Towards answering opinion questions

TLDR

Opinion question answering is a challenging task for natural language processing. The paper aims to develop components for opinion question answering by separating opinions from facts at document and sentence levels and introducing a first model to classify opinion sentences as positive, negative, or neutral. We employ a Bayesian classifier to distinguish opinion‑rich documents from regular news and use three unsupervised statistical techniques to detect opinions at the sentence level, along with a model for classifying sentence sentiment. Results on a large news story collection and a human evaluation of 400 sentences show document classification precision and recall above 97 % and sentence‑level opinion detection and sentiment classification accuracy up to 91 %.

Abstract

Opinion question answering is a challenging task for natural language processing. In this paper, we discuss a necessary component for an opinion question answering system: separating opinions from fact, at both the document and sentence level. We present a Bayesian classifier for discriminating between documents with a preponderance of opinions such as editorials from regular news stories, and describe three unsupervised, statistical techniques for the significantly harder task of detecting opinions at the sentence level. We also present a first model for classifying opinion sentences as positive or negative in terms of the main perspective being expressed in the opinion. Results from a large collection of news stories and a human evaluation of 400 sentences are reported, indicating that we achieve very high performance in document classification (upwards of 97% precision and recall), and respectable performance in detecting opinions and classifying them at the sentence level as positive, negative, or neutral (up to 91% accuracy).