New pipeline graphs historical actions using machine learning

Researchers have developed a new pipeline for transforming historical documents into structured data, focusing on actions as the fundamental unit of analysis. This approach, based on the GRAM-framework (Graph of Roles and Actions Model), utilizes machine learning tools to automate the graphing of actions. The paper demonstrates this method by analyzing actions related to runaways and itinerants in 18th and 19th-century Denmark, integrating close readings with automated graphing. AI

IMPACT This research demonstrates a novel application of machine learning for structuring historical data, potentially enabling new forms of historical analysis and discovery.

RANK_REASON Academic paper describing a new methodology and framework. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.IR (Information Retrieval) →

• alphaXiv
• auto-GRAMS
• CatalyzeX Code Finder for Papers
• Connected Papers
• CORE Recommender
• DagsHub
• Denmark
• Gotit.pub
• GRAM-framework
• Graph of Roles and Actions Model
• Hugging Face
• Influence Flower
• Litmaps
• ScienceCast
• scite Smart Citations

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →