Intelligent Systems And Approaches For Information Visualization

Information visualization is one of the major components in visual communication design.It provides an efficient way to analyze and pressent data information in the big data era.Although useful,technique barriers,such as analysis,design,and scripting,make information visualization difficult for general users without expertise,especially without visualization literacy.The research questions is how might we design intelligent visualization systems and methods to facilitate data exploration and analysis and data presentation and communication.To lower the technical barriers,we design intelligent systems and approaches.The first part of this dissertation focuses on the system and approach for designing visualization charts for data exploration and analysis,including a visualization design system based on semantic actions and an approach for task-oriented optimal sequencing of visualization charts.The second part extends the work from visualization charts to visual data stories for data presentation and communication.We first present Calliope,a system that automatically generates visual data stories from spreadsheets.To further facilitate the generation of data videos,we built an automatic approach for data video generation that can generate coherent chart animations from given data facts.There are four major contributions in this dissertation:(1)A visualization design system based on semantic actions,that helps average users to construct visualizations step by step.Our system contributes a set of action-based visualization components and a high-level grammar for semantic actions;(2)A novel chart sequencing method based on reinforcement learning to capture the connections between charts in the context of three analysis tasks,including correlation analysis,anomaly detection,and cluster analysis;(3)A visual data story generating system,Calliope,which creates visual data stories from an input spreadsheet through an automatic process and facilities the revision of the generated story based on an online story editor;(4)An optimizationbased approach,Auto Clips,to further lower the barrier of creating data videos.It can automatically generate data videos given the input of a sequence of data facts.