A study on clustering algorithm of Web search results based on rough set

With the development of the Internet, the Web has brought great convenience to people´s lives. But the explosive growth of information also makes it difficult for users to find exactly what they need at the same time. Although the search engines are the most popular Internet search tool for retrieving information from the Web, the users are still troubled by browsing the query results list carefully and excluding irrelevant results. Approach to Web search results clustering is an effective way to solve this problem. This paper adopts a generalized rough set (tolerance relation) to describe Web search results and uses LINGO algorithm to do clustering. The experimental results show that LINGO algorithm has a better performance than traditional K-Means clustering algorithm.