Ellie Young: Grounding Knowledge Graphs in the Humanities – Episode 4

Podcast: Play in new window | Download

Subscribe: Apple Podcasts | Spotify | Amazon Music | Android | Youtube Music | RSS

Ellie Young effortlessly connects the human and technical elements that go into ontologies and knowledge graph building.

Ellie came to the world of knowledge graphs with backgrounds in both literature and sustainability. “If the world wasn’t on fire,” she says, ” I would probably be writing novels.”

That sense of urgency drives her work at Common Action, a platform she is creating to address climate change and advance sustainability. She also applies her knowledge graph expertise in projects like HelioWeb at NASA, which connects scientists in the field of heliophysics.

We talked about:

• her work at Common Action, a platform for climate and for sustainability that uses knowledge graph technology
• her work at NASA to facilitate collaboration and expose knowledge across the domain of heliophysics (the study of the sun)
• how personal knowledge graphs can connect individuals and collectives of people
• how her background in design, art,literature, and the humanities manifests in her knowledge graph work
• her desire to leverage metadata and capabilities like her language knowledge to facilitate topical discovery
• the interplay between the efficiencies that AI tech like LLMs offer and the uniquely imaginative variations that human beings create
• the importance of the practice of design in advancing the productive use of information
• how user experience design connects to ontologies and back-end tech
• how she applies, and imagines how others might apply, a literary mindset to ontology practice
• how she applied ethnographic methods from anthropology to a paper she co-authored on the NASA HelioWeb ontology
• her ongoing call for volunteers to help with her Common Action program, specifically a current need for creating a “phenomena ontology”

Ellie’s bio

Ellie Young brings knowledge to communities to catalyze successful, local actions to address climate/sustainability problems.

She is the founder of Common Action, an innovation network facilitating climate and sustainability action through the development of community and knowledge graph technology.

Previously she served as Head of Community and Director of Conference Operations at The Knowledge Graph Conference.

Connect with Ellie online

• LinkedIn
• ellie at common-action dot org

Resources

• The cultural-social nucleus of an open community: A multi-level community knowledge graph and NASA application, Applied Computing and Geosciences
• Common Action vision

Video

Here’s the video version of our conversation:

Podcast intro transcript

This is the Knowledge Graph Insights podcast, episode number 4. In the domains of ontology engineering and the semantic web, there are plenty of people with advanced technical skills. Practitioners with social-science skills, well-developed literary instincts, and a design mindset are harder to find. Ellie Young smoothly navigates the technical and linguistic worlds that intersect in knowledge graphs, applying her humanities mindset to projects that connect scientists at NASA and address climate change and sustainability.

Interview transcript

Larry:
Okay. Hi everyone. Welcome to episode number four of the Knowledge Graph Insights podcast. I am super delighted today to welcome to the show Ellie Young. Ellie is the founder of Common Action, a sustainability and climate change activist organization. She’s also … The way I first met her, she’s the former head of community for the Knowledge Graph Conference, and one of the people who really ushered a lot of people into this community. So welcome Ellie. Tell the folks a little bit more about what you’re up to these days.

Ellie:
Thanks, Larry, and thank you for inviting me to be a special guest with you on this very nice community visit. So yeah. Now I’ve gone from KGC. I think I left about three years ago to starting Common Action, which is not really an activist organization. It’s more like of a design and deep operations platform. And so what we’re trying to do is bring technology to the climate problem. Because if we think about it, there’s many, many things that make climate challenging to solve. But one of the core components is that it’s a coordination challenge. It’s a communication challenge. It’s a really big project. And so if we think about really big projects, those tend to happen on Gmail or on Slack or maybe on Teams if you’re really unlucky and it’s a lot of interaction between moving parts, many people, and there’s a lot of confusion in that. And it’s always dependent on those people knowing each other, especially when you think about project management software like Asana or something like that.

