comprehensive manner throughout the design process.” It has been applied successfully for over 20 years.
But what is a value? In the literature it is defined as “what a person or group of people consider important in life.” I like this definition because it is easy to grasp but also underlines the slippery nature of values. Some things to keep in mind when talking about values:
In a narrow sense, the word “value” refers simply to the economic worth of an object. This is not the meaning employed by Value Sensitive Design.
Values should not be conflated with facts (the “fact/value distinction”) especially insofar as facts do not logically entail value.
“Is” does not imply “ought” (the naturalistic fallacy).
Values cannot be motivated only by an empirical account of the external world, but depend substantively on the interests and desires of human beings within a cultural milieu. (So contrary to what some right-wingers like to say: “Facts do care about your feelings.”)
Let’s dig into the way this all works. “Value Sensitive Design is an iterative methodology that integrates conceptual, empirical, and technical investigations.” So it distinguishes between three types of activities (“investigations”) and it prescribes cycling through these activities multiple times. Below are listed questions and notes that are relevant to each type of investigation. But in brief, this is how I understand them:
Defining the specific values at play in a project;
Observing, measuring, and documenting people’s behaviour and the context of use;
Analysing the ways in which a particular technology supports or hinders particular values.
Who are the direct and indirect stakeholders affected by the design at hand?
How are both classes of stakeholders affected?
What values are implicated?
How should we engage in trade-offs among competing values in the design, implementation, and use of information systems (e.g., autonomy vs. security, or anonymity vs. trust)?
Should moral values (e.g., a right to privacy) have greater weight than, or even trump, non-moral values (e.g., aesthetic preferences)?
How do stakeholders apprehend individual values in the interactive context?
How do they prioritise competing values in design trade-offs?
How do they prioritise individual values and usability considerations?
Are there differences between espoused practice (what people say) compared with actual practice (what people do)?
And, specifically focusing on organisations:
What are organisations’ motivations, methods of training and dissemination, reward structures, and economic incentives?
Not a list of questions here, but some notes:
Value Sensitive Design takes the position that technologies in general, and information and computer technologies in particular, have properties that make them more or less suitable for certain activities. A given technology more readily supports certain values while rendering other activities and values more difficult to realise.
Technical investigations involve the proactive design of systems to support values identified in the conceptual investigation.
Technical investigations focus on the technology itself. Empirical investigations focus on the individuals, groups, or larger social systems that configure, use, or are otherwise affected by the technology.
Value Sensitive Design enlarges the arena in which values arise to include not only the work place
Value Sensitive Design contributes a unique methodology that employs conceptual, empirical, and technical investigations, applied iteratively and integratively
Value Sensitive Design enlarges the scope of human values beyond those of cooperation (CSCW) and participation and democracy (Participatory Design) to include all values, especially those with moral import.
Value Sensitive Design distinguishes between usability and human values with ethical import.
Value Sensitive Design identifies and takes seriously two classes of stakeholders: direct and indirect.
Value Sensitive Design is an interactional theory
Value Sensitive Design builds from the psychological proposition that certain values are universally held, although how such values play out in a particular culture at a particular point in time can vary considerably
[ad 4] “By moral, we refer to issues that pertain to fairness, justice, human welfare and virtue, […] Value Sensitive Design also accounts for conventions (e.g., standardisation of protocols) and personal values”
[ad 5] “Usability refers to characteristics of a system that make it work in a functional sense, […] not all highly usable systems support ethical values”
[ad 6] “Often, indirect stakeholders are ignored in the design process.”
[ad 7] “values are viewed neither as inscribed into technology (an endogenous theory), nor as simply transmitted by social forces (an exogenous theory). […] the interactional position holds that while the features or properties that people design into technologies more readily support certain values and hinder others, the technology’s actual use depends on the goals of the people interacting with it. […] through human interaction, technology itself changes over time.”
[ad 8] “the more concretely (act-based) one conceptualises a value, the more one will be led to recognising cultural variation; conversely, the more abstractly one conceptualises a value, the more one will be led to recognising universals”
Value Sensitive Design doesn’t prescribe a particular process, which is fine by me, because I believe strongly in tailoring your process to the particular project at hand. Part of being a thoughtful designer is designing a project’s process as well. However, some guidance is offered for how to proceed in most cases. Here’s a list, plus some notes.
Start with a value, technology, or context of use
Identify direct and indirect stakeholders
Identify benefits and harms for each stakeholder group
Map benefits and harms onto corresponding values
Conduct a conceptual investigation of key values
Identify potential value conflicts
Integrate value considerations into one’s organisational structure
[ad 1] “We suggest starting with the aspect that is most central to your work and interests.”
