Link agency CBJ sections to matching appropriations report language using keywords, topic modeling, and ML.
Problem
Connecting agency budget justifications (CBJs) with relevant sections of appropriations committee reports (which explain funding decisions and provide directives to agencies) requires manual cross-referencing and analysis.
Solution
Develop a system to automatically link sections of CBJs to corresponding sections in appropriations committee reports. This could involve:
- Keyword Matching: Identifying shared keywords and phrases between CBJ sections and report sections.
- Topic Modeling: Using natural language processing techniques to identify thematic similarities between documents.
- Machine Learning: Training a model to recognize relationships between CBJ requests and committee report language.