Ellie:
So in the climate case where we literally cannot know everybody who needs to do something about climate because it’s the globe, how would we think about organizing those communications and supporting specific people to identify routes to action pathways that help them become part of this mission set in a productive way? So anybody who wants to do something about climate, where do they go? What do they do? We are trying to be that middle space, both for just equipping people with strategies and also for looking at the unfolding changes globally in the physical layer and anticipating what kind of effects we might have and then supporting people to respond and prepare to those as well. So there’s a whole lot of things that we want to facilitate, but at the end of the day, it’s a technology-based firm that is bringing to the market complexity-based software, and that is always backed by knowledge graph technology.

Larry:
Because how else would you ever organize that scope that you just described? That’s a really ambitious domain you described. But your current work, you’re working in a slightly more constrained domain. At NASA, you’re working on the HelioWeb project. That’s at least … What? Science is the boundary of that one?

Ellie:
Yeah. Well, even better, it’s one division of science. So we’re just cutting our teeth on a small project for NASA. And what this is called … And as you said, it’s called HelioWeb. What this is about is basically solving some of the same communication and discovery problems for scientists who work both within NASA and beyond NASA within this investigation space of the heliophysics. And so you probably haven’t heard of heliophysics. It’s not as well socialized as astrophysics, but it is actually another form of astrophysics and it’s all about the study of the sun. So there’s a lot of people that participate in studying the sun, not only inside NASA, as I mentioned, but also in universities and also abroad in the European Space Agency and other related space agencies.

Ellie:
As I mentioned, what are our collaboration opportunities? Well, we can work on Slack, we can go to Teams and we can meet in a conference. And so what we’re trying to do is expose the knowledge that is latent in a conference space. And we’ve talked about this too at KGC. So that we can see who is there beyond a simple interaction in the hallway. Because let’s say you go to a conference, there’s a thousand people there, you can’t talk to every one of them. And even if you did, you wouldn’t necessarily know everything that would be relevant for them. For them to tell you or for you to share with them. We just don’t have the surface area for that in our interactions in person. So what we’re doing is supplementing that with a software system that allows individuals who are part of the HelioWeb and heliophysics community to report items of interest about themselves. That could be activities that they’re doing, roles that they have, projects that they’re organizing, softwares that they built or are maintaining. Any of the contributions that they make to science they can record it in a catalog, and then they can search using an ontology for different kinds of parameters, which are not connected necessarily to an individual name.

Ellie:
So I may not know who I would like to work with in this group of thousands of scientists because I haven’t met them yet, or because I don’t know how someone’s research interests have transformed or morphed over time. But I know that I’m interested in solar flares or coronal mass eruptions. And so I can search for those topics and see what other people have contributed to the knowledge base on those topics like, like I said, software systems or data sets or papers or whatever you have that people have entered. And then so in that way, discover the actual network. So it’s this user interface navigation notebook for supporting the discourse in the field alongside making it accessible to find materials, which is also a challenge in the NASA environment. As you can imagine, they have millions, trillions of data objects.

Larry:
No kidding. As you’re saying that, you’re reminding me, have you ever talked to Ashley Faith about personal knowledge graphs?

Ellie:
A little bit.

Larry:
Yeah. Because as you’re saying that, one of the things … Because I was talking to her on another podcast years ago about this notion of personal knowledge graphs as a way to just know and understand people, but we were talking about them in the context of enterprise content strategy as a way to know people who know stuff and to get permission to share stuff. But it was all about sharing the kinds of things you just mentioned, like personal interests, things you’ve done, activities you’ve done. So the way you described that, you can totally see how you just associate in the ontology, all those interests and activities with the people. Is it as simple as that, or is there more to it? Were there any challenges I guess, in developing the ontology that drives that?

Ellie:
Yeah. There’s multiple stages of HelioWeb, and in the current moment we’re in the first stage, which is this catalog. And you’re right that it mirrors the idea or the many ideas behind personal knowledge graphs pretty well. I don’t know if this is always the way that personal knowledge graphs are conceived, but what’s really specifically of interest to me in the HelioWeb use case, in the climate and sustainability use case, and in general in the use cases that I like to think about, there’s always the interaction between the individual and the collective. The community space. So if I have my own instance of HelioWeb, my profile and my personal knowledge graph base that I’m adding to, that is not only for my reference, but it’s also connecting it to this global community base.

