Polarity Classification Based on Sentiment Tags

被引：0
|
作者：
Zhou M. [1 ]
Zhu F.-X. [1 ]
机构：
[1] Computer School, Wuhan University, Wuhan, 430072, Hubei
来源：
Zhu, Fu-Xi (fxzhu@whu.edu.cn) | 1600年 / Chinese Institute of Electronics卷 / 45期
关键词：
Co-training learning; Polarity classification; Semi-supervised learning; Sentiment tag;
D O I：
10.3969/j.issn.0372-2112.2017.04.034
中图分类号：
学科分类号：
摘要：
Sentiment analysis is a very important technology in text mining. However, a number of systems require amounts of annotated training data in different fields. In order to solve these problems, an approach to polarity classification based on sentiment tags is proposed. Firstly, on the basis of all the documents, the sentiment-topic model is developed and the sentiment tags for each review are extracted. Then each review is divided into two sub-texts by these sentiment tags, and each sub-text is classified by exploiting the co-training algorithm. Finally, the category results of two sub-texts are combined to determine document-level polarity of each review. Experimental results show that compared with other algorithms, the method improves the classification precision without a large number of annotated samples. © 2017, Chinese Institute of Electronics. All right reserved.
引用
收藏
页码：1018 / 1024
页数：6
相关论文
共 24 条
  • [1] Pang B., Lee L., Vaithyanathan S., Thumbs up? Sentiment classification using machine learning techniques, Proceedings of the ACL-02 Conference on Empirical Methods in Natural Language Processing, 10, pp. 79-86, (2002)
  • [2] Turney P.D., Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews, Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 417-424, (2002)
  • [3] Pang B., Lee L., Opinion mining and sentiment analysis, Foundations and Trends in Information Retrieval, 2, 1-2, pp. 1-135, (2008)
  • [4] Feng S., Fu Y., Yang F., Et al., Blog sentiment orientation analysis based on dependency parsing, Journal of Computer Research and Development, 49, 11, pp. 2395-2406, (2012)
  • [5] Tan C., Lee L., Tang J., Et al., User-level sentiment analysis incorporating social networks, Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1397-1405, (2011)
  • [6] Zhao Y., Qin B., Liu T., Sentiment analysis, Journal of Software, 21, 8, pp. 1834-1848, (2010)
  • [7] Yessenalina A., Yue Y., Cardie C., Multi-level structured models for document-level sentiment classification, Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pp. 1046-1056, (2010)
  • [8] Wang L.-D., Wei B.-G., Yuan J., Document clustering based on probabilistic topic model, Acta Electronica Sinica, 40, 11, pp. 2346-2350, (2012)
  • [9] Cui H., Mittal V., Datar M., Comparative experiments on sentiment classification for online product reviews, Proceedings of AAAI the 21st National Conference on Artificial Intelligence, pp. 1265-1270, (2006)
  • [10] Kim S.M., Hovy E., Automatic identification of pro and con reasons in online reviews, Proceedings of the COLING/ACL on Main Conference Poster Sessions, pp. 483-490, (2006)
123