[ad 2] “direct stakeholders are those individuals who interact directly with the technology or with the technology’s output. Indirect stakeholders are those individuals who are also impacted by the system, though they never interact directly with it. […] Within each of these two overarching categories of stakeholders, there may be several subgroups. […] A single individual may be a member of more than one stakeholder group or subgroup. […] An organisational power structure is often orthogonal to the distinction between direct and indirect stakeholders.”
[ad 3] “one rule of thumb in the conceptual investigation is to give priority to indirect stakeholders who are strongly affected, or to large groups that are somewhat affected […] Attend to issues of technical, cognitive, and physical competency. […] personas have a tendency to lead to stereotypes because they require a list of “socially coherent” attributes to be associated with the “imagined individual.” […] we have deviated from the typical use of personas that maps a single persona onto a single user group, to allow for a single persona to map onto to multiple stakeholder groups”
[ad 4] “In some cases, the corresponding values will be obvious, but not always.”
[ad 5] “the philosophical ontological literature can help provide criteria for what a value is, and thereby how to assess it empirically.”
[ad 6] “value conflicts should usually not be conceived of as “either/or” situations, but as constraints on the design space.”
[ad 7] “In the real world, of course, human values (especially those with ethical import) may collide with economic objectives, power, and other factors. However, even in such situations, Value Sensitive Design should be able to make positive contributions, by showing alternate designs that better support enduring human values.”
This table is a useful heuristic tool for values that might be considered. The authors note that it is not intended as a complete list of human values that might be implicated. Another more elaborate tool of a similar sort are the Envisioning Cards.
For the ethics nerds, it may be interesting to note that most of the values in this table hinge on the deontological and consequentialist moral orientations. In addition, the authors have chose several other values related to system design.
When doing the empirical investigations you’ll probably rely on stakeholder interviews quite heavily. Stakeholder interviews shouldn’t be a new thing to any design professional worth their salt. But the authors do offer some practical pointers to keep in mind.
First of all, keep the interview somewhat open-ended. This means conducting a semi-structured interview. This will allow you to ask the things you want to know, but also creates the opportunity for new and unexpected insights to emerge.
Laddering—repeatedly asking the question “Why?” can get you quite far.
The most important thing, before interviewing stakeholders, is to have a good understanding of the subject at hand. Demarcate it using criteria that can be explained to outsiders. Use descriptions of issues or tasks for participants to engage in, so that the subject of the investigation becomes more concrete.
Two things I find interesting here. First of all, we are encouraged to map the relationship between design trade-offs, value conflicts and stakeholder groups. The goal of this exercise is to be able to see how stakeholder groups are affected in different ways.
The second useful suggestion for technical investigations is to build flexibility into a product or service’s technical infrastructure. The reason for this is that over time, new values and value conflicts can emerge. As designers we are not always around anymore once a system is deployed so it is good practice to enable the stakeholders to adapt our design to their evolving needs. (I was very much reminded of the approach advocated by Stewart Brand in How Buildings Learn.)
When discussing matters of ethics in design with peers I often notice a reluctance to widen the scope of our practice to include these issues. Frequently, folks argue that since it is impossible to foresee all the potential consequences of design choices, we can’t possibly be held accountable for all the terrible things that can happen as a result of a new technology being introduced into society.
I think that’s a misunderstanding of what ethical design is about. We may not always be directly responsible for the consequences of our design (both good and bad). But we are responsible for what we choose to make part of our concerns as we practice design. This should include the values considered important by the people impacted by our designs.
In the 1996 article mentioned at the start of this post, Friedman concludes as follows:
“As with the traditional criteria of reliability, efficiency, and correctness, we do not require perfection in value-sensitive design, but a commitment. And progress.” (Friedman 1996)
I think that is an apt place to end it here as well.
Friedman, Batya, Peter Kahn, and Alan Borning. “Value sensitive design: Theory and methods.” University of Washington technical report (2002): 02–12.
Le Dantec, Christopher A., Erika Shehan Poole, and Susan P. Wyche. “Values as lived experience: evolving value sensitive design in support of value discovery.” Proceedings of the SIGCHI conference on human factors in computing systems.ACM, 2009.
Borning, Alan, and Michael Muller. “Next steps for value sensitive design.” Proceedings of the SIGCHI conference on human factors in computing systems.ACM, 2012.
Freidman, B., P. Kahn, and A. Borning. “Value sensitive design and information systems.” Human–computer interaction in management information systems: Foundations (2006): 348–372.
At the end of last year I was invited to speak at the PLAYTrack conference in Aarhus about the workplace change management games made by Hubbub. It turned out to be a great opportunity to reconnect with the play research community.
