Co-adaptation in cognitive computing systems
Mar 9, Wednesday, 11:30 am - 12:30 pm, on Zoom. The Zoom link is circulated separately via the BEE email list. Please fill the registration form to join our mailing list.
Presenter
PhD Candidate at University of Michigan - School of Information
Abstract
Cognitive computing systems (CCSs) are a new generation of automated IT systems that simulate the cognitive capabilities of humans. The CCS reshapes the interaction between humans and machines and challenges the way we approach technology use and adaptation. This work introduces co-adaptation and defines it as a series of activities between a user and a system that is done simultaneously in order to make the system more user-friendly. Co-adaptation involves two types of adaptation: human adaptation and machine adaptation. Human adaptation refers to the user changing their behavior to adjust to the technology or changing the technology to adjust to their use. In contrast, machine adaptation refers to the system adapting itself to fit users’ needs. Using polynomial modeling and response surface analysis, we examine longitudinal survey data of 249 Intelligent Assistant users work from home. Findings show that equality between human adaptation and machine adaptation leads to the highest impact on individuals compared with inequality.