Review-Level Sentiment Classification with Sentence-Level Polarity Correction

TL;DR

This paper introduces a sentence-level polarity correction method to improve review-level sentiment classification, enhancing classifier accuracy by ensuring polarity consistency within reviews.

Contribution

It presents a novel polarity correction technique that filters inconsistent sentences, leading to improved sentiment classification performance across various product review domains.

Findings

Achieved an average of 82% F-measure across four product domains.

Outperformed baseline models without polarity correction.

Effective in handling diverse review types.

Abstract

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.