Rosenverse

This video is only accessible to Gold members. Log in or register for a free Gold Trial Account to watch.

Log in Register

Most conference talks are accessible to Gold members, while community videos are generally available to all logged-in members.

Latent Scope: Finding structure in unstructured data
Gold
Wednesday, June 11, 2025 • Designing with AI 2025

This video is featured in the AI and UX playlist and 1 more.

Share the love for this talk
Latent Scope: Finding structure in unstructured data
Speakers: Ian Johnson
Link:

Summary

As a data visualization designer and developer the challenge I often face is what to do with unstructured data. One case study I can show is exploring survey results where the multiple-choice questions are straightforward to analyze but interesting open-ended questions like “What do your colleagues not understand about data visualization?” are much harder to crack. Latent Scope is an open-source tool I built that streamlines a process of embedding text, mapping it to 2D, clustering the data points on the map and summarizing those clusters with an LLM. Once the process is done on a dataset structure emerges from the unstructured text, allowing us to get a sense of patterns in the survey answers. Themes like “the time it takes” to develop data visualization pop out, as do “the importance of good design.” While people don’t use the same language to describe these themes, they show up as clusters in the tool thanks to the power of embedding models. https://github.com/enjalot/latent-scope

Key Insights

  • AI embeddings transform unstructured data like text or sketches into high-dimensional vectors capturing hidden semantic patterns.

  • Dimensionality reduction algorithms map these high-dimensional embeddings into 2D clusters, making patterns visually accessible.

  • Free text survey responses, often too large to analyze manually, can be organized and explored effectively through embedding and clustering.

  • Google Cloud user journey data revealed surprising usage patterns, like enterprise and beginner tools being combined unexpectedly.

  • Simple rule-based filters for harmful prompts in generative AI image models can be bypassed by subtle prompt variations; embedding-based classifiers are more effective.

  • Latent Scope is an open source tool enabling non-technical users to embed, cluster, label, and visualize unstructured text data locally.

  • Local runs of embedding and clustering models on modest hardware are practical, preserving data privacy and sensitive user information.

  • Embedding models trained on multilingual data can cluster semantically similar texts across diverse languages in one shared space.

  • Breaking long text into smaller chunks can make embeddings more manageable and improve similarity comparisons.

  • Hands-on exploration of embedding models via platforms like Hugging Face helps users internalize concepts of semantic similarity and pattern discovery.

Notable Quotes

"People just don't get that the design and the process is fundamental."

"Similar inputs will produce similar high dimensional numbers."

"Dimensionality reduction algorithms take data points in high dimensional space and put them close together in 2D if they're similar."

"We found patterns that product teams didn’t expect or even want to look for."

"Simple word-list based filters can easily be tricked by misspellings or slight variations in prompts."

"What if you didn’t know there were important questions you should be asking in your data?"

"Latent Scope lets you quickly explore hundreds or thousands of free text responses to find clusters and patterns."

"You don’t need special hardware; these open source models can run locally on an M1 MacBook or a gaming machine."

"Multilingual embedding models can cluster similar meanings across languages in a shared latent space."

"Downloading and playing with local open source models gives a different experience than using faceless APIs mediated through interfaces."

Ask the Rosenbot
Jon Fukuda
All the Ops: Successful cross-functional collaboration
2025 • DesignOps Summit 2025
Gold
Cheryl Platz
Collaborative Creativity through Improv
2018 • DesignOps Summit 2018
Gold
Wendy Johansson
Design at Scale: Behind the Scenes
2021 • Enterprise Community
Maish Nichani
Sparking a Service Excellence Mindset at a Government Agency
2021 • Civic Design 2021
Gold
Taylor Jennings
Repository Retrospective: Learnings from Introducing a Central Place for UX Research
2022 • Advancing Research 2022
Gold
Jamie Beck Alexander
How can you find your role in climate?
2024 • Climate UX Interest Group
John Taschek
Making People the X-Factor in the Enterprise
2018 • Enterprise Experience 2018
Gold
JP Allen
Navigating the UX Tool Landscape
2021 • Advancing Research 2021
Gold
Sam Proulx
To Boldly Go: The New Frontiers of Accessibility
2022 • DesignOps Summit 2022
Gold
Maria Skaaden
Continuous Design: One eye on the horizon and the other on the next wave
2018 • DesignOps Summit 2018
Gold
Erin May
Distributed, Democratized, Decentralized: Finding a Research Model to Support Your Org
2022 • Advancing Research 2022
Gold
Victor Lombardi
Bridging Design and Climate Science
2024 • Climate UX Interest Group
Ben Davies
Expert Panel: The Principles of Research Repository Design
2022 • Advancing Research 2022
Gold
Julie Norvaisas
Back to basics, or start from scratch?
2025 • Advancing Research 2025
Gold
Catherine Blizzard
Using Integrated Insight to Drive Growth
2022 • Advancing Research 2022
Gold
Robin Beers
Panel: Excellence in Communicating Insights
2024 • Advancing Research 2024
Gold

More Videos

John Calhoun

"Endlessly justifying yourself rarely changes others’ opinions. It positions design ops as up for debate."

John Calhoun Rachel Posman

Meters, Miles, and Madness: New Frameworks to Measure the (Elusive) Value of DesignOps

September 24, 2024

Nicole Bergstrom

"Progress over perfection—that’s how accessibility wins get made and sustained."

Nicole Bergstrom Anna Cook Kate Kalcevich Saara Kamppari-Miller

AccessibilityOps: Moving beyond “nice to have”

September 19, 2024

Louis Rosenfeld

"We do about a hundred free community sessions a year where anyone with membership can attend."

Louis Rosenfeld

The Rosenbot and the Rosenverse: An AMA with Lou Rosenfeld

June 5, 2024

Christian Crumlish

"We can design the experience of working with us just like we design for end users."

Christian Crumlish Wendy Johansson Rich Mironov Aditi Ruiz Adam Thomas

Afternoon Insights Panel

December 6, 2022

Crystal Yan

"Customer centricity must be part of hiring, performance reviews, and budgeting for it to truly stick."

Crystal Yan

Building a Customer-Centric Culture

March 30, 2020

Ron Bronson

"If you do enough research, you might find 20% of your users are edge cases, so maybe you’re not building for the right people."

Ron Bronson

Design, Consequences & Everyday Life

November 18, 2022

Kim Holt

"Values determine the team environment you create; they permeate through leadership and affect performance and happiness."

Kim Holt Emma Wylds Pearl Koppenhaver Maisee Xiong

A Salesforce Panel Discussion on Values-Driven DesignOps

September 8, 2022

Nalini Kotamraju

"What happens if research does not report into UX? What might happen if we uncouple research from UX?"

Nalini Kotamraju

Research After UX

March 25, 2024

Rachael Dietkus, LCSW

"Our ability to entice participants to share their most personal stories raises the potential to exploit them for design research."

Rachael Dietkus, LCSW

Trauma-Responsive Design: Reimagining the Future of Design Now

December 10, 2021