Knowing about people’s opinions and viewpoints plays an essential role in decision-making processes involving regular customers to executive managers. Therefore, in the past decade, with the advent of Web 2.0, a new orientation of natural language processing science called opinion mining has been emerged. The main problem of exploring feature-level opinions is the complexity of feature extraction and its relations with the words containing the sentiment within unstructured texts, which reduces the accuracy of opinion mining. The purpose of the structured opinion summarization is to demonstrate the mentioned features in the reviews and express the sentiment value of users for each feature, quantitatively. The main idea of this research is to consider the semantic (knowledge) to analyze the sentiment in the review by developing the opinion ontology. Therefore, a semantic framework as an integrated method is proposed in all stages of feature-based opinion summarization

Keywords