A multi-task neural network for multilingual sentiment classification and language detection on Twitter

Jonatas Wehrmann, Willian E. Becker, Rodrigo C. Barros

Abstract: In this paper, we propose a novel approach for classifying both the sentiment and the language of tweets. Our proposed architecture comprises a convolutional neural network (ConvNet) with two distinct outputs, each of which designed to minimize the classification error of either sentiment assignment or language identification. Results show that our method outperforms both single-task and multi-task state-of-the-art approaches for classifying multilingual tweets.