San Francisco, California
London, United Kingdom
With social networks and massive digitalization projects, nowadays the Internet has lots of data ready for analysis, at the hand of whoever wants to work with it. With these data, we can study social movements, the evolution of a concept or the public interest for a specific brand -- in fact, we can study everything that uses text. For massive datasets, we use automatic learning and text mining algorithms to extract concepts and associations to analyze.
In collaboration with the [Laboratoire d'analyse cognitive de l'information (LANCI)][lanci], Montréal-Python invites you to discover these text analysis methods, in English. Only basic knowledge of Python programming is required.
In this workshop, you'll learn:
- the different steps of computer assisted text analysis
- the fundamental concepts of distributed linguistics and its impact on text analysis
- to use the main techniques of text preprocessing
- to cut a text and regroup it by similar segments
- to extract the representative terms of one or many textes
Bring your laptop or pair up with someone else.
You'll need Python running on your computer, with these modules installed : pattern, numpy and scipy. It's also recommended to have IPython installed.
Generally speaking, if you want to have fun with the code in Montréal-Python workshops without loosing your time with configuring your machine and if you want a guaranteed support by the assistants, do yourself a favor and get a developer workstation on Ubuntu by following these simple steps.
If you need help to setup your development environment, we'll be there to help before the workshop, starting at 5:30 PM.
See you next Thursday!
When & Where
Connecting nodes in the Montreal data community since 2014.