The human-like emotions recognition using mutual information and semantic clues. (English)
Chang, Maiga (ed.) et al., Edutainment technologies. Educational games and virtual reality/augmented reality applications. 6th international conference on e-learning and games, Edutainment 2011, Taipei, Taiwan, September 2011. Proceedings. Berlin: Springer (ISBN 978-3-642-23455-2/pbk). Lecture Notes in Computer Science 6872, 464-470 (2011).
Summary: In this work, we collect the sentences posted in Plurk as our corpus. The emoticons are classified into four types based on Thayer’s 2-D Model which is composed of valence (positive/negative emotions) and arousal (the strength of emotions). The system will preprocess the sentence to eliminate the useless information, and then transform it to be the emotion lexicon. Besides, this research analyzes three kinds of semantic clues: negation, transition, and coordinating conjunctions. The final emotion is decided by SVM and the merging algorithm proposed in this work.
Start
Contact
Print
General Help
