Differential Language Analysis ToolKit

Differential Language Analysis ToolKit

DLATK is an end to end human text analysis package, specifically suited for social media and social scientific applications. It is written in python 3 and developed by the World Well-Being Project at the University of Pennsylvania.

It contains:

feature extraction part-of-speech tagging correlation prediction and classification mediation dimensionality reduction and clustering wordcloud visualization

DLATK can utilize:

Mallet for creating LDA topics Stanford Parser CMU's TweetNLP pandas dataframe output Installation

DLATK is available via conda, pip or github.

conda install -c wwbp dlatk pip install dlatk python setup.py install Dependencies mysqlclient NumPy scikit-learn SciPy statsmodels

See the full installation instructions for recommended and optional dependencies.

Documentation

The documentation for the latest release is at dlatk.wwbp.org .

License

Licensed under a GNU General Public License v3 (GPLv3)

Background

Developed by the World Well-Being Project based out of the University of Pennsylvania.