I was very much impressed by the program assembled by the organisers. People came from a wide range of disciplines and crucially, there was ample time to discuss and reflect on the materials presented. As I tweeted afterwards, this is a thing that most conference organisers get wrong.
Back in Utrecht after a wonderful time in Århus attending #PLAYTrack. The lectures were uniformly fascinating but the one thing this conference really got right was the ample time to reflect and discuss. Really elevates the experience to something more than the usual info dump.
The abstract for my talk is below, which covers most of what I talked about. I tried to give people a good sense of:
what the games consisted of,
what we were aiming to achieve,
how both the fiction and the player activities supported these goals,
how we made learning outcomes visible to our players and clients,
and finally how we went about designing and developing these games.
Both projects have solid write-ups over at the Hubbub website, so I’ll just point to those here: Code 4 and Ripple Effect.
In the final section of the talk I spent a bit of time reflecting on how I would approach projects like this today. After all, it has been seven years since we made Code 4, and four years since Ripple Effect. That’s ages ago and my perspective has definitely changes since we made these.
First of all, I would get even more serious about co-designing with players at every step. I would recruit representatives of players and invest them with real influence. In the projects we did, the primary vehicle for player influence was through playtesting. But this is necessarily limited. I also won’t pretend this is at all easy to do in a commercial context.
But, these games are ultimately about improving worker productivity. So how do we make it so that workers share in the real-world profits yielded by a successful culture change?
I know of the existence of participatory design but from my experience it is not a common approach in the industry. Why?
Value sensitive design
On a related note, I would get more serious about what values are supported by the system, in whose interest they are and where they come from. Early field research and workshops with audience do surface some values but values from customer representatives tend to dominate. Again, the commercial context we work in is a potential challenge.
I know of value sensitive design, but as with participatory design, it has yet to catch on in a big way in the industry. So again, why is that?
One thing I continue to be interested in is to reduce the complexity of a game system’s physical affordances (which includes its code), and to push even more of the substance of the game into those social allowances that make up the non-material aspects of the game. This allows for spontaneous renegotiation of the game by the players. This is disintermediation as a strategy. David Kanaga’s take on games as toys remains hugely inspirational in this regard, as does Bernard De Koven’s book The Well Played Game.
Gamefulness versus playfulness
Code 4 had more focus on satisfying the need for autonomy. Ripple Effect had more focus on competence, or in any case, it had less emphasis on autonomy. There was less room for ‘play’ around the core digital game. It seems to me that mastering a subjective simulation of a subject is not necessarily what a workplace game for culture change should be aiming for. So, less gameful design, more playful design.
Finally, the agency model does not enable us to stick around for the long haul. But workplace games might be better suited to a setup where things aren’t thought of as a one-off project but more of an ongoing process.
In How Buildings Learn, Stewart Brand talks about how architects should revisit buildings they’ve designed after they are built to learn about how people are actually using them. He also talks about how good buildings are buildings that its inhabitants can adapt to their needs. What does that look like in the context of a game for workplace culture change?
Playful Design for Workplace Change Management
Code 4 (2011, commissioned by the Tax Administration of the Netherlands) and Ripple Effect (2013, commissioned by Royal Dutch Shell) are both games for workplace change management designed and developed by Hubbub, a boutique playful design agency which operated from Utrecht, The Netherlands and Berlin, Germany between 2009 and 2015. These games are examples of how a goal-oriented serious game can be used to encourage playful appropriation of workplace infrastructure and social norms, resulting in an open-ended and creative exploration of new and innovative ways of working.
Serious game projects are usually commissioned to solve problems. Solving the problem of cultural change in a straightforward manner means viewing games as a way to persuade workers of a desired future state. They typically take videogame form, simulating the desired new way of working as determined by management. To play the game well, players need to master its system and by extension—it is assumed—learning happens.
These games can be be enjoyable experiences and an improvement on previous forms of workplace learning, but in our view they decrease the possibility space of potential workplace cultural change. They diminish worker agency, and they waste the creative and innovative potential of involving them in the invention of an improved workplace culture.
We instead choose to view workplace games as an opportunity to increase the space of possibility. We resist the temptation to bake the desired new way of working into the game’s physical and digital affordances. Instead, we leave how to play well up to the players. Since these games are team-based and collaborative, players need to negotiate their way of working around the game among themselves. In addition, because the games are distributed in time—running over a number of weeks—and are playable at player discretion during the workday, players are given license to appropriate workplace infrastructure and subvert social norms towards in-game ends.
We tried to make learning tangible in various ways. Because the games at the core are web applications to which players log on with individual accounts we were able to collect data on player behaviour. To guarantee privacy, employers did not have direct access to game databases and only received anonymised reports. We took responsibility for player learning by facilitating coaching sessions in which they could safely reflect on their game experiences. Rounding out these efforts, we conducted surveys to gain insight into the player experience from a more qualitative and subjective perspective.
