The Characteristic of Chinese Search Based on Sogou Log

Abstract

To characterize Chinese search, this paper investigates a one-month user log from Sogou, a famous Chinese search engine. The query log analysis we perform falls into two categories: analysis of the query composition, and analysis of the query structure. Statistical results reveal that, in addition to Chinese character, users are accustomed to using the full-width and half-width characters and Japanese occasionally in the query. From the view of query structure, the simple query amounts to 81.6% of the total number, while complex queries accounts for 18.4%. Finally the differences between the Chinese search engine and the English one in the query formulation are discussed. The findings of this paper are beneficial to the study of information retrieval modeling, as well as the future log analysis of search engine.