Ellie:
So far we’ve built the first foundation layer of that vision. As we continue, we hope to build much, much more. So the grand vision is really for not just a catalog and a record space, but for a discursive environment. So as I mentioned, if we want to do collaboration … And especially in science, where talking to each other about the topics in the field is actually the practice of science in some ways. We are limited to email, Zoom calls, Slack and these other communication technologies, and none of them have been designed for community, large-scale, intersectional, inter-organizational, cross disciplinary interaction spaces.

Ellie:
If you think about Slack for instance, the assumption is that you’re a single workspace, typically a company. You can use it for something like a community like KGC does, but it’s not designed for that. And so some of the features just don’t really support you, including the pricing model where it’s super expensive to have a pay-per-seat for everyone in the open community that you might want to host. And that’s just one of the many, many frictions. With NASA, there’s even more frictions because you have to think about security at a really detailed level and so I don’t even think some of these tools are allowed to be used.

Ellie:
And so how do we pitch ourselves beyond the limits of how communications technologies have been conceived of so far? Which is a design question. And that’s the kind of thing that … That’s my background is design and art and literature and the humanities side of the fence where we take a ball of string and then we look at it and we say, “What could this become?” Really, really differently than what tech has been. Which is a lot of building on top of standards, very important to do, but also limiting in certain ways. So we’re taking that creative and curious and interactive design methodology and applying that to some of these problem sets that really haven’t been looked at in 20 years like email to get to another kind of interaction space.

Ellie:
And so the grand vision for HelioWeb is not only a discovery platform, a library or even a CRM, a lookup for scientists, but it’s also a space where we can allow scientists to share perspectives about the things that they’re studying and seeing and reading and hearing. They’re talking amongst the field in this living organism of interactions that also produces a living emergent history of where the field is going, it’s unfolding into the future, and where it’s been. So we can see explicit linkages between a material that was published in, I don’t know, 1970, that’s foundational in the field, and that somebody may want to reference because we learned how XYZ worked on the moon, and so maybe we can extrapolate something about the sun, or maybe we can extrapolate something from Mars about the sun. Who knows what we could really link? That’s the nature of science is a lateral interaction that is by definition, novel and interesting.

Larry:
And as you’re saying that, you’re reminding me that … Two things about this. One, that is so awesome. It feels like you’re on the brink of some really cool new communication tool that… So much of this whole community that we’re in originated with that notion of the semantic web. And it’s never really come to the fore, I think because the use case around … I don’t know. But the way you’re describing this seems like something that could get as close to the semantic web as we’ve ever got. So there’s that. The communication part of it.

Larry:
But also to what you were just talking about, it points to … One of the powerful things about knowledge graph technology in particular is that inference capability. That you know a bunch of stuff, you know how it’s connected and you can make inferences that you could never make with other technologies. So one, kudos on the cool new communications platform, but can you talk a little bit about that second point about how the technology permits this stuff?

Ellie:
Yeah. Obviously with communication, part of it is just having a space where you can send the right telephone message over the line and that really doesn’t involve semantics necessarily. But with the discovery function, in heliophysics especially, in the science use case especially, we do want to understand not only what the inferences are that we as ontologists say. So for instance, we’re used to the kind of inference like so-and-so is a man or a woman, thus so-and-so is a human being. The obvious state conditions that an ontologist can define.

Ellie:
In science we also want user-defined inferences. Scientists want to know what other scientists think about products. So, so-and-so claims that this data set shows that XYZ phenomenon is caused by blah, blah, blah. Or someone else presents an argument or disagrees with the argument. There’s this whole discursive interaction space and it happens in person. It happens when you go to a conference, it happens when someone is speaking and someone raises their hand and says, “I don’t agree.” Or it happens across journal articles where the same thing happens and there’s divergent and convergent conversations. But it’s not captured as metadata in those manual spaces, and thus it’s not part of the search experience. It’s not part of the engagement experience. I would like to go beyond this idea of search to this idea of supporting workflows, which is really, you’re right, what the semantic web vision initially was about.

