Review-Level Sentiment Classification with Sentence-Level Polarity Correction
This addresses sentiment classification for product reviews, but it is incremental as it builds on existing methods with a correction technique.
The paper tackled review-level sentiment classification by removing sentences with inconsistent polarities and using consistent ones to train classifiers, achieving an average F-measure of 82% across four product review domains.
We propose an effective technique to solving review-level sentiment classification problem by using sentence-level polarity correction. Our polarity correction technique takes into account the consistency of the polarities (positive and negative) of sentences within each product review before performing the actual machine learning task. While sentences with inconsistent polarities are removed, sentences with consistent polarities are used to learn state-of-the-art classifiers. The technique achieved better results on different types of products reviews and outperforms baseline models without the correction technique. Experimental results show an average of 82% F-measure on four different product review domains.