As time has gone by, research has pointed out that there remains skepticism in the community when it comes to using such tools that are focused around automating parts of the data discovery process. As my research as well as previous research has shown, practitioners prefer using traditional tools over newer tools, even if it involves more manual effort and time. The workflows that many data scientists follow today, do not completely utilize the new capabilities that are available to them through ML/AI.
How can a user interface be designed that bridges this gap between intelligent algorithms and user needs? The aim of this project would be to envision, design, and develop a data discovery module that helps accelerate exploratory data analysis, through the connection of intelligent algorithms with a GUI that supports data visualizations and rich interactions.
Students in Georgia Tech's interdisciplinary MS in Human-Computer Interaction program do multiple group class projects, and a capstone individual project. Some projects are presented as part of other labs listed here; others are showcased in the MS-HCI Project Lab.
The two-year program spans four schools: Industrial Design; Interactive Computing; Literature, Media and Communications (Digital Media Program); and Psychology. Approximately 50 new students enroll each fall semester.