AOL4PS: A Large-Scale Data Set for Personalized Search

Personalized search is a promising way to improve the quality of Websearch, and it has attracted much attention from both academic industrial communities. Much current related research based on commercial engine data, which can not be released publicly for such reasons as privacy protection information security. This leads serious lack accessible public data sets in this field. The few available have become widely used academia because complexity processing process required study personalized methods. together with difficulties brought obstacles fair comparison evaluation models. In paper, we constructed large-scale set AOL4PS evaluate methods, collected processed AOL query logs. We present complete detailed construction process. Specifically, address challenges time storage space demands by massive volumes, optimized proposed an improved BM25 algorithm. Experiments are performed some classic state-of-the-art experiment results demonstrate that measure effect