This video is only accessible to conference ticket holders.
Log in Create account
For 90 days after a conference, only paid ticket holders can watch conference videos. After that, all Gold members have access.
Contact Support if you are having any issues.
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
-
•
Unstructured data poses significant analytical challenges, especially when dealing with qualitative responses in large datasets.
-
•
AI techniques like embeddings and dimensionality reduction can effectively map the structure of unstructured data, revealing hidden patterns.
-
•
Juxtaposing user data through dimensional reduction can yield unexpected insights about product usage and user behavior.
-
•
Latent Scope simplifies the process of analyzing unstructured data, making advanced techniques accessible to non-experts.
-
•
Finding similar patterns in diverse data, such as sketches or survey responses, can uncover insights that traditional analysis methods miss.
Notable Quotes
"I want to take you on a bit of a journey of how I came to care about unstructured data."
"Organizing these responses is often a manual labor of love."
"This set of techniques and embedding, mapping, clustering and then visualizing data sets is not new, but daunting to execute."
"What if you didn't know there were important questions you should be asking?"
"I wanted a way to turn it into a robust and easy to use process."
















More Videos

"The best outcomes resulted when we had full participation from the multi-disciplinary team."
Carla Casariego Sarah SpencerDesignOps in Wonderland
October 24, 2019

"You need to demonstrate compelling reasons why they should work with you."
Noel LambCultivating Business Partnerships to Grow Research Ops
March 21, 2022

"We still have work to do helping teams better understand and leverage the design quality scores."
Chris MosesStretching the Definition of DesignOps with Product Development
November 7, 2018

"When you're looking at whatever measures you use, if you're chasing the outcome but not focusing on the means to get there, it's going to be pretty rough."
Sara Asche Anderson Jamie KaspszakNot Your Ordinary Re-Brand: Design's Path to Driving Customer Obsession at Best Buy
January 8, 2024

"When I started at Apfolio, I think everybody just expected that I would go and build wireframes and make suggestions."
JJ KercherA Roadmap for Maturing Design in the Enterprise
June 15, 2018

"Spectrum makes it a priority to support multiple themes while ensuring accessibility and inclusivity."
PJ Buddhari Nate BaldwinMeet Spectrum, Adobe’s Design System
June 9, 2021

"The best practitioners see a biased view of their community's ability."
Adrian HowardSturgeon’s Biases
September 25, 2024

"Connection is actually what helps to bring people back to a safe state."
Alla WeinbergDesign Teams Need Psychological Safety: Here’s How to Create It
September 8, 2022

"What percentage of what agents do comes from their mind having to work versus the system telling them how much to earn?"
Greg PetroffDesign is the Differentiator: Bringing New Design Innovations to a Very Antiquated and Very Large Industry
June 9, 2021