CataAnno: An Ancient Catalog Annotator for Annotation Cleaning by Recommendation.

Area of Science:

• Digital Humanities
• Information Science
• Historical Bibliography

Background:

• Classical bibliography research involves analyzing historical catalogs to understand cultural development.
• Annotating ancient Chinese catalogs is complex and requires specialized domain expertise.
• Existing annotation methods can be time-consuming and prone to inconsistency.

Purpose of the Study:

• To introduce an efficient system, CataAnno, for annotating Chinese ancient catalogs.
• To enhance the accuracy, consistency, and efficiency of the catalog annotation process.
• To reduce the reliance on specialized knowledge for data annotation.

Main Methods:

• Developed the CataAnno system incorporating cross-linked views and recommendation algorithms.
• Implemented a recommendation method that learns from expert annotations and prior data.
• Designed convenient annotation interactions and visualizations for user comprehension.

Main Results:

• CataAnno demonstrated improved annotation efficiency and accuracy.
• The system's recommendations and visualizations aided users in understanding entry correlations.
• Expert feedback confirmed the system's ability to mitigate the need for specialized knowledge.

Conclusions:

• CataAnno significantly enhances the efficiency and quality of ancient catalog annotation.
• The system democratizes the annotation process by lowering knowledge barriers.
• This work contributes to the digital humanities by improving historical data accessibility.