赞
踩
Sentiment Analysis and Opinion Mining (P23):
Document sentiment classification is perhaps the most extensively studied topic. It aims to classify an opinion document as expressing a positive or negative opinion or sentiment. A large majority of research papers on this topic classifies online reviews.
Problem definition: Given an opinion document d evaluating an entity, determine the overall sentiment s of the opinion holder about the entity, i.e., determine s expressed on aspect GENERAL in the quintuple (_, GENERA L, s, _, _ ), where the entity e, opinion holder h, and time of opinion t are assumed known or irrelevant (do not care).
Assumption: Sentiment classification or regression assumes that the opinion document d (e.g., a product review) expresses opinions on a single entity e and contains opinions from a single opinion holder h. This assumption holds for reviews of products and services because each review usually focuses on evaluating a single product or service and is written by a single reviewer.
If sentiment takes categorical values, e.g., positive and negative, then it is a typical classification problem.
If sentiment takes numeric values or ordinal scores within a given range, e.g., 1~5, the problem becomes regression.
Most existing techniques for document-level classification use supervised learning, although there are also unsupervised methods. Sentiment regression has been done mainly using supervised learning.
Sentiment classification is essentially a text classification problem.
Traditional text classification mainly classifies documents of different topics, e.g., politics, sciences, and sports. In such classifications, topic-related words are the key features.
However, in sentiment classification, sentiment or opinion words that indicate positive or negative opinions
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。