https://github.com/jethronap/asylumdata_ku

Text Mining and NLP Analysis on Data from https://fln.dk/praksis
https://github.com/jethronap/asylumdata_ku

feature-extraction jupyter-notebook nlp python text-mining topic-modeling

Last synced: about 1 month ago
JSON representation

Text Mining and NLP Analysis on Data from https://fln.dk/praksis

• Host: GitHub
• URL: https://github.com/jethronap/asylumdata_ku
• Owner: jethronap
• Created: 2022-04-19T07:49:59.000Z (almost 3 years ago)
• Default Branch: main
• Last Pushed: 2022-08-18T10:47:59.000Z (over 2 years ago)
• Last Synced: 2023-10-17T09:37:15.652Z (over 1 year ago)
• Topics: feature-extraction, jupyter-notebook, nlp, python, text-mining, topic-modeling
• Language: Jupyter Notebook
• Homepage:
• Size: 52.6 MB
• Stars: 1
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Trying to understand Asylum Practices in Denmark.

This repository contains the source code for the analysis of data from the Danish Refugee Appeals Board (Flygtningenævnet). The data are case summaries in textual format and are publicly available from https://fln.dk/praksis.

The source code for the steps of the analysis is included in each jupyter notebook. Notebooks starting with `UH` refer to cases denoted as Unknown Homeland. `ALL` is used for all other cases.

## Running the notebooks:

Before running the notebooks please `cd` into the `requirements` then

```

pip install - r requirements_(respective notebook name).txt

```

The previous command will install the appropriate dependencies for each notebook. 

However, please run first:

```

pip install - r requirements_utilities.txt

```

This will install all dependencies used in the helpers functions found [in this subdirectory](https://github.com/jethronap/AsylumData_KU/tree/main/utilities).

### Disclaimer:

This project is still a work in progress.