Using Hashtags to Capture Fine Emotion Categories from Tweets

• DOI: 10.1111/coin.12024
• Publication Date: 2014-01-10T07:48:25Z
• Authors: Saif M. Mohammad; Svetlana Kiritchenko
• Keywords: Sentiment Analysis; Microblogging; Admiration; Emotion detection

Detecting emotions in microblogs and social media posts has applications for industry, health, security. Statistical, supervised automatic methods emotion detection rely on text that is labeled emotions, but such data are rare available only a handful of basic emotions. In this article, we show emotion‐word hashtags good manual labels tweets. We also propose method to generate large lexicon word–emotion associations from emotion‐labeled tweet corpus. This the first with real‐valued association scores. begin experiments six hashtag annotations consistent match trained judges. how extracted corpus can be used improve classification accuracy different nontweet domain. Eminent psychologist Robert Plutchik had proposed have relationship personality traits. However, empirical establish been stymied by lack comprehensive resources. Because may associated any hundreds because our approach scales easily number extend collecting tweets pertaining 585 fine Then, time, present categories as those excitement, guilt, yearning, admiration useful automatically detecting text. Stream‐of‐consciousness essays collections Facebook marked traits author test sets.