This video is featured in the AI and UX playlist and 1 more.
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."
Or choose a question:
More Videos
"These steps aren’t just research tactics – they could be life savers when employed well."
Amanda Kaleta-Kott Lea Martin, PhDThe Joys and Dilemmas of Conducting UX Research with Older Adults
March 11, 2022
"I am responsible not just for insights but for my team's well-being, legal commitments, and fiduciary responsibilities."
Nalini P. KotamrajuTwo Jobs in One: Being a “Leader who is a Researcher” and a “Researcher who is a Leader"
March 10, 2021
"The Austin studio’s walls can be put up and taken down by a 90-pound person on a Home Depot shopping cart."
Phil GilbertA Consistent Culture of Design
May 14, 2015
"The very thing that got us into trouble—the complexity of small pieces—is exactly our way out of it."
Jeff SussnaWhat DesignOps Can Learn From DevOps
November 6, 2017
"IKEA's instruction manual is rigid; you must do exactly what you're told to get a specific result."
Michelle MorrisonPractice What You Preach
January 8, 2024
"Exploratory user research can help teams think outside of commonplace organizational silos and facilitate collaboration across teams."
Sharon BautistaTime to Make the Donuts: How User Research Helped Bridge Disparate Teams
January 8, 2024
"We capture component design decisions and health transparently with checklists; unchecked items correspond to open tickets for prioritization."
PJ Buddhari Nate BaldwinMeet Spectrum, Adobe’s Design System
June 9, 2021
"Workshop content is equivalent to a one-day in-person event spread over 10 virtual hours with coaching and support."
Rachael Dietkus, LCSW Victor Udoewa Jennifer StricklandEverything You Need to Know about the Civic Design 2022 Call for Presentations
May 17, 2022
"We come to these spaces not to escape but to partake of them."
Sha HwangThe First Fifty Years of Civic Design
November 16, 2022
