Semantic Role Labeling of Emotions in Tweets
Saif M. Mohammad, Xiaodan Zhu, Joel Martin · 2014
Past work on emotion processing has fo-cused solely on detecting emotions, and ignored questions such as ‘who is feeling the emotion (the experiencer)? ’ and ‘to-wards whom is the emotion directed (the stimulus)?’. We automatically compile a large dataset of tweets pertaining to the 2012 US presidential elections, and anno-tate it not only for emotion but also for the experiencer and the stimulus. We then develop a classifier for detecting emotion that obtains an accuracy of 56.84 on an eight-way classification task. Finally, we show how the stimulus identification task can also be framed as a classification task, obtaining an F-score of 58.30. 1