This paper addresses the problem of modeling textual conversations and detecting emotions. Our proposed model makes use of 1) deep transfer learning rather than the classical shallow methods of word embedding; 2) self-attention mechanisms to focus on the most important parts of the texts and 3) turn-based conversational modeling for classifying the emotions. The approach does not rely on any hand-crafted features or lexicons. Our model was evaluated on the data provided by the SemEval-2019 shared task on contextual emotion detection in text. The model shows very competitive results.

Dans ce papier, nous décrivons notre participation au défi d’analyse de texte DEFT 2018. Nous avons participé à deux tâches : (i) classification transport/non-transport et (ii) analyse de polarité globale des tweets : positifs, negatifs, neutres et mixtes. Nous avons exploité un réseau de neurone basé sur un perceptron multicouche mais utilisant une seule couche cachée.