Beyond literal meaning, words have associations with sentiment, emotion,colour, and even music. Such affect associations are particularly salient in overtly creative instances of language, such as stories and poems. They arealso found in implicitly creative day-to-day formulations such as metaphors, hashtags, and opposing polarity phrases (phrases made of one positive word and one negative word). I will first present methods that capture affect associations of words, phrases, and metaphoric expressions. Then I will show how these associations can be used for sentiment analysis of tweets, understanding semantic composition, determining the mechanisms under pinning metaphor, detecting personality traits, analyzing stories, and even generating music from novels.
Dr. Saif M. Mohammad is Senior Research Officer at the National ResearchCouncil Canada (NRC). He received his Ph.D. in Computer Science from theUniversity of Toronto. His primary research interest is in ComputationalLinguistics, especially Lexical Semantics, Sentiment Analysis, CrowdAnnotations, Computational Studies of Literature, and InformationVisualization. His team developed a system that ranked first in recentSemEval shared tasks on the sentiment analysis of tweets and on aspect-based sentiment analysis. His word-emotion association resource, the NRCEmotion Lexicon, is widely used for text analysis and information visualization. His work on detecting emotions in social media and on generating music from text have garnered widespread media attention, including articles in Time, Slashdot, LiveScience, io9, The Physics arXiv Blog, PC World, and Popular Science. (Website: http://saifmohammad.com)