Affective computing
Building a large annotated corpus of English: the penn treebank
Computational Linguistics - Special issue on using large corpora: II
Emotion recognition from text using semantic labels and separable mixture models
ACM Transactions on Asian Language Information Processing (TALIP)
Emotion Classification Using Web Blog Corpora
WI '07 Proceedings of the IEEE/WIC/ACM International Conference on Web Intelligence
Learning to identify emotions in text
Proceedings of the 2008 ACM symposium on Applied computing
Towards Text-based Emotion Detection—A Survey and Possible Improvements
ICIME '09 Proceedings of the 2009 International Conference on Information Management and Engineering
UPAR7: a knowledge-based system for headline sentiment tagging
SemEval '07 Proceedings of the 4th International Workshop on Semantic Evaluations
Evaluation of unsupervised emotion models to textual affect recognition
CAAGET '10 Proceedings of the NAACL HLT 2010 Workshop on Computational Approaches to Analysis and Generation of Emotion in Text
| Hi-index | 0.00 |
Emotion detection from text is still an appealing challenge. The approaches to this problem have been done firstly based on just emotional keywords, and then extended with utilizing also other generic terms. However, they still lack of some useful semantic features, such as a psychological characteristic that emotion is the result of a mental state sequence. Recent works focus on using rules to exploit those features, but have the coverage problem. In this paper, we propose a method using the high-order Hidden Markov Model whose states are automatically generated to model the process that a mental state sequence causes an emotion. Our experiments on the ISEAR dataset have shown a better result in comparison with the state-of-the-art methods.