The project is about Brain Drain in Tunisia. A survey was conducted among Tunisian people in order to get answers of several questions about this topic. As a team, we are mainly interested in making analysis about two basic questions among all the questions being answered:
✦ What are the reasons that would push you to leave Tunisia? ✦ Socially, what’s the difference between Tunisia and abroad in social life?
The text mining project pipeline is as follow:
- Read questionnaire data from a csv file
- Initialize raw corpus
- Text cleaning
- Text representation
- Topic modeling
- Clustering
- Predictive modeling
- Visualization and interpretation of final results
We resort technically to the programming language Python.
