(German) Introduction to natural language processing with Python

Published on 2019-04-25

This is a talk given at the Linuxtage Graz on 2019-04-25, provided as Jupyter notebook to play around with yourself.

It covers the following topics:

• tag clouds, a visual representation of the most important words in a text
• explanation of basic terminology
• splitting text in sentences and works (tokens)
• token types and their roles
• sentiment analysis to extract the mood and rating of a text
• topic modelling to cluster similar texts together

The Jupyter notebook together with instructions on how to obtain the demo data are available from a GitHub project.

Watch the video