Arabic Tweet-Act: Speech Act Recognition for Arabic Asynchronous Conversations

摘要: Speech acts are the actions that a speaker intends when performing an utterance within conversations. In this paper, we proposed speech act classification for asynchronous conversations on Twitter using multiple machine learning methods including SVM and deep neural networks. We applied ArSAS tweets dataset. The obtained results show superiority of compared to SVMs, where Bi-LSTM managed achieve accuracy 87.5% macro-averaged F1 score 61.5%. believe our first be reported task speech-act recognition Arabic Twitter.