GradAscent at EmoInt-2017: Character and Word Level Recurrent Neural Network Models for Tweet Emotion Intensity Detection

• Egor Lakomkin ^[1] ; Chandrakant Bothe ^[1] ; Stefan Wermter ^[1]
  1. [1] University of Hamburg

     University of Hamburg

     Hamburg, Freie und Hansestadt, Alemania

     
• 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. 169-174
• Idioma: inglés
• Enlaces
  • Texto completo (pdf)
• Resumen

  • The WASSA 2017 EmoInt shared task has the goal to predict emotion intensity val- ues of tweet messages. Given the text of a tweet and its emotion category (anger, joy, fear, and sadness), the participants were asked to build a system that assigns emotion intensity values. Emotion inten- sity estimation is a challenging problem given the short length of the tweets, the noisy structure of the text and the lack of annotated data. To solve this problem, we developed an ensemble of two neural models, processing input on the charac- ter. and word-level with a lexicon-driven system. The correlation scores across all four emotions are averaged to determine the bottom-line competition metric, and our system ranks place forth in full inten- sity range and third in 0.5-1 range of in- tensity among 23 systems at the time of writing (June 2017).