An Active Learning approach for political text annotation using the manifesto project corpus.

The experiments are explained in this manuscript.

A demo using active learning to annotate texts can be found here. The app uses some annotations to estimate the political bias of annotators in order to recommend 'unbiasing' news.

Create virtualenv:

python3.6 -m venv venv

Activate virtualenv:

source venv/bin/activate

Install dependencies:

pip install -r requirements.txt

Add API-Key to manifesto_data.py (see Manifesto Project Website).

See Readme.md in services directory.