Jeff Heer on Augmenting Data Scientists: The Promise and Peril of AI-Assisted Analysis

This lecture was recorded and is now live on our YouTube channel

Stanford Data Science is pleased to host our Fall Distinguished Lecture on October 10th, 2023. Our speaker is Dr. Jeffrey Heer ( University of Washington), who will be giving a lecture on Data Scientists: The Promise and Peril of AI-Assisted Analysis.

We welcome you to join us at 6:30pm for a dinner reception and an opportunity to engage with others in the Stanford Data Science community, followed by the lecture at 7:30pm. The Reception and Check-in are located on the 2nd Floor. 

Jeffrey Heer is the Jerre D. Noe Endowed Professor of Computer Science & Engineering at the University of Washington, where he co-directs the Interactive Data Lab and conducts research on data visualization and human-computer interaction. The visualization tools developed by Jeff and his collaborators—Vega(-Lite), D3.js, Protovis, Prefuse—are used by researchers, companies, and data enthusiasts around the world. 

Jeff's research papers have received awards at the premier venues in Human-Computer Interaction and Visualization (ACM CHI, UIST, CSCW, IUI, IEEE InfoVis, VAST, EuroVis). Honors include MIT Technology Review's TR35 (2009), a Sloan Fellowship (2012), the ACM Grace Murray Hopper Award (2016), the IEEE Visualization Technical Achievement Award (2017), and induction into the IEEE Visualization (2019) and ACM SIGCHI (2021) academies. Jeff received B.S., M.S., and Ph.D. degrees in Computer Science from UC Berkeley, whom he then "betrayed" to join the Stanford CS faculty (2009–2013). He also co-founded Trifacta, a provider of interactive tools for scalable data transformation acquired by Alteryx in 2022.

Distinguished Lecture on Augmenting Data Scientists: The Promise and Peril of AI-Assisted Analysis

Abstract
Data analysis is a rich sensemaking process, with frequent shifts among data representations, tools, and both conceptual & mathematical models. Computational methods can go beyond fitting models and rendering charts to make in-context recommendations and even guide end-to-end analysis workflows. How does the design of such tools affect people's exploration, modeling, and understanding of data? In this talk, we will consider methods for augmenting data science work by integrating proactive computational support into interactive tools, with the goal of providing algorithmic assistance to augment and enrich, rather than replace, people’s intellectual work. Across tasks such as data transformation, visualization, and statistical modeling, we will apply artificial intelligence to bridge gaps between user intent and robust analysis results. At the same time, we will pay careful attention to ways these methods may exacerbate bias, foster dependence, and pose vital challenges for the future of data analysis.