Designing Automated Assistants for Visual Data Exploration
Visual data exploration enables analysts to identify trends and patterns, generate and verify hypotheses, and detect outliers and anomalies. However, the overwhelming number of decisions required in visual data exploration presents a barrier to discovering useful, actionable insights from data.
In this dissertation talk, Dr. Doris Lee discusses how automated assistance via tooling aids visual data exploration. Lee developed four systems to survey the design space of visual exploration assistants across different analytical tasks and interface modalities. Findings from this dissertation contribute towards designing an intelligent visual exploration assistant that suggests helpful tailored feedback based on user’s analytical needs and seamlessly guides users towards data-driven insights.
Doris Lee is a Ph.D. graduate from the School of Information at UC Berkeley. During her Ph.D., she led the development of Lux, a tool for accelerating visual insight discovery. To date, Lux has over 2.9K stars on GitHub and has been used by data scientists in a variety of industries and sectors.