Workshop - New Analysis Methods and their Implication for Megadata Management in SSH (part 2)

This panel is part of the training Megadata and Advanced Techniques Demystified (session 7).

Humanities and social sciences are often confronted with the analysis of unstructured data, such as text. After preparing the data, several analysis techniques from machine learning can be used. During this workshop, participants will be introduced to pre-processing textual data and supervised and unsupervised methods for analysis purposes with Python.

Note: It is not mandatory to have followed part 1 (October 27 session) to attend this workshop. However, you can watch it again in replay if you wish.

Workshop structure

  • Part 1: Plenary presentation of supervised and unsupervised methods with a Python script (60 minutes)
  • Part 2: Individual and team work (20 minutes)
  • Part 3: Conclusion in plenary mode (10 minutes)

Whether you have Python programming skills or not, this workshop will allow you to use your knowledge of statistics and data analysis, and to discover the possibilities of automatic natural language processing.

What can you expect? Here's a quick overview!


This is a bi-modal session that you could attend on site or online.

Simultaneous translation available.


Bruno Agard
Professeur titulaire au département de mathématiques et de génie industriel à Polytechnique Montréal

Davide Pulizzotto
PhD en Sémiotique et spécialiste en analyse de texte assistée par ordinateur dans le domaine des sciences sociales (Text Mining for Humanities) à Polytechnique Montréal

Informations :

This content has been updated on 2022-11-23 at 16 h 14 min.