Emotion Classification Using Massive Examples Extracted from the Web

In this paper, we propose a data-oriented method for inferring the emotion of a speaker conversing with a dialog system from the semantic content of an utterance. We first fully automatically obtain a huge collection of emotion-provoking event instances from the Web. With Japanese cho

• Type: Conference
• Year: 2008
• Where: COLING
• Authors: Ryoko Tokhisa, Kentaro Inui, Yuji Matsumoto
• Keywords: COLING 2008, Computational Linguistics, Data-oriented Method, Emotion-provoking Event Instances, Semantic Content