These games offer a model for a reasonably democratic and ethical way of doing game-based workplace change management. However, we would like to see efforts that further democratise their design and development—involving workers at every step. We also worry about how games can be used to create the illusion of worker influence while at the same time software is deployed throughout the workplace to limit their agency.
Our examples may be inspiring but because of these developments we feel we can’t continue this type of work without seriously reconsidering our current processes, technology stacks and business practices—and ultimately whether we should be making games at all.
Returning to what is something of an annual tradition, these are the books I’ve read in 2017. I set myself the goal of getting to 36 and managed 38 in the end. They’re listed below with some commentary on particularly memorable or otherwise noteworthy reads. To make things a bit more user friendly I’ve gone with four broad buckets although as you’ll see within each the picks range across genres and subjects.
I always have one piece of fiction or narrative non-fiction going. I have a long-standing ‘project’ of reading cult classics. I can’t settle on a top pick for the first category so it’s going to have to be a tie between Lowry’s alcohol-drenched tale of lost love in pre-WWII Mexico, and Salter’s unmatched lyrical prose treatment of a young couple’s liaisons as imagined by a lecherous recluse in post-WWII France.
When I feel like something lighter I tend to seek out sci-fi written from before I was born. (Contemporary sci-fi more often than not disappoints me with its lack of imagination, or worse, nostalgia for futures past. I’m looking at you, Cline.) My top pick here would be the Strugatsky brothers, who blew me away with their weird tale of a world forever changed by the inexplicable visit by something truly alien.
I’ve also continued to seek out works by women, although I’ve been less strict with myself in this department than previous years. Here I’m ashamed to admit it took me this long to finally read anything by Woolf because Mrs Dalloway is every bit as good as they say it is. I recommend seeking out the annotated Penguin addition for additional insights into the many things she references.
I’ve also sometimes picked up a newer book because it popped up on my radar and I was just really excited about reading it. Most notably Dolan’s retelling of the Iliad in all its glorious, sad and gory detail, updated for today’s sensibilities.
Each time I read a narrative treatment of history or current affairs I feel like I should be doing more of it. All of these are recommended but Kapuściński towers over all with his heart-wrenching first-person account of the Iranian revolution.
A few books on design and technology here, although most of my ‘professional’ reading was confined to academic papers this year. I find those to be a more effective way of getting a handle on a particular subject. Books published on my métier are notoriously fluffy. I’ll point out Löwgren for a tough but rewarding read on how to do interaction design in a non-dogmatic but reflective way.
I got into leftist politics quite heavily this year and tried to educate myself a bit on contemporary anti-capitalist thinking. Fisher’s book is a most interesting and also amusing diagnosis of the current political and economic world system through a cultural lens. It’s a shame he’s no longer with us, I wonder what he would have made of recent events.
I decided to work my way through a bunch of roleplaying game books all ‘powered by the apocalypse’ – a family of games which I have been aware of for quite a while but haven’t had the opportunity to play myself. I like reading these because I find them oddly inspirational for professional purposes. But I will point to the original Apocalypse World as the one must-read as Baker remains one of the designers I am absolutely in awe of for the ways in which he manages to combine system and fiction in truly inventive ways.
The Perilous Wilds, Jason Lutes
Urban Shadows: Political Urban Fantasy Powered by the Apocalypse, Andrew Medeiros
Dungeon World, Sage LaTorra
Apocalypse World, D. Vincent Baker
I don’t usually read poetry for reasons similar to how I basically stopped reading comics earlier: I can’t seem to find a good way of discovering worthwhile things to read. The collection below was a gift, and a delightful one.
As always, I welcome suggestions for what to read next. I’m shooting for 36 again this year and plan to proceed roughly as I’ve been doing lately—just meander from book to book with a bias towards works that are non-anglo, at least as old as I am, and preferably weird or inventive.
We developed three exercises, one for each type of Wekinator output: regression, classification and dynamic time warping.
In contrast to the first version, we had two hours to run through the whole thing, in stead of a day… So we had to cut some corners, and doubled down on walking participants through a number of exercises so that they would come out of it with some readily applicable skills.
We dubbed the workshop ‘prototyping the useless butler’, with thanks to Philip van Allen for the suggestion to frame the exercises around building something non-productive so that the focus was shifted to play and exploration.
All of the code, the circuit diagram and slides are over on GitHub. But I’ll summarise things here.
We spent a very short amount of time introducing machine learning. We used Google’s Teachable Machine as an example and contrasted regular programming with using machine learning algorithms to train models. The point was to provide folks with just enough conceptual scaffolding so that the rest of the workshop would make sense.
