Simpler is better? Lexicon-based ensemble sentiment classification beats supervised methods
- 1 August 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 924-929
Abstract
It has been shown in this paper that simplistic Bag of Words (BoW) lexicon methods for sentiment polarity assignment with ensemble classifiers are much faster than a supervised approach to sentiment classification while yielding similar accuracy. BoW methods also proved to be efficient and fast across all examined datasets. Moreover, a new approach to lexicon extraction that can be successfully used for sentiment polarity assignment is presented in the paper. It has been shown that accuracy obtained from such lexicons outperforms other lexicon based approaches.Keywords
This publication has 8 references indexed in Scilit:
- An Approach to Sentiment Analysis of Movie Reviews: Lexicon Based vs. Classification2014
- Hidden factors and hidden topics2013
- Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank2013
- A Survey of Opinion Mining and Sentiment Analysis2012
- Improving Opinion Retrieval Based on Query-Specific Sentiment Lexicon2009
- Opinion Mining and Sentiment AnalysisFoundations and Trends® in Information Retrieval, 2008
- Ensemble based systems in decision makingIEEE Circuits and Systems Magazine, 2006
- Bagging predictorsMachine Learning, 1996