This paper proposes a blogger reputation evaluation model based on opinion analysis for blogosphere (namedTOAM). This model not only calculates the semantic opinion of blog comment text, but also takes the reputation of blogger into evaluation and retrieves the topic opinion attitudes of internet users with different reputation. Oriented to the different length of blog comment, TOAM adopts two calculation methods for long text and short text respectively. For long comment text, the model evaluates the opinion weight of each character and the distribution density of opinion characters in target text. Through constructing the text opinion case knowledge base for long text, the model reuses the evaluation result of historical case and improves the execution efficiency effectively. For short comment text, the text opinion is calculated by summing the opinion weight of each character. On the other hand, the model analyzes the amount of topics, reviews, comments and the semantic opinion of each comment, and evaluates the reputation of each blogger in virtual network society. Finally, with the help of web ontology language (OWL), TOAM further abstracts the blog topic opinion relations and realizes the public opinion classification retrieval of different reputation levels people by SPARQL Protocol And RDF Query Language (SPARQL). To validate the performance, the experiments on the data corpus about “Network Culture” demonstrate that the model has higher precision of text opinion analysis and practicality of public opinion retrieval.
Mendeley saves you time finding and organizing research
Choose a citation style from the tabs below