We then introduced our ‘toolchain’ which consists of Wekinator, the Arduino MKR1000 module and the OSC protocol. The aim of this toolchain is to allow designers who work in the IoT space to get a feel for the material properties of machine learning through hands-on tinkering. We tried to create a toolchain with as few moving parts as possible, because each additional component would introduce another point of failure which might require debugging. This toolchain would enable designers to either use machine learning to rapidly prototype interactive behaviour with minimal or no programming. It can also be used to prototype products that expose interactive machine learning features to end users. (For a speculative example of one such product, see Bjørn Karmann’s Objectifier.)
Participants were then asked to set up all the required parts on their own workstation. A list can be found on the Useless Butler GitHub page.
We then proceeded to build the circuit. We provided all the components and showed a Fritzing diagram to help people along. The basic idea of this circuit, the eponymous useless butler, was to have a sufficiently rich set of inputs and outputs with which to play, that would suit all three types of Wekinator output. So we settled on a pair of photoresistors or LDRs as inputs and an RGBLED as output.
With the prerequisites installed and the circuit built we were ready to walk through the examples. For regression we mapped the continuous stream of readings from the two LDRs to three outputs, one each for the red, green and blue of the LED. For classification we put the state of both LDRs into one of four categories, each switching the RGBLED to a specific color (cyan, magenta, yellow or white). And finally, for dynamic time warping, we asked Wekinator to recognise one of three gestures and switch the RGBLED to one of three states (red, green or off).
When we reflected on the workshop afterwards, we agreed we now have a proven concept. Participants were able to get the toolchain up and running and could play around with iteratively training and evaluating their model until it behaved as intended.
However, there is still quite a bit of room for improvement. On a practical note, quite a bit of time was taken up by the building of the circuit, which isn’t the point of the workshop. One way of dealing with this is to bring those to a workshop pre-built. Doing so would enable us to get to the machine learning quicker and would open up time and space to also engage with the participants about the point of it all.
We’re keen on bringing this workshop to more settings in future. If we do, I’m sure we’ll find the opportunity to improve on things once more and I will report back here.
Many thanks to Iskander and the rest of the ThingsCon team for inviting us to the conference.
Earlier this year I coached Design for Interaction master students at Delft University of Technology in the course Research Methodology. The students organised three seminars for which I provided the claims and assigned reading. In the seminars they argued about my claims using the Toulmin Model of Argumentation. The readings served as sources for backing and evidence.
The claims and readings were all related to my nascent research project about machine learning. We delved into both designing for machine learning, and using machine learning as a design tool.
Below are the readings I assigned, with some notes on each, which should help you decide if you want to dive into them yourself.
The only non-academic piece in this list. This served the purpose of getting all students on the same page with regards to what machine learning is, its applications of machine learning in interaction design, and common challenges encountered. I still can’t think of any other single resource that is as good a starting point for the subject as this one.
Fiebrink’s Wekinator is groundbreaking, fun and inspiring so I had to include some of her writing in this list. This is mostly of interest for those looking into the use of machine learning for design and other creative and artistic endeavours. An important idea explored here is that tools that make use of (interactive, supervised) machine learning can be thought of as instruments. Using such a tool is like playing or performing, exploring a possibility space, engaging in a dialogue with the tool. For a tool to feel like an instrument requires a tight action-feedback loop.
A really good survey of how designers currently deal with machine learning. Key takeaways include that in most cases, the application of machine learning is still engineering-led as opposed to design-led, which hampers the creation of non-obvious machine learning applications. It also makes it hard for designers to consider ethical implications of design choices. A key reason for this is that at the moment, prototyping with machine learning is prohibitively cumbersome.
The second Fiebrink piece in this list, which is more of a deep dive into how people use Wekinator. As with the chapter listed above this is required reading for those working on design tools which make use of interactive machine learning. An important finding here is that users of intelligent design tools might have very different criteria for evaluating the ‘correctness’ of a trained model than engineers do. Such criteria are likely subjective and evaluation requires first-hand use of the model in real time.
Bostrom, Nick, and Eliezer Yudkowsky. 2014. “The Ethics of Artificial Intelligence.” In The Cambridge Handbook of Artificial Intelligence, edited by Keith Frankish and William M Ramsey, 316–34. Cambridge: Cambridge University Press. doi:10.1017/CBO9781139046855.020.
Bostrom is known for his somewhat crazy but thoughtprovoking book on superintelligence and although a large part of this chapter is about the ethics of general artificial intelligence (which at the very least is still a way out), the first section discusses the ethics of current “narrow” artificial intelligence. It makes for a good checklist of things designers should keep in mind when they create new applications of machine learning. Key insight: when a machine learning system takes on work with social dimensions—tasks previously performed by humans—the system inherits its social requirements.
