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
"Assistive technology can feel like another person in the room during a research session, which you have to understand and include."
Kavana RameshMeaningful inclusion: Practicing accessibility research with confidence
September 24, 2024
"Quantitative data boils complex situations down to single numbers that are easy to grasp and discuss."
Rima Campbell Amrit S BhachuIncrease Productivity and Drive Business Impact
September 24, 2024
"If you want your question asked, please put it in the Slack channel, because I cannot keep up with the rapid things happening live."
Bria Alexander Louis RosenfeldOpening Remarks Day 1
March 25, 2024
"Design is really a team sport, and we are investing in specialists to help with design systems, operations, research, and content strategy."
Kim LenoxLeading Distributed Global Teams
May 20, 2019
"I’ve been in the UX world for like 30 something years before we were even calling it UX."
Louis RosenfeldThe Rosenbot and the Rosenverse: An AMA with Lou Rosenfeld
June 5, 2024
"Historians say the past doesn’t repeat itself, it rhymes."
Steve PortigalLooking Back…to Look Ahead
March 26, 2024
"We created a self-service UXR hub to empower teammates with research fundamentals amid downsized research teams."
Maggie DieringerCreating Consistency Through Constant Change
January 8, 2024
"Mature research repositories are rare, and return on investment depends heavily on scale, governance, and organizational structure."
Brigette Metzler Dana ChrisfieldResearch Repositories: A global project by the ResearchOps Community
August 27, 2020
"Screen magnification is really about making the screen larger, changing color contrast, reducing motion, and panning around the magnified area."
Sam ProulxPrototype Reviews, People With Disabilities, and You
October 1, 2021