Ensemble learning for sentiment classification

Authors:
Ying Su;Yong Zhang;Donghong Ji;Yibing Wang;Hongmiao Wu
Affiliations:
Department of Computer and Electronic, Huazhong University of Science and Technology Wuchang Branch, Wuhan, P.R. China;Computer School, Wuhan University, Wuhan, P.R. China, Department of Computer Science, Huazhong Normal University, Wuhan, P.R. China;Computer School, Wuhan University, Wuhan, P.R. China;Third Faculty, Second Artillery Command College, P.R. China;School of Foreign Languages and Literature, Wuhan University, Wuhan, P.R. China
Venue:
CLSW'12 Proceedings of the 13th Chinese conference on Chinese Lexical Semantics
Year:
2012

Citing 16
Cited 1

Original Contribution: Stacked generalization

Neural Networks
On the Optimality of the Simple Bayesian Classifier under Zero-One Loss

Machine Learning - Special issue on learning with probabilistic representations
Data mining: practical machine learning tools and techniques with Java implementations

Data mining: practical machine learning tools and techniques with Java implementations
Measures of Diversity in Classifier Ensembles and Their Relationship with the Ensemble Accuracy

Machine Learning
Naive (Bayes) at Forty: The Independence Assumption in Information Retrieval

ECML '98 Proceedings of the 10th European Conference on Machine Learning
Thumbs up?: sentiment classification using machine learning techniques

EMNLP '02 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - Volume 10
Combining Information Extraction Systems Using Voting and Stacked Generalization

The Journal of Machine Learning Research
A survey on sentiment detection of reviews

Expert Systems with Applications: An International Journal
Recognizing contextual polarity: An exploration of features for phrase-level sentiment analysis

Computational Linguistics
Issues in stacked generalization

Journal of Artificial Intelligence Research
The effect of negation on sentiment analysis and retrieval effectiveness

Proceedings of the 18th ACM conference on Information and knowledge management
Mine the easy, classify the hard: a semi-supervised approach to automatic sentiment classification

ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2 - Volume 2
Adapting information bottleneck method for automatic construction of domain-oriented sentiment lexicon

Proceedings of the third ACM international conference on Web search and data mining
Semi-supervised latent variable models for sentence-level sentiment analysis

HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers - Volume 2
Sentiment analysis for online reviews using an author-review-object model

AIRS'11 Proceedings of the 7th Asia conference on Information Retrieval Technology
Modeling review comments

ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1

Sentiment classification: The contribution of ensemble learning

Decision Support Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents an ensemble learning method for sentiment classification of reviews. The diversity among the machine learning algorithms for sentiment classification with different settings, which includes different features, different weight measures and the modeling of negation, is investigated in three domains, which gives a space for improving the performance. Then the ensemble learning framework, stacking generalization is introduced based on different algorithms with different settings, and compared with the majority voting. According to the characteristic of reviews, the opinion summary of review is proposed in this paper, which is composed of the first two and last two sentences of review. Results show that stacking has been proven to be consistently effective over all domains, working better than majority voting, and that using the opinion summary can improve the performance further.