A Multi-Level Naïve Bayes Classifier for Sentiment Classification

Abstract:

A great demand of sentiment classification comes with the rapid development of the internet. At present, the methods about sentiment classification based on machine learning have been widely used. The sentiment classification is a more difficult task, which needs more in-depth study than the traditional topic-based classification method [1]. Naïve Bayesian classifier is widely used in text classification. However, it requires two basic assumptions as its prerequisite and the performance would have been poor if these two were dissatisfied. We propose a multi-level naïve Bayes classifier to make up the deficiency of the traditional naïve Bayes classifier. The research below shows that the multi-level naïve Bayes classifier gets better performance than the traditional naïve Bayes classifier on the sentiment classification of movie reviews.

• Periodical: Advanced Engineering Forum (Volumes 6-7)
• Pages: 553-560
• DOI: https://doi.org/10.4028/www.scientific.net/AEF.6-7.553
• Online since: September 2012
• Authors: Jun Zheng Shi, Lei Guo, Shi Min Wei
• Keywords: Multi-Mixture Model, Naive Bayes Classifier, Sentiment Classification

References

[1] B. Pang, L. Lee. Opinion mining and sentiment analysis. Foundation and Trends in Information Retrieval. 2008. 2(1-2). 1-135.

[2] B. Pang, L. Lee, and S. Vaithyanathan. Thumbs up? Sentiment classification using machine learning techniques, Proceedings of EMNLP Philadelphia, USA: ACL, 2002: 79-86.

DOI: 10.3115/1118693.1118704

[3] B. Pang, L. Lee. A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts. In Proceedings of the Association for Computational Linguistics. Barcelona, Spain. 2004. Morristown, USA. Association for Computational Linguistics. 2004. 271-278.

DOI: 10.3115/1218955.1218990

[4] Zhang Yan-bo. Research of Text Sentiment Classification [Dissertation]. Beijing. Beijing Jiaotong University, (2010).

[5] FAN Xing-Hua, SUN Mao-Song. High Performance Two-Class Chinese Text Categorization Method. CHINESE JOURNAL OF COMPUTERS, 2006, (01) . 124-131.

[6] K. Nigam, A. K. McCallum, S. Thrun, and T. Mitchell, Text classification from labeled and unlabeled documents using EM, Machine Learning, Vol. 39, and pp.: 103-134.

DOI: 10.21236/ada350490

[7] John Blitzer, Ryan McDonald, Fernando Percira. Domain adaptation with structural correspondence learning[C]. Processings of the 2006 Conference on Empirical Methods in Natural Language Processing, Sydney, Australia, July 2006, PP. 120-128.

DOI: 10.3115/1610075.1610094

[8] Dai W. Y, GR Xue, Q. Yang, and Y. Yu. Transferring naive Bayes classifiers for text classification. In Proceedings of the 22nd Conference on Artificial Intelligence (AAAI), pages 540–545, (2007).