CASTCurate: An Agentic System to Accelerate the Collection and Annotation of Data-Driven Stories

Key Points

• The aim is to develop a system that streamlines the creation and annotation of data-oriented narratives in educational contexts.
• Design an agentic system for interactive data collection
• Integrate machine learning for improved annotation processes
• Employ natural language processing to facilitate storytelling
• Demonstrated faster story annotation compared to traditional methods
• Showed increased engagement in educational contexts
• Enhanced the quality of data-driven narratives