Existing opinion analysis techniques rely on the clues within the sentence that focus on the sentiment analysis task itself. However, the sentiment analysis task is not isolated from other NLP tasks (co-reference resolution, entity linking, etc) but they can benefit each other. In this paper, we define dependencies between sentiment analysis and other tasks, and express the dependencies in first order logic rules regardless of the representations of different tasks. The conceptual framework proposed in this paper using such dependency rules as constraints aims at exploiting information outside the sentence and outside the document to improve sentiment analysis. Further, the framework allows exception to the rules.
展开▼
