Download poster and program (PDF): here 

Data collection and preparation

 May 6, 2024

Training morning

8.45am to 9.30am: Welcome greetings

9.30am to 12.30am (including a break): Training of your choice:

• Data collection
  

- what is webscraping
- getting familiar with web technologies: creating and publishing our first website from scratch!
- understanding selectors
- webscraping static pages with python
- understanding dynamic web pages
- scraping dynamic web pages with python and selenium

Speaker: Laurent Berge (Associate professor, University of Bordeaux, BSE)

• Textual data processing (text mining)

 During this workshop, the participants will learn the basics of text processing in python. Through practical implementations the participants will familiarize themselves with specific terminology, progressing in practical and theoretical knowledge. One part of the workshop will be dedicated to the tasks of text cleaning and its preparation for further analysis, using 'spacy' and 'nltk' libraries. Also,  the subject of text vectorization, and word and sentence embeddings will be presented.

The workshop is dedicated for beginners in text processing. The knowledge of python is useful but not mandatory.

Speaker: Olha Nahorna (Research engineer, CNRS, BSE)

 12.30pm to 2pm: Lunch 

Afternoon of presentations

2pm to 3 pm : Key-note speaker Kévin Cortial et Nicolas Sauzéat (OpenStudio)

Towards agile and resilient industrial sectors: the atlas of productive synergies

3pm to 3:45pm : Andriy Romanyuk (BSE, University of Bordeaux), Francesco Lissoni (BSE, University of Bordeaux)

Stay rates and careers of foreign doctorate recipients from Dutch universities: A bibliometric analysis

3:45pm to 4pm : Pause

4pm to 4:45 : Océane Tenebay (THEMA, CY Cergy Paris Université)

Estimation of land use regulations from past building permits

4:45pm to 5:45pm :  Tommaso Bianco ((CTO, independent researcher),Aurélien Hazan (LISSI, Université Paris Est Créteil), Arnold Vialfont  (ERUDITE, Université Paris Est Créteil)

• A network exploratory analysis of firm ownership at subgraph level, in the case of France
• Information extraction for the analysis of the French Competition Authority’s decisions using machine learning

Join us by videoconference for free (only on afternoon)!

7pm to 11pm: Gala dinner