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 more options you can offer, the more accessible you will be."
Sam ProulxOnline Shopping: Designing an Accessible Experience
June 7, 2023
"Our values in design are changing from seeking perfection to embracing 'good enough' for the moment."
Hugh DubberlyProblems with Problems: Reconsidering the Frame of Designing as Problem-Solving
June 19, 2019
"You don't want to mix and match types of critiques; just pick one and give it a try."
Joseph MeersmanSweating the Pixel: Scaling Quality through Critique
June 10, 2021
"Love letters are great. They continually highlight work that improves the product."
Kim Fellman CohenMeasuring the Designer Experience
October 23, 2019
"Solid roles and responsibilities won't magically solve everything."
Alastair SimpsonDebunking the Myths of Cross-Disciplinary Collaboration
October 24, 2019
"When starting a project, prioritizing what matters most becomes essential to success."
Harry MaxPriority Zero: Some Things are More Equal than Others
June 9, 2016
"Choosing to remain silent is still a choice."
Sahibzada MayedThe Politics of Radical Research: A Manifesto
March 27, 2023
"Clear visuals and customer-centered narratives help bridge understanding."
Dr. Nikki SmithResearch Strategy: Connecting Insights to Outcomes
March 12, 2025
"Being trauma-informed is a commitment to not repeat those experiences and moving towards healing."
Uday Gajendar Rachael Dietkus, LCSW Dr. Dawn Emerick Dawn E. Shedrick, LCSWLeading through the long tail of trauma
July 13, 2022