Ellie:
And what I’ve been discovering is that the methods to doing that are to leverage language in ways that are informed I guess by my perspective as a linguistic type of person. What if we used standardized forms of language to express conversation styles? For instance, like a set of 25 conversation verbs and people could label themselves as agreeing or disagreeing or something like that. What if that was a form of metadata entry? What if that was a form of not only expressive descriptions from a person like we’re used to seeing on Facebook or Twitter with likes and retweets, I guess on Twitter. What if it wasn’t just us saying, yeah, I feel this way, but it was actually something that was machine-readable and could start to compute and say, okay, well, 55 people are arguing about this paper. Maybe it’s important. And that elevates it on the discovery screen. You can see, oh, this thing is getting really a lot of attention today.

Ellie:
And that kind of interaction, that kind of symbolic communication, which is what user interfaces are all about, is how does the computer help us to interact with it and with each other. So I think that there’s a lot of different ways to imagine how to use the tool set that was created by Tim Berners-Lee and the limit is always just your imagination. So part of what I would like to see more of in our field is more design thinking and more creative thinking, which borrows explicitly from the arts.

Larry:
Yeah. I agree completely. I’m often concerned about the lack of UX and design and humanity’s talent. Although I got to say I’m delighted to find more and more people like you and met a woman named Vera at a conference a couple of weeks ago who’s of a similar mindset. But everything you were just saying, especially about the limitation has always just been our imagination. And this is something we talked about a couple of weeks ago when we were getting ready for this conversation, was like, can we just make this about people instead of money? And I think a lot of the current focus and the lack of imagination is about financial prerogatives over advancing humanity.

Ellie:
Yeah. Especially when we think about LLMs and how they’re going to solve everything because they’re available, I guess. Oh, that makes sense to me too. Yeah. This question of what gets done and why is becoming more and more pregnant, I guess, in this space because … And I definitely am using a very arts word there. But because we have gotten to a point of really total efficiency. I think LLMs describe that more than anything else. You can get code immediately on a subject that you know nothing about, because you can ask the statistical machine to produce it, which obviously has figured out the best way from all of these samples that it has. And there’s a value to that. And the value certainly is in some ways in speed. But also competition is based around ideas of variation. And if we go back to the old web, which by the way is when Tim Berners-Lee was creating these languages … 2001 was still pretty early on.

Ellie:
That was a very different experience, and there was a lot of stuff that doesn’t scale, but that is also really cool like small blogs that people were cultivating and stuff like that. And crazy UIs. If you go back to the Internet Archive and you look at the ’90s, you see Nickelodeon’s crazy UIs, and you see Fight Club. And it’s so quaint now how they conceived of a space and so on. But the fact is that they were doing interesting things and they were doing experimental things, and now the web almost looks like it’s one long infinity scroll and there’s bars, and that’s what you get. You just get different colors and different shapes of boxes. And I think that users are getting bored with that. And so as always happens, something gets to be super efficient and then it penetrates the entire market and then it’s old and people move on to the next thing.

Ellie:
I think that there’s already desire for the cool stuff to come back and to be able to be found and not to be submerged in all of this noise, especially noise that can be intensified by LLMs. But then also if we think about this in an operational setting, our ability to solve problems is limited and not only by imagination, because there’s also real constraints. There’s the constraints of software, there’s the constraints of real life. But our ability to solve problems is always defined and related to strategy, and that’s what we miss, I think, a lot of the time. That’s what I’m always struck by as a person who’s from the humanities entering the software space. There’s not a lot of imagine what the goals are and work backwards to achieve them design thought. It’s really just like this is a foundation that works. It does something similar to what we need. I’ve seen it before. It interacts and clicks together with all these other things. Efficiency of the build is so predominantly focused upon that the user gets left behind and the need, the use case itself.

