Adaptive Reading Support for Long-Form Chinese Historiography: Dual Annotations and Dynamic Scaffolding
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.
Authors
- Zixun Wang (ORCID: https://orcid.org/0009-0007-7947-0708)
- Xusheng Zhang (ORCID: https://orcid.org/0000-0001-8751-7958)
- Zuoxiu Zheng (ORCID: https://orcid.org/0000-0001-9915-8761)
- Xi Zeng (ORCID: https://orcid.org/0009-0001-1051-1272)
- Yifan Zheng (ORCID: https://orcid.org/0009-0000-3838-4335)
Institutions
- Zhejiang University (CN)
Publication Details
- Journal
- International Journal of Human-Computer Interaction
- Published
- 2026-11-17
- DOI
- https://doi.org/10.1080/10447318.2026.2749303
- Primary Topic
- Intelligent Tutoring Systems and Adaptive Learning
- Type
- article
- Field-Weighted Citation Impact
- 0.00