Visual text analytics

• Grant number: 13/50380-4
• Support type: Regular Research Grants
• Duration: November 01, 2013 - October 31, 2015
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Cooperation agreement: Consortium of Alberta, Laval, Dalhousie and Ottawa (CALDO)
• Principal Investigator: Maria Cristina Ferreira de Oliveira
• Grantee: Maria Cristina Ferreira de Oliveira
• Principal investigator abroad: Evangelos Milios
• Institution abroad: Dalhousie University, Halifax, Canada
• Home Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated research grant: 11/22749-8 - Challenges in exploratory visualization of multidimensional data: paradigms, scalability and applications, AP.TEM

Abstract

This proposal is related, on the Brazilian side, to the thematic research project "Challenges in Exploratory Visualization of Multidimensional Data: Paradigms, Scalability and Applications" (FAPESP 2011/227498) developed at ICMC-USP, and on the Canadian side, to the project "Visual Text Analytics" (https://projects.cs.dal.ca/visualtextanalytics/), developed at the Dalhousie University in partnership with Aerolnfo Systems (Boeing Canada Operations Ltda.). Both projects have as one of their goals the development and improvement of techniques for visual analytics of text corpora, which requires integrating text mining and interactive text visualization to create computer tools to support humans in sense-making activities. Key challenges include: the development of new visualization techniques and metaphors suitable to handle text; investigation of text processing techniques capable of capturing relevant information to create semantically informative visualizations; the extraction and visualization of concepts, names and relations from large noisy text corpora; visualization of relations between concepts in text as graph structures; support for real-time visualization and interaction, which requires a careful trade-off between off-line and on-line processing; novel text visualization techniques and interaction techniques that permit a domain analyst to browse through the knowledge content of the text corpus and fine tune the text mining and/or the visualization, without becoming a text mining expert. (AU)