A linguistic approach for opinionated documents summary

Now, the web pages contain opinions on almost anything, at review sites, forums, discussion groups, and blogs which called user generated content. They contain valuable information for different users such as persons or organizations, the processes of collecting, analyzing and classifying them to positive or negative opinions in addition to summarizing the opinions are considered a very important research issue. Summarizing opinions helps users to explore the opinion of others about the key aspects of a topic or an entity. The proposed opinion summarization system receives a document that contains sentences expressing opinions about an entity and generates a summary considering the important aspects, their relations, their sentiments and the textual evidences, as expressed in the reviews. In this paper we present a linguistic approach to summarize the opinionated documents across different domains, our evaluation based on a dataset of hotels, cars and various products reviews. The reviews collected from Tripadvisor, Amazon and Edmunds, each review document consist of a set of unordered, redundant reviews sentence, there are approximately 100 sentences per review document. The summary depends on the type of the opinion which is direct, comparative, or superlative. Each type is assigned to a specialist who is responsible for the summary.