deepCybErNet at EmoInt-2017: Deep Emotion Intensities in Tweets

• Vinayakumar R ^[1] ; Premjith B ^[1] ; Sachin Kumar S ^[1] ; Soman K P ^[1] ; Prabaharan Poornachandran ^[1]
  1. [1] Amrita University, India
• Localización: 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis WASSA 2017: Proceedings of the Workshop / Alexandra Balahur Dobrescu (ed. lit.), Saif M. Mohammad (ed. lit.), Erik van der Goot (ed. lit.), 2017, ISBN 978-1-945626-95-1, págs. 259-263
• Idioma: inglés
• Enlaces
  • Texto completo (pdf)
• Resumen

  • This working note presents the method- ology used in deepCybErNet submission to the shared task on Emotion Intensities in Tweets (EmoInt) WASSA-2017. The goal of the task is to predict a real val- ued score in the range [0-1] for a particular tweet with an emotion type. To do this, we used Bag-of-Words and embedding based on recurrent network architecture. We have developed two systems and experi- ments are conducted on the Emotion In- tensity shared Task 1 data base at WASSA- 2017. A system which uses word em- bedding based on recurrent network archi- tecture has achieved highest 5 fold cross- validation accuracy. This has used embed- ding with recurrent network to extract op- timal features at tweet level and logistic regression for prediction. These methods are highly language independent and ex- perimental results shows that the proposed methods is apt for predicting a real valued score in than range [0-1] for a given tweet with its emotion type.