Visual Search and Analysis in Textual and Non-textual Document Repositories-Approaches, Applications, and Research Challenges

摘要

Information retrieval and analysis are key tasks in dealing with the information overload problem characteristic for today's networked digital environments. Advances in data acquisition, transmission and storage, and emergence of social media, lead to an abundance of textual and non-textual information items available to everyone at any time. Advances in visual-interactive data analysis can provide for effective visual interfaces for query formulation, navigation, and result exploration in complex information spaces. In this presentation, we will discuss selected approaches for visual analysis in large textual and non-textual document collections. First, recent techniques for visual analysis of readability, sentiment and opinion properties in large amounts of textual documents, including promising application possibilities, will be discussed. Then, we will focus on visual analysis support for information retrieval in non-textual documents, in particular multimedia and time-oriented research data. We argue that new visual-interactive approaches can provide for effective user access to large document corpora, including discovering of interesting relationships between data items, and understanding the space of similarity notions for a given document repository. We will conclude the presentation by discussing research opportunities at the intersection of visual data analysis, information retrieval, and evaluation.