Visualizing search results and document collections using topic maps

This paper explores visualizations of document collections, which we call topic maps. Our topic maps are based on a topic model of the document collection, where the topic model is used to determine the semantic content of each document. Using two collections of search results, we show how topic maps reveal the semantic structure of a collection and visually communicate the diversity of content in the collection. We describe techniques for assessing the validity and accuracy of topic maps, and discuss the challenge of producing useful two-dimensional maps of documents.