Finally, a feet-in-the-mud exploration of what it actually means to design for machine learning with the tools most commonly used by designers today: drawings and diagrams of various sorts. In this case the focus is on using machine learning to make an interface adaptive. It includes an interesting discussion of how to balance the use of implicit and explicit user inputs for adaptation, and how to deal with inference errors. Once again the limitations of current sketching and prototyping tools is mentioned, and related to the need for designers to develop tacit knowledge about machine learning. Such tacit knowledge will only be gained when designers can work with machine learning in a hands-on manner.
I provided this to students so that they get some additional grounding in the various kinds of prototyping that are out there. It helps to prevent reductive notions of prototyping, and it makes for a nice complement to Buxton’s work on sketching.
Some of the papers refer to machine learning as a “design material” and this paper helps to understand what that idea means. Software is a material without qualities (it is extremely malleable, it can simulate nearly anything). Yet, it helps to consider it as a physical material in the metaphorical sense because we can then apply ways of design thinking and doing to software programming.
This is not exactly a now page, but I thought I would write up what I am doing at the moment since last reporting on my status in my end-of-year report.
The majority of my workdays are spent doing freelance design consulting. My primary gig has been through Eend at the Dutch Victim Support Foundation, where until very recently I was part of a team building online services. I helped out with product strategy, setting up a lean UX design process, and getting an integrated agile design and development team up and running. The first services are now shipping so it is time for me to move on, after 10 months of very gratifying work. I really enjoy working in the public sector and I hope to be doing more of it in future.
So yes, this means I am available and you can hire me to do strategy and design for software products and services. Just send me an email.
Shortly before the Dutch national elections of this year, Iskander and I gathered a group of fellow tech workers under the banner of “Tech Solidarity NL” to discuss the concerning lurch to the right in national politics and what our field can do about it. This has developed into a small but active community who gather monthly to educate ourselves and develop plans for collective action. I am getting a huge boost out of this. Figuring out how to be a leftist in this day and age is not easy. The only way to do it is to practice and for that reflection with peers is invaluable. Building and facilitating a group like this is hugely educational too. I have learned a lot about how a community is boot-strapped and nurtured.
And finally, the last major thing on my plate is a continuing effort to secure a PhD position for myself. I am getting great support from people at Delft University of Technology, in particular Gerd Kortuem. I am focusing on internet of things products that have features driven by machine learning. My ultimate aim is to develop prototyping tools for design and development teams that will help them create more innovative and more ethical solutions. The first step for this will be to conduct field research inside companies who are creating such products right now. So I am reaching out to people to see if I can secure a reasonable amount of potential collaborators for this, which will go a long way in proving the feasibility of my whole plan.
If you know of any companies that develop consumer-facing products that have a connected hardware component and make use of machine learning to drive features, do let me know.
That’s about it. Freelance UX consulting, leftist tech-worker organising and design-for-machine-learning research. Quite happy with that mix, really.
On May 24 of this year, Niels ’t Hooft and myself ran a workshop titled ‘Hybrid Writing for Conversational Interfaces’ at TU Delft. Our aim was twofold: teach students about writing characters and dialog, and teach them how to prototype chat interfaces.
We spent a day with roughly thirty industrial design students alternating between bits of theory, writing exercises, instructions on how to use Twine (our prototyping tool of choice) and closed out with a small project and a show and tell.
I was very pleased to see prototypes with quite a high level of complexity and sophistication at the end of the day. And throughout, I could tell students were enjoying themselves writing and building interactive conversations.
Here’s a rough outline of how the workshop was structured.
After briefly introducing ourselves, Niels presented a mini-lecture on interactive fiction. A highlight for me was a two-by-two of the ways in which fiction and software can intersect.
I then took over and did a show and tell of the absolute basics of using Twine. Things like creating passages, linking them, creating branches and testing and publishing your story.
The first exercise after this was for students to take what they just learned about Twine and try to create a very simple interactive story.
After a coffee break, Niels then presented his second mini-lecture on the very basics of writing. With a particular focus on writing characters and dialog. This included a handy cheatsheet for things to consider while writing.
In our second exercise students worked in pairs. They first each created a character, which they then described to each other. They then first planned out the structure of an encounter between these two characters. And finally they collaboratively wrote the dialogue for this encounter. They were required to stick to Hollywood formatting. Niels and I then did a reading of a few (to great amusement of all present) to close out the morning section of the workshop.
After lunch Niels presented his third and final mini-lecture of the day, on conversational interfaces, relying heavily on the great work of our friend Alper in his book on the subject.
