NSEmo at EmoInt-2017: An Ensemble to Predict Emotion Intensity in Tweets

• Sreekanth Madisetty ^[1] ; Maunendra Sankar Desarkar ^[1]
  1. [1] IIT Hyderabad, Hyderabad, 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. 219-224
• Idioma: inglés
• Enlaces
  • Texto completo (pdf)
• Resumen

  • In this paper, we describe a method to pre- dict emotion intensity in tweets. Our ap- proach is an ensemble of three regression methods. The first method uses content- based features (hashtags, emoticons, elon- gated words, etc.). The second method considers word n-grams and character n- grams for training. The final method uses lexicons, word embeddings, word n- grams, character n-grams for training the model. An ensemble of these three meth- ods gives better performance than individ- ual methods. We applied our method on WASSA emotion dataset. Achieved re- sults are as follows: average Pearson cor- relation is 0.706, average Spearman cor- relation is 0.696, average Pearson corre- lation for gold scores in range 0.5 to 1 is 0.539, and average Spearman correlation for gold scores in range 0.5 to 1 is 0.514.