![]() |
NACSOS-nexusNACSOS 2 is our internal platform to perform large-scale systematic maps and reviews with machine learning assistance. It is inspired by the original NACSOS platform, but rewritten from the ground up. |
For more information, please check out the documentation or other supplemental materials linked below.
- Platform: https://nacsos.pik-potsdam.de/
- NACSOS Documentation: https://nacsos.pik-potsdam.de/docs/
- Source code: https://gitlab.pik-potsdam.de/mcc-apsis/nacsos
- Intro slides: Slides
If you used NACSOS in your academic work, please cite us as
Citation
Repke, Callaghan. 2025. "NACSOS-nexus: NLP Assisted Classification, Synthesis and Online Screening with New and EXtended Usage Scenarios". https://arxiv.org/abs/2405.04621
NACSOS—NLP Assisted Classification, Synthesis and Online Screening
NACSOS is a django site for managing collections of documents, screening or coding them by hand, and doing NLP tasks with them like topic modelling or classifiation.
It was built for handling collections of scientific document metadata, but has extensions that deal with twitter data and parliamentary data.
It currently contains many experimental, redundant or unsupported features, and is not fully documented.
The part that deals with topic modelling is a fork of Allison J.B Chaney’s tmv repository. It extends this by managing multiple topic models and linking these with various document collections.
NACSOS is research software produced by the “Evidence for climate solutions” (ECS, formerly APSIS) working group at the Mercator Research Institute on Global Commons and Climate Change (MCC), and some parts of the repository are instution specific. We are in an ongoing process of generalising, and documenting.
Refer to the documentation for a (partial) guide to using the app.
If you used the old version of NACSOS in academic work, you can cite it as
Citation
Max Callaghan, Finn Müller-Hansen, Jérôme Hilaire, & Yuan Ting Lee. (2020). NACSOS: NLP Assisted Classification, Synthesis and Online Screening. Zenodo. http://doi.org/10.5281/zenodo.4121525