Ellie:
And so just to give a made up example off the top of my head, a while ago, I was participating on an NSF design sprint for Open Knowledge Networks and Open Knowledge Networks, just like what we’re talking about now with the HelioWeb and Common Action projects, they’re based on lots of different types of users interacting in a shared information space for a big picture goal. And so one of the things we talked about way back when was nurses. Nurses entering data about patients in the process of providing nursing services during their day of work. And if you think about that, if you have something that’s extremely hard to use, the nurse is not going to use it.

Ellie:
It’s just not going to be adopted as part of the workflow. But if you work backwards from that usage and context, you might be able to think of new ways of organizing the information that don’t even seem that big of a deal, like the box is here instead of there, but that totally influence her user flow and her ability to seamlessly integrate with that. Where I see there being a lot of space for more research and more investigation and more competitiveness is in that black box of design because the user is forgotten in many cases. Not even on purpose.

Larry:
Your critique of the modern web is so brilliant. You’re exactly right. It is one long infinite scroll interacted by like, “Oh, look, there’s a border radius of 20 instead of 10. How innovative.” But you also mentioned around that same time, the concept of variation. And I want to try to stitch this into your interest in ecology and biology because the variation and adaptability of the foundation of modern biology, that’s how evolution occurs and all that stuff. And I just wonder if you see what the mechanisms might be in these systems that you’re ideating and creating and actually building to get more variability in there, to get more creativity, to inspire more of the kind of thinking that’s going to be necessary to get us where you’re picturing things.

Ellie:
Well, on a very fundamental level, I think there needs to be more … I’m just going to make things up because this is a pie in the sky question. There needs to be more ease for creating materials online. And what we’re talking about, we’re really talking about user experiences. I think. You and I right now. And that connects to the back end, it connects to ontologies. As I’ve tried to allude to, I’m thinking about how metadata can be integrated in the user interface so it doesn’t feel like a chore. And it does things that we’re not used to doing with metadata. More than labels. And what I would love to be able to do as a designer who’s doing that is play with it. I work on paper so I can cut it up and move it around and experimentally view different shapes and spaces and forms. I can’t do that on the web. I’m actually completely incapable of doing that unless I have a developer and I described to the developer and then the developer was like, well, I don’t want to build it unless we’re going to use it. And so the play space missing. And I think that makes it inaccessible for a lot of would be creators who could very easily throw up something that you and I could only imagine imagining right now. It’s just the tooling is not there for them.

Ellie:
And I think even we see that with something that is more familiar to the typical knowledge graph viewer and participants is the broken spreadsheet. I’ve heard so many people talking about, oh my God, you would not believe what people did to their spreadsheet. And it’s like, yeah, but why they do that is because most users who are not technical have so little access to creating front ends that our ability to create a front end is basically limited to what you can Jerry-rig on Excel.

Larry:
That is so true. Oh, God. I see that everywhere in the things that I do. I love this idea of the missing play space and how might we create that. I know that was a pretty wide open question, but I’m just going to put that out there to the community as like, Hey, let’s just make this a little more playful. Because we were both talking before we went on the air that we’ve both been wrestling with computer stuff the last few days just trying to get things done and just reduce those obstacles, please so we can get on with fixing the web and climate and stuff.

Ellie:
Yeah. That was a common refrain that I heard while I was in community at the Knowledge Graph Conference. It was like, how do we sell this? And it’s like, okay, well, part of that is explaining to the front of house people, the business strategists and whoever else is making decisions that it’s necessary for them. And if they can’t interact with it, if the backend that you’re selling is something that’s invisible to a person, it’s really hard to understand what makes it better. You need to have something tactile. We know that as software people, it’s like, don’t really try to describe your prototype, show him. Make an MVP. You have to give someone something to look at. But I think even more broadly, to step away from UIs because I know that that’s not really what a lot of people … It’s not easy to break into that. Start learning Java, I guess. But thinking about ontologies and how a different framework can inform them.

