An Iterative Emotion Classification Approach for Microblogs

详细信息    查看全文

• 作者：Ruifeng Xu (14)
  Zhaoyu Wang (14)
  Jun Xu (14)
  Junwen Chen (16)
  Qin Lu (15)
  Kam-Fai Wong (16)
  
  14. Shenzhen Engineering Laboratory of Performance Robots at Digital Stage ; Harbin Institute of Technology Shenzhen Graduate School ; Shenzhen ; China
  16. Dept. of Systems Engineering & Engineering Management ; The Chinese University of Hong Kong ; Shatin ; Hong Kong
  15. Dept. of Computing ; The Hong Kong Polytechnic University ; Kowloon ; Hong Kong
  
• 关键词：Emotion Classification ; Iterative Classification ; Microblogs
• 刊名：Lecture Notes in Computer Science
• 出版年：2015
• 出版时间：2015
• 年：2015
• 卷：9042
• 期：1
• 页码：104-113
• 全文大小：296 KB
• 参考文献：1. Quan, C., Ren, F.: Construction of a Blog Emotion Corpus for Chinese Emotional Expression Analysis. In: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pp. 1446鈥?454 (2009)
  2. Shen, Y., Li, S.: Emotion Mining Research on Micro-blog. In: Proceedings of 1st IEEE Symposium on Web Society, pp. 71鈥?5 (2009)
  3. Ma, C., Osherenko, A., et al.: A Chat System Based on Emotion Estimation from Text and Embodied Conversational Messengers. In: Proceedings of IEEE International Conference on Active Media Technology (2005)
  4. Strapparava, C., Mihalcea, R.: Learning to Identify Emotions in Text. In: Proceedings of 2008 ACM Symposium on Applied Computing, pp. 1556鈥?560 (2008)
  5. Aman, S., Szpakowicz, S. Identifying Expressions of Emotion in Text. In: Matou拧ek, V., Mautner, P. eds. (2007) Text, Speech and Dialogue. Springer, Heidelberg, pp. 196-205 CrossRef
  6. Pang, L., Li, S., Zhou, G. (2012) Emotion Classification Method of Chinese Micro-blog Based on Emotional Knowledge. Computer Engineering 38: pp. 156-158
  7. Pak, A., Paroubek, P.: Twitter as a Corpus for Emotion Analysis and Opinion Mining. In: Proceedings of Language Resources and Evaluation Conference, pp. 1320鈥?326 (2010)
  8. Zhang, J., Zhu, B. (2014) Recognition and Classification of Emotions in the Chinese Microblog based on Emotional Factor. Journal of Peking University 50: pp. 79-84
  9. He, F., He, Y. (2014) A Microblog Short Text Oriented Multi-class Feature Extraction Method of Fine-Grained Emotion Analysis. Journal of Peking University 50: pp. 48-54
  10. Ouyang, C., Yang, X., Lei, L. (2014) Multi-strategy Approach for Fine-grained Emotion Analysis of Chinese Micro-blog. Journal of Peking University 50: pp. 67-72
  11. Liu, Z., Liu, L. (2012) Empirical Study of Emotion Classification for Chinese Microblog based on Machine Learning. Computer Engineering and Applications 48: pp. 1-4
  12. Lin, J., Yang, A., Zhou, Y. (2012) Classification of Microblog Emotion Based on Na茂ve Bayesian. Computer Engineering and Science 34: pp. 160-165
  13. Tsoumakas, G., Katakis, I., Vlahavas, I.: Mining Multi-label Data. In: Data Mining and Knowledge Discovery Handbook, pp. 667鈥?85. Springer (2010)
  14. Ghamrawi, N., McCallum, A.: Collective Multi-label Classification. In: Proceedings of the 2005 ACM Conference on Information and Knowledge Management, pp. 195鈥?00 (2005)
  15. Hullermeier, E., Furnkranz, J., Cheng, W. (2008) Label Ranking by Learning Pairwise Preferences. Artificial Intelligence 172: pp. 1897-1916 CrossRef
  16. Trohidis, K., Tsoumakas, G., Kalliris, G., et al.: Multilabel Classification of Music into Emotions. In: Proceedings of 2008 International Conference on Music Information Retrieval, pp. 325鈥?30 (2008)
  
• 作者单位：Computational Linguistics and Intelligent Text Processing
• 丛书名：978-3-319-18116-5
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

The typical emotion classification approach adopts one-step single-label classification using intra-sentence features such as unigrams, bigrams and emotion words. However, single-label classifier with intra-sentence features cannot ensure good performance for short microblogs text which has flexible expressions. Target to this problem, this paper proposes an iterative multi-label emotion classification approach for microblogs by incorporating intra-sentence features, as well as sentence and document contextual information. Based on the prediction of the base classifier with intra-sentence features, the iterative approach updates the prediction by further incorporating both sentence and document contextual information until the classification results converge. Experimental results obtained by three different multi-label classifiers on NLP & CC2013 Chinese microblog emotion classification bakeoff dataset demonstrates the effectiveness of our iterative emotion classification approach.