Emotion Estimation Adapted to Gender of User Based on Deep Neural Networks

In this study, we focus on Twitter as a representative SNS and target emotion estimation from tweets posted on Twitter by male and female users. Specifically, we construct gender-based emotion estimation models assuming that there are different word usage tendencies between genders. By analyzing gender-specific differences in the use of emotion-related slang and emoji, we propose a method to improve emotion estimation based on neural networks using a different distributed representation model for each gender. Our evaluation experiments show that training with Deep Convolutional Neural Networks using word's distributed representation as the feature produced higher estimation accuracy than training with Feed Forward Neural Networks.