Keywords: Twitter | Natural Language Processing | Deep Learning | Graph theory
Project coordinator: Stefanie Bailer
CeDA collaborator: Sébastien Boyer

Project objectives

  • Characterizing the different flavors of interactions (positive, negative, offensive, etc...) between politicians and the general public on social media.


  • Multilingual context dependent word embedding for sentences classification.
  • Graph representation of social media interaction.

Analytical methods

  • Transformer-based Deep Neural Networks: Multilingual BERT or XML-RoBERTa.
  • Graph Convolutional Neural Networks.

Figure 1. Tweets sentiment analysis based on context dependent word embedding, allows us to draw with confidence, directed edges representing emotional flow between politician tweets.ΒΆ