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.
|Title of host publication||Proceedings of the 2017 ACM on Conference on Information and Knowledge Management|
|Place of Publication||United States|
|Publisher||Association for Computing Machinery|
|Number of pages||4|
|Publication status||Published - 6 Nov 2017|
|Event||26th ACM International Conference on Information and Knowledge Management - Pan Pacific Singapore Hotel, Singapore, Singapore|
Duration: 6 Nov 2017 → 10 Nov 2017
|Name||International Conference on Information and Knowledge Management, Proceedings|
|Conference||26th ACM International Conference on Information and Knowledge Management|
|Abbreviated title||CIKM 2017|
|Period||6/11/17 → 10/11/17|
Bibliographical noteThis research was supported by the National Natural Science Foundation of China (61502545, 61472453, U1401256, U1501252, U1611264), Research Grants Council of Hong Kong Special Administrative Region, China (UGC/FDS11/E03/16), and the Internal Research Grant (RG 66/2016-2017) of The Education University of Hong Kong.
- Cross-domain classification
- Emotion detection