While data analysts have a variety of tools to support their work, these visual analytic tools take a standard approach that doesn’t take into account an analyst's particular skills and working methods.
Alvitta Ottley, assistant professor of computer science & engineering in the McKelvey School of Engineering at Washington University in St. Louis, plans to take a closer look at individual differences on tasks and visualization designs with a five-year, $528,223 CAREER Award from the National Science Foundation. CAREER awards support junior faculty who model the role of teacher-scholar through outstanding research, excellence in education and the integration of education and research within the context of the mission of their organization. One-third of current McKelvey Engineering faculty have received the award.
One aspect of Ottley’s research involves identifying personality traits that impact strategy during data exploration. She and members of her lab also apply machine learning to predict individual characteristics, such as personality traits and cognitive abilities, from user interaction logs. They use machine learning and artificial intelligence algorithms to learn from those interactions then develop new visual analytics systems that predict intentions and provide support for the user during analytical tasks.
In the new research, she and members of her lab will study the impact of these individual characteristics by using behavioral data, such as the user’s interactions with the mouse, to model a user’s cognitive profile, attention and workflow. With the data and models, she and her team will assess and predict cognitive traits that affect an analyst’s strategies and visualization effectiveness, then develop new visual analytics tools that provide personalized guidance and suggestions based on the user’s characteristics and profile.
“Achieving these goals will produce a new class of user models that will use behavioral insights from the visualization and psychology literature,” Ottley said. “My vision treats humans and machines as partners in a multi-agent system in which both the analyst and the visualization system collaborate in the analytic process.”
The research supports the Future of Work at the Human-Technology Frontier, one of the agency’s 10 Big Ideas for Future NSF Investments.
“By considering the user’s cognitive profile, the community can deliver data analysis solutions to a more diverse end-user population, which will allow more people to make data-informed decisions,” Ottley said. “It will develop new theoretical foundations, algorithms and techniques that will lead to a more cooperative relationship between the human and the visual analytic tool during data analysis.”
For the outreach component, Ottley will create a new summer camp for K-12 students and partner with the WashU Girls Who Code club, a local division of an organization that works to reach girls around the world and to close the gender gap in new entry-level tech jobs. In addition, Ottley will train a diverse group of undergraduate students through programs such as the NSF’s Louis Stokes Alliances for Minority Participation program in Missouri and Distributed Research Experiences for Undergraduates. She also plans a network of diverse mentors, composed of students, alumni and faculty, to shepherd students through STEM research and education programs to improve the retention of students from underrepresented minority groups in the STEM fields.