I then took over for the second show and tell. Here we ramped up the challenge and introduced the Twine Texting Project – a framework for prototyping conversational interfaces in Twine. On GitHub, you can find the starter file I had prepared for this section.
The third and final exercise of the day was for students to take what they learned about writing dialog, and prototyping chat interfaces, and to build an interactive prototype of a conversational interface or interactive fiction in chat format. They could either build off of the dialog they have created in the previous exercise, or start from scratch.
We finished the day with demos, where put the Twine story on the big screen and as a group chose what options to select. After each demo the creator would open up the Twine file and walk us through how they had built it. It was pretty cool to see how many students had put what they had learned to very creative uses.
Reflecting on the workshop afterwards, we felt the structure was nicely balanced between theory and practice. The difficulty level was such that students did learn some new things which they could incorporate into future projects, but still built on skills they had already acquired. The choice for Twine worked out well too since it is highly accessible. Non-technical students managed to create something interactive, and more advanced students could apply what they knew about code to produce more sophisticated prototypes.
For future workshops we did feel we could improve on building a bridge between the writing for interactive fiction and writing for conversational interfaces of software products and services. This would require some adaptation of the mini lectures and a slightly different emphasis in the exercises. The key would be to have students imagine existing products and services as characters, and to then write dialog for interactions and prototype them. For a future iteration of the workshop, this would be worth exploring further.
A few weeks ago I facilitated a discussion on ‘advocacy in a post-truth era’ at the European Digital Rights Initiative’s annual general assembly. And last night I was part of a discussion on fake news at a behaviour design meetup in Amsterdam. This was a good occasion to pull together some of my notes and figure out what I think is true about the ‘fake news’ phenomenon.
There is plenty of good writing out there exploring the history and current state of post-truth political culture.
Kellyanne Conway’s “alternative facts” and Michael Gove’s “I think people have had enough of experts” are just two examples of the right’s appropriation of what I would call epistemological relativism. Post-modernism was fun while it worked to advance our leftist agenda. But now that the tables are turned we’re not enjoying it quite as much anymore, are we?
Part of the fact-free politics playbook goes back at least as far as big tobacco’s efforts to discredit the anti-smoking lobby. “Doubt is our product” still applies to modern day reactionary movements such as climate change deniers and anti-vaxers.
The double whammy of news industry commercialisation and internet platform consolidation has created fertile ground for coordinated efforts by various groups to turn the sowing of doubt all the way up to eleven.
There is Russia’s “firehose of falsehood” which sends a high volume of messages across a wide range of channels with total disregard for truth or even consistency in a rapid, continuous and repetitive fashion. They seem to be having fun destabilising western democracies — including the Netherlands — without any apparent end-goal in mind.
And then there is the outrage marketing leveraged by trolls both minor and major. Pissing off mainstream media builds an audience on the fringes and in the underground. Journalists are held hostage by figures such as Milo because they depend on stories that trigger strong emotions for distribution, eyeballs, clicks and ultimately revenue.
So, given all of this, what is to be done? First some bad news. Facts, the weapon of choice for liberals, don’t appear to work. This is empirically evident from recent events, but it also appears to be borne out by psychology.
Facts are often more complicated than the untruths they are supposed to counter. It is also easier to remember a simple lie than a complicated truth. Complicating matters further, facts tend to be boring. Finally, and most interestingly, there is something called the ‘backfire effect’: we become more entrenched in our views when confronted with contradicting facts, because they are threatening to our group identities.
More bad news. Given the speed at which falsehoods spread through our networks, fact-checking is useless. Fact-checking is after-the-fact-checking. Worse, when media fact-check falsehoods on their front pages they are simply providing even more airtime to them. From a strategic perspective, when you debunk, you allow yourself to be captured by your opponent’s frame, and you’re also on the defensive. In Boydian terms you are caught in their OODA loop, when you should be working to take back the initiative, and you should be offering an alternative narrative.
I am not hopeful mainstream media will save us from these dynamics given the realities of the business models they operate inside of. Journalists inside of these organisations are typically overworked, just holding on for dear life and churning out stories at a rapid clip. In short, there is no time to orient and manoeuvre. For bad-faith actors, they are sitting ducks.
What about literacy? If only people knew about churnalism, the attention economy, and filter bubbles ‘they’ would become immune to the lies peddled by reactionaries and return to the liberal fold. Personally I find these claims highly unconvincing not to mention condescending.
My current working theory is that we, all of us, buy into the stories that activate one or more of our group identities, regardless of wether they are fact-based or outright lies. This is called ‘motivated reasoning’. Since this is a fact of psychology, we are all susceptible to it, including liberals who are supposedly defenders of fact-based reasoning.
