ProvThreads: Analytic Provenance Visualization and Segmentation
This work addresses the need for better meta-analysis of analytic provenance in text analysis, though it appears incremental as it builds on existing visual analytics and topic modeling techniques.
The paper tackles the problem of understanding analysts' strategies during exploratory text analysis by introducing ProvThreads, a visual analytics approach that generates visualizations to illustrate relationships between user interactions and data topics, using topic threads to show topic coverage and investigation progression over time.
Our work aims to generate visualizations to enable meta-analysis of analytic provenance and aid better understanding of analysts' strategies during exploratory text analysis. We introduce ProvThreads, a visual analytics approach that incorporates interactive topic modeling outcomes to illustrate relationships between user interactions and the data topics under investigation. ProvThreads uses a series of continuous analysis paths called topic threads to demonstrate both topic coverage and the progression of an investigation over time. As an analyst interacts with different pieces of data during the analysis, interactions are logged and used to track user interests in topics over time. A line chart shows different amounts of interest in multiple topics over the duration of the analysis. We discuss how different configurations of ProvThreads can be used to reveal changes in focus throughout an analysis.