Personalized Web Search Using Emotional Features

摘要: Re-ranking and re-retrieval of search results are useful techniques for satisfying users’ intentions, since current engines cannot always return user-desired pages at the top ranks. In this paper, we propose a system personalized Web considering emotional aspects. Given query topic, presents major emotion tendency on topic that returned from reflecting. The also enables users to specify polarities strengths their emotions (e.g., happy or sad, glad angry, peaceful strained) offers re-ranking list initial based similarity emotions. Particularly, can automatically obtain with minor by extracting sub-queries opposite conducting re-retrieval. Experimental evaluations show achieve encouraging in comparison results.