Seriously though, what about literacy? I’m sorry, no. There is evidence that scientific literacy actually increases polarisation. Motivated reasoning trumps factual knowledge you may have. The same research shows however that curiosity in turn trumps motivated reasoning. The way I understand the distinction between literacy and curiosity is that the former is about knowledge while the latter is about attitude. Motivated reasoning isn’t counteracted by knowing stuff, but by wanting to know stuff.
This is a mixed bag. Offering facts is comparatively easy. Sparking curiosity requires storytelling which in turn requires imagination. If we’re presented with a fact we are not invited to ask questions. However, if we are presented with questions and those questions are wrapped up in stories that create emotional stakes, some of the views we hold might be destabilised.
In other words, if doubt is the product peddled by our opponents, then we should start trafficking in curiosity.
On Wednesday Péter Kun, Holly Robbins and myself taught a one-day workshop on machine learning at Delft University of Technology. We had about thirty master’s students from the industrial design engineering faculty. The aim was to get them acquainted with the technology through hands-on tinkering with the Wekinator as central teaching tool.
The reasoning behind this workshop is twofold.
On the one hand I expect designers will find themselves working on projects involving machine learning more and more often. The technology has certain properties that differ from traditional software. Most importantly, machine learning is probabilistic in stead of deterministic. It is important that designers understand this because otherwise they are likely to make bad decisions about its application.
The second reason is that I have a strong sense machine learning can play a role in the augmentation of the design process itself. So-called intelligent design tools could make designers more efficient and effective. They could also enable the creation of designs that would otherwise be impossible or very hard to achieve.
The workshop explored both ideas.
The structure was roughly as follows:
In the morning we started out providing a very broad introduction to the technology. We talked about the very basic premise of (supervised) learning. Namely, providing examples of inputs and desired outputs and training a model based on those examples. To make these concepts tangible we then introduced the Wekinator and walked the students through getting it up and running using basic examples from the website. The final step was to invite them to explore alternative inputs and outputs (such as game controllers and Arduino boards).
In the afternoon we provided a design brief, asking the students to prototype a data-enabled object with the set of tools they had acquired in the morning. We assisted with technical hurdles where necessary (of which there were more than a few) and closed out the day with demos and a group discussion reflecting on their experiences with the technology.
As I tweeted on the way home that evening, the results were… interesting.
Not all groups managed to put something together in the admittedly short amount of time they were provided with. They were most often stymied by getting an Arduino to talk to the Wekinator. Max was often picked as a go-between because the Wekinator receives OSC messages over UDP, whereas the quickest way to get an Arduino to talk to a computer is over serial. But Max in my experience is a fickle beast and would more than once crap out on us.
The groups that did build something mainly assembled prototypes from the examples on hand. Which is fine, but since we were mainly working with the examples from the Wekinator website they tended towards the interactive instrument side of things. We were hoping for explorations of IoT product concepts. For that more hand-rolling was required and this was only achievable for the students on the higher end of the technical expertise spectrum (and the more tenacious ones).
The discussion yielded some interesting insights into mental models of the technology and how they are affected by hands-on experience. A comment I heard more than once was: Why is this considered learning at all? The Wekinator was not perceived to be learning anything. When challenged on this by reiterating the underlying principles it became clear the black box nature of the Wekinator hampers appreciation of some of the very real achievements of the technology. It seems (for our students at least) machine learning is stuck in a grey area between too-high expectations and too-low recognition of its capabilities.
These results, and others, point towards some obvious improvements which can be made to the workshop format, and to teaching design students about machine learning more broadly.
We can improve the toolset so that some of the heavy lifting involved with getting the various parts to talk to each other is made easier and more reliable.
We can build examples that are geared towards the practice of designing IoT products and are ready for adaptation and hacking.
And finally, and probably most challengingly, we can make the workings of machine learning more transparent so that it becomes easier to develop a feel for its capabilities and shortcomings.
We do intend to improve and teach the workshop again. If you’re interested in hosting one (either in an educational or professional context) let me know. And stay tuned for updates on this and other efforts to get designers to work in a hands-on manner with machine learning.
Special thanks to the brilliant Ianus Keller for connecting me to Péter and for allowing us to pilot this crazy idea at IDE Academy.
Sources used during preparation and running of the workshop:
The Wekinator – the UI is infuriatingly poor but when it comes to getting started with machine learning this tool is unmatched.
Arduino – I have become particularly fond of the MKR1000 board. Add a lithium-polymer battery and you have everything you need to prototype IoT products.
OSC for Arduino – CNMAT’s implementation of the open sound control (OSC) encoding. Key puzzle piece for getting the above two tools talking to each other.