Analyzing and Classifying User Search Histories for Web Search Engine Optimization

The job of finding relevant information related to a specific topic is difficult in web due to the enormity of internet data. This scenario makes search engine optimization techniques into an indispensable method in the eyes of researchers, academicians, and industrialists. Search history analysis is the detailed examination of web data from different users for the purpose of understanding and optimizing web handling. Query log or user search history includes users´ previously submitted queries and their corresponding clicked documents or sites´ URLs. Thus query log analysis is considered as the most used method for enhancing the users´ search experience. The proposed method analyzes and classifies user search histories for the purpose of search engine optimization. In this approach, the problem of organizing users´ historical queries into groups in a dynamic and automated fashion is studied. The automatically classified query groups will help in different search engine optimization techniques like query suggestion, search result re-ranking, query alterations etc. The proposed method considers a query group as a collection of queries together with the corresponding set of clicked URLs that are related to each other around a general information need. This method proposes a new method of combining word similarity measures along with document similarity measures to form a combined similarity measure. In the proposed method other query relevance measures such as query reformulation and clicked URL concept are also considered. Evaluation results show how the proposed method outperforms existing methods.