Ellie:
As I mentioned, I was thinking about literature techniques. If the world was not on a fire, I would probably be writing novels. And so I think a lot about plot lines and how we could do interaction space with heliophysics or with climate actors as a plot. Almost like a strategy that gets described in a narrative form and then translate that into an ontology. And that is a very different approach from what I’ve seen of ontologies, which typically start with a bottom-up, here’s the terminology that’s being used. We don’t necessarily understand it because we are computer scientists and this is just actually a bunch of strings and we’re going to maybe add a bit of structure to make those strings make sense.

Ellie:
But you get to a lot of these problems where, how do we have terminology that agrees? How do we make these people come to one term to describe this thing? And I would suggest that that’s the wrong mindset. Because a search, it depends on what the use case is. But in general, search should be rich and messy because we want to have many different ways to find the material, which is probably interesting from more than one reason.

Ellie:
And so another that comes from my experience with NASA. We had a vocabulary workshop a little while ago at Goddard Space Flight Center where we were sourcing terms to put into the ontology from scientists. And we got so many terms. We were like, oh my goodness, what are the linkages between these things? And I think that that is really what we need to talk about more in the ontology world, is how do we think about foundational approaches to creating linkages, especially in spaces that we are not familiar like heliophysics? I can probably make an ontology for cats and dogs. It’s harder to make an ontology for MR5E and other things that I literally have no idea.

Ellie:
But there are certainly practices that we could adopt, and I don’t see a lot of material about this. To approach creating those linkages in a way that makes sense to the domain user, not just from our perspective. And that’s where the mechanics of writing a novel come in. Because these are problems that people have thought about. They’re just working on different complex texts and they’re not publishing in computer science journals, but the material is the same, it’s words, and it’s the way that we relate words together. I’ve noticed that there’s different ways of framing the problem that allow for some of these core problems of our domain space, of the semantic web in terms of development, adoption, design, that can inform those problems in a new way.

Larry:
Well, I hope you’re involved with Kogan and Maru on the educational stuff with you with the OKN, because everything you just said makes so much sense. I personally think that you should be in charge of how ontology design and engineering are taught for the next five years. Because your attitude in there is … But the beauty of this community is that the people who came up with the Pete’s ontology and the bottom up, top down and all the ontology engineering techniques-

Ellie:
Michael. That’s Michael DeBellis. He’s on our team.

Larry:
Oh, cool. So that’s all well entrenched, but it feels like we’re at a juncture where we could use more of your thinking. Yeah. But hey, Ellie, I can’t believe that we’re coming up on time already, and I could literally talk about this stuff forever with you. But before we wrap up, is there anything last, anything you want to revisit from the conversation or just make sure that we share before we wrap up?

Ellie:
So the information that I shared about HelioWeb, we have a paper on how we designed the ontology with ethnographic methods from anthropology. And also I’m going to be writing another one that describes the broader design space. So if any of these ideas have been interesting to folks, there will be a paper forthcoming about that. And we’re also developing this platform for climate and for sustainability. So if people are interested in that space, especially from a volunteering for knowledge management types of projects, feel free to get in touch with me. We’re interested right now in creating a phenomena ontology, so specifically describing things that happen in the real world and how they’re related to each other, specifically in ecological context and looking for like NLP support for named entity recognition and things like that.

Larry:
Okay. So this is the right community to be recruiting for something like that. I’ll make sure that’s in the show notes. You’re making me think I need to up my game with the podcasts and these resources and to make this enduring so that we can share when your paper comes out.

Ellie:
I have an app for that.

Larry:
I know. You’re the exact right person, so it’s very meta and circular. Well, thanks. Oh, hey, one very last thing, Ellie, if folks want to follow or connect online, what’s the best place to find you?

Ellie:
Yeah. I’m on LinkedIn at linkedin.com/in/sellieyoung, S-E-L-L-I-E-Y-O-U-N-G. You can also reach out if you want to chat about anything particular to my email. I’m at ellie@common-action.org.

Larry:
Great. I’ll link to that in the show notes as well. Thanks so much, Ellie. Great conversation. I really appreciate it.

Ellie:
Thanks, Larry.

entists at NASA and address climate change and sustainability.

Interview transcript