Fast and accurate sentiment classification using an enhanced Naive Bayes model
Computation and Language
2013-11-05 v2 Information Retrieval
Machine Learning
Abstract
We have explored different methods of improving the accuracy of a Naive Bayes classifier for sentiment analysis. We observed that a combination of methods like negation handling, word n-grams and feature selection by mutual information results in a significant improvement in accuracy. This implies that a highly accurate and fast sentiment classifier can be built using a simple Naive Bayes model that has linear training and testing time complexities. We achieved an accuracy of 88.80% on the popular IMDB movie reviews dataset.
Keywords
Cite
@article{arxiv.1305.6143,
title = {Fast and accurate sentiment classification using an enhanced Naive Bayes model},
author = {Vivek Narayanan and Ishan Arora and Arjun Bhatia},
journal= {arXiv preprint arXiv:1305.6143},
year = {2013}
}
Comments
8 pages, 2 figures