Annoxplorer: A Scalable, Integrated Approach For The Visual Analysis Of Text Annotations

Text annotation data in terms of a series of tagged text segments can pose scalability challenges within the dimensions of quantity (long texts bearing many annotations), configuration (overlapping annotations or annotations with multiple tags), or source (annotations by multiple annotators). Accordingly, exploration tasks such as navigating within a long annotated text, recognizing patterns in the annotation data or assessing differences between annotators can be demanding. Our approach of an annotation browser deals with all of these data and task challenges simultaneously by providing a continuous range of views on large amounts of complex annotation data from multiple sources. We achieve this by using a combined geometric/semantic zooming mechanism that operates on an abstract representation of the sequence of a text's tokens and the annotations thereupon, which is interlinked with a view on the text itself. The approach was developed in the context of a joint project with researchers from fields concerned with textual sources. We derive our approach's requirements from a series of tasks that are typical in natural language processing and digital humanities, show how it supports these tasks, and discuss it in the light of the feedback we got from our domain experts.