Online citations, reference lists, and bibliographies.

Cross-Collection Emotion Tagging For Online News

L. Yu, X. Zhao, Chao Ching Wang, H. Zhang, Ying Zhang
Published 2016 · Computer Science

Cite This
Download PDF
Analyze on Scholarcy
Share
With the rapid development of Internet and social media, online news has become an important type of information that attracts millions of readers to express their emotions. Therefore, it is of great significance to build an emotion classifier for online news. However, it largely relies on the collection with sufficient labeled news to build an emotion classifier and the manually labeling work can be quite labor intensive. Moreover, different collections may have different domains such as politics or entertainment. Even in the same domain, different collections require different classifiers, since they have different emotion labels and feature distributions. In this paper, we focus on the task of cross-collection emotion tagging for online news. This task can be formulated as a transfer learning problem which utilizes a source collection with abundant labeled data and a target collection with limited labeled data within the same domain. We proposed a novel method to transfer knowledge from source collection to help build an emotion classifier for target collection. Experimental results on four real datasets show that our method outperforms competitive baselines.
This paper references
10.1145/1571941.1572093
Knowledge transformation for cross-domain sentiment classification
Tao Li (2009)
10.1145/2733373.2806216
Weakly-Shared Deep Transfer Networks for Heterogeneous-Domain Knowledge Propagation
Xiangbo Shu (2015)
Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification
John Blitzer (2007)
10.1109/TKDE.2009.191
A Survey on Transfer Learning
Sinno Jialin Pan (2010)
10.3115/1073083.1073153
Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews
Peter D. Turney (2002)
A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data
R. Ando (2005)
10.1145/2600428.2609587
Cross-domain and cross-category emotion tagging for comments of online news
Ying Zhang (2014)
10.1145/2348283.2348468
Emotion tagging for comments of online news by meta classification with heterogeneous information sources
Ying Zhang (2012)
10.1109/WIIAT.2008.197
Emotion Classification of Online News Articles from the Reader's Perspective
K. Lin (2008)
10.1145/2749459
Latent Discriminative Models for Social Emotion Detection with Emotional Dependency
Xiaojun Quan (2015)
10.1007/s10791-012-9196-x
Sentiment detection with auxiliary data
D. Zhang (2012)
10.1109/ICDM.2008.113
Document-Word Co-regularization for Semi-supervised Sentiment Analysis
V. Sindhwani (2008)
10.3115/1610075.1610094
Domain Adaptation with Structural Correspondence Learning
John Blitzer (2006)
10.1007/11562214_1
A New Method for Sentiment Classification in Text Retrieval
Y. Hu (2005)
10.1561/1500000011
Opinion Mining and Sentiment Analysis
Bo Pang (2007)
10.1007/978-3-319-25255-1_6
Multi-Label Emotion Tagging for Online News by Supervised Topic Model
Ying Zhang (2015)
10.3115/1118693.1118704
Thumbs up? Sentiment Classification using Machine Learning Techniques
B. Pang (2002)



This paper is referenced by
Semantic Scholar Logo Some data provided by SemanticScholar