GraphTide: Augmenting Knowledge-Intensive Text with Progressive Nested Graph
For readers of complex texts like academic articles, GraphTide reduces cognitive load by dynamically revealing relationships, but the improvement is incremental over existing graph-based methods.
GraphTide is a visualization technique that progressively constructs nested entity-relationship graphs with animation to help users comprehend knowledge-intensive texts. A user study shows it significantly improves comprehension compared to traditional graph-based techniques and static nested graph representations.
Knowledge-intensive text usually contains fruitful entities and complex relationships, such as academic articles and scientific exposition. Reading and comprehending such texts often demands considerable time and mental effort to track the relationships between entities. To reduce the burden, we present GraphTide, a visualization technique that progressively constructs nested entity-relationship graphs with animation to support the understanding of complex text. Our method features an on-demand entity-relationship decomposition pipeline that constructs nested graphs to represent intra- and inter-sentence relationships. Moreover, we propose a structure-aware force-directed layout optimization algorithm to enhance structural clarity. Sentences and their associated entities are incrementally revealed through animated transitions, helping users maintain context as the narrative unfolds. A user study shows that GraphTide significantly improves users' comprehension of knowledge-intensive texts compared to traditional graph-based techniques and static nested graph representations.