Adaptive Reading Support for Long-Form Chinese Historiography: Dual Annotations and Dynamic Scaffolding
Year: 2026
Type: article
Abstract: Long-form Chinese historiography challenges non-expert readers to continuously track dense events, historical figures, and implicit causal relationships. This study examines whether retrospective and expansive annotations can provide interpretable support-seeking cues for low-disruption dynamic scaffolding. A formative study tested whether the relative use of the two annotation types varied with perceived difficulty in consistent directions and could provide a calibration reference for conservative regulation. These cues were then instantiated in a reading system using a Large Language Model assisted retrieval-based workflow to prepare source-grounded chapter variants and dual annotations. A subsequent user study compared behavior-driven and user-selected regulation during the dynamic reading stage. Behavior-driven regulation was associated with lower perceived workload, with no reliable between-group differences in reading outcomes. The findings provide initial evidence that dual annotations may function as support-seeking cues for low-disruption dynamic scaffolding in long-form Chinese historiography reading.
Source: Figshare
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Keywords: Chinese historiography, perceived workload
Open Access status: green
OpenAlex ID: W7235324576
