Abstract
The vast amount and rapid growth of data on the Web and in document repositories make knowledge extraction and trend analysis a challenging task. A well-proven approach for the unsupervised analysis of large text corpora is dynamic topic modeling. While there is a solid body of research on fundamentals and applications of this technique, visual-interactive analysis systems for allowing end-users to perform analysis tasks using topic models are still rare. In this paper, we present D-VITA, an interactive text analysis system that exploits dynamic topic modeling to detect the latent topic structure and dynamics in a collection of documents. D-VITA supports end-users in understanding and exploiting the topic modeling results by providing interactive visualizations of the topic evolution in document collections and by browsing documents based on keyword search and similarity of their topic distributions. The system was evaluated by a scientific community that used D-VITA for trend analysis in their data sources. The results indicate high usability of D-VITA and its usefulness for productive analysis tasks.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have