Machine learning meets visualization for extracting insights from text data

Abstract

Historically, text mining methods have been enriched substantially by both statistical learning and symbolic AI. Different approaches have been extensively applied over the last 30 years to extract "knowledge" from text. However, in scenarios where the path from data to decisions is unclear, or where different users may be interested in different solutions, the involvement of the user or analyst in the text mining process becomes crucial. Visual Text Analytics aims at addressing these problems by incorporating concepts from Visual Analytics to text mining and natural language processing (Keim et. al, 2010).