ADVisE project will mainly focus on theories of user’s individual differences in information processing within the visual analytics area for providing adaptive and personalized solutions in the business context and information discovery. The variables that concern individual cognitive characteristics are emerging from psychological theories.
The Adaptive Data Visualizations Framework ADVisE is a combination of the scientific disciplines of Cognitive Psychology, Web Adaptation and Personalization and Visual Analytics.
Given the users’ diversified requirements, needs and perceptual preferences as well as the size, diversity and processing overhead of big data sets, it is expected that this research will yield flexible best-fit data visualizations and methods that will support the unique end-users during the interaction process.
The main challenge is to identify and develop enhanced data representations that will be able to capture the fuzzy human nature and multi-objective tasks in terms of providing information in different modalities, navigation patterns and interaction logic thus allowing for adaptation based on users’ cognitive processing abilities, role, expertise and tasks. This will increase information assimilation, accuracy and decision making during tasks execution bringing new business insights. In a broader perspective, the results of the ADVisE framework will have a wider social and economic impact by helping users to comprehend and familiarize themselves with usable data visualizations adjusted to their knowledge and abilities, enhancing their satisfaction and acceptability of related services.
More specifically, the main research pillars of this project are:
(i) to investigate the influence of individual differences in cognitive processing with respect to visual analytics and formulate an inclusive human-centered user model
(ii) to identify potential correlations of cognitive factors referring to high-level information processes as well as elementary cognitive processes with different kinds of data visualizations, in terms of type and complexity (e.g., network diagrams, area and radar graphs, bar and line charts)
(iii) to analyze and suggest a set of adaptive visualization interventions that could increase the usability and satisfaction of users based on their role or levels of expertise
(iv) to develop and evaluate an Adaptive Data Visualizations framEwork that will dynamically adjust the content and interaction style of data visualizations based on users’ individual differences, the data characteristics and the task at hand.