Learning Emotion Indicators from Tweets: Hashtags, Hashtag Patterns, and Phrases

We present a weakly supervised approach for learning hashtags, hashtag patterns, and phrases associated with five emotions: AFFEC-TION, ANGER/RAGE, FEAR/ANXIETY, JOY, and SADNESS/DISAPPOINTMENT. Starting with seed hashtags to label an initial set of tweets, we train emotion classifiers and use them to learn new emotion hashtags and hashtag patterns. This process then repeats in a bootstrapping framework. Emotion phrases are also extracted from the learned hashtags and used to create phrase-based emotion classifiers. We show that the learned set of emotion indicators yields a substantial improvement in F-scores, ranging from +%5 to +%18 over baseline classifiers.