A Statistical Parsing Framework for Sentiment Classification

TL;DR

This paper introduces a probabilistic sentiment parsing framework that directly analyzes sentence sentiment structures, effectively handling complex phenomena like negation and contrast, and demonstrates improved classification accuracy on benchmark datasets.

Contribution

It develops a novel sentiment parser based on CFGs that trains directly from sentiment labels without requiring syntactic annotations, enabling better handling of complex sentiment phenomena.

Findings

Significant accuracy improvements over baseline methods

Effective handling of negation, intensification, and contrast

Training from large-scale sentiment-labeled review data

Abstract

We present a statistical parsing framework for sentence-level sentiment classification in this article. Unlike previous works that employ syntactic parsing results for sentiment analysis, we develop a statistical parser to directly analyze the sentiment structure of a sentence. We show that complicated phenomena in sentiment analysis (e.g., negation, intensification, and contrast) can be handled the same as simple and straightforward sentiment expressions in a unified and probabilistic way. We formulate the sentiment grammar upon Context-Free Grammars (CFGs), and provide a formal description of the sentiment parsing framework. We develop the parsing model to obtain possible sentiment parse trees for a sentence, from which the polarity model is proposed to derive the sentiment strength and polarity, and the ranking model is dedicated to selecting the best sentiment tree. We train the parser directly from examples of sentences annotated only with sentiment polarity labels but without any syntactic annotations or polarity annotations of constituents within sentences. Therefore we can obtain training data easily. In particular, we train a sentiment parser, s.parser, from a large amount of review sentences with users' ratings as rough sentiment polarity labels. Extensive experiments on existing benchmark datasets show significant improvements over baseline sentiment classification approaches.