Association for Computing Machinery
Understanding the sentiment of sentences allows users to summarize opinions which could help people make informed decisions. All of the state-of-the-art algorithms perform well on individual sentences without considering any context in-formation, but their accuracy is dramatically lower on the document level because they fail to consider context and the syntactic structure of sentences at the same time. This paper proposes a method based on conditional random fields to incorporate sentence structure (syntax and semantics) and context information to identify sentiments of sentences within a document. It also proposes and evaluates two different active learning strategies for labeling sentiment data. The experiments with the proposed approach demonstrate a 5-15% improvement in accuracy on Amazon customer reviews compared to existing supervised learning and rule-based methods.