TY - GEN
T1 - Cluster-level emotion pattern matching for cross-domain social emotion classification
AU - Zhu, Endong
AU - Rao, Yanghui
AU - Xie, Haoran
AU - Liu, Yuwei
AU - Yin, Jian
AU - Wang, Fu Lee
N1 - Publisher Copyright:
© 2017 Association for Computing Machinery.
PY - 2017/11/6
Y1 - 2017/11/6
N2 - 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.
AB - 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.
KW - Clustering
KW - Cross-domain classification
KW - Emotion detection
UR - http://www.scopus.com/inward/record.url?scp=85037331234&partnerID=8YFLogxK
U2 - 10.1145/3132847.3133063
DO - 10.1145/3132847.3133063
M3 - Conference contribution
AN - SCOPUS:85037331234
T3 - International Conference on Information and Knowledge Management, Proceedings
SP - 2435
EP - 2438
BT - CIKM 2017 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management
T2 - 26th ACM International Conference on Information and Knowledge Management, CIKM 2017
Y2 - 6 November 2017 through 10 November 2017
ER -