Fiche du document
2 octobre 2018
- handle: 10670/1.wdobot
- GOid: 0xc1aa5576_0x003a10ea
info:eu-repo/semantics/openAccess
Mots-clés
Linguistics and LiteratureSujets proches
Knowledge, Classification ofCiter ce document
Elena Cabrio et al., « InriaFBK at Germeval 2018: Identifying Offensive Tweets Using Recurrent Neural Networks », Elektronisches Publikationsportal der Österreichischen Akademie der Wissenschafte, ID : 10670/1.wdobot
Métriques
Partage / Export
Résumé
In this paper, we describe two systems for predicting message-level offensive language in German tweets: one discriminates between offensive and not offensive messages, and the second performs a fine-grained classification by recognizing also classes of offense. Both systems are based on the same approach, which builds upon Recurrent Neural Networks used with the following features: word embeddings, emoji embeddings and social-network specific features. The model is able to combine word-level information and tweet-level information in order to perform the classification tasks.