Abstract
This paper addresses the task of cross-domain social emotion classification of online documents. The cross-domain task is formulated as using abundant labeled documents from a source domain and a small amount of labeled documents from a target domain, to predict the emotion of unlabeled documents in the target domain. Although several cross-domain emotion classification algorithms have been proposed, they require that feature distributions of different domains share a sufficient overlapping, which is hard to meet in practical applications. This paper proposes a novel framework, which uses the emotion distribution of training documents at the cluster level, to alleviate the aforementioned issue. Experimental results on two datasets show the effectiveness of our proposed model on cross-domain social emotion classification. Copyright © 2017 Association for Computing Machinery.
Original language | English |
---|---|
Title of host publication | CIKM '17 Proceedings of the 2017 ACM Conference on Information and Knowledge Management, November 6-10, 2017, Singapore |
Place of Publication | New York |
Publisher | ACM |
Pages | 2435-2438 |
ISBN (Electronic) | 9781450349185 |
DOIs | |
Publication status | Published - 2017 |
Citation
Zhu, E., Rao, Y., Xie, H., Liu, Y., Yin, J., & Wang, F. L. (2017). Cluster-level emotion pattern matching for cross-domain social emotion classification. In CIKM '17 Proceedings of the 2017 ACM Conference on Information and Knowledge Management, November 6-10, 2017, Singapore (pp. 2435-2438). New York: ACM.Keywords
- Emotion detection
- Cross-domain classification
- Clustering