作者: James Allan , Giridhar Kumaran
DOI:
关键词: User journey 、 User experience design 、 Computer user satisfaction 、 Computer science 、 Interactive systems engineering 、 Set (psychology) 、 Human–computer interaction 、 User interface 、 Interaction technique 、 User modeling
摘要: We present new ways of interacting with a user based on query analysis and reformulation. Our goal is to not only improve retrieval performance but also help the understand process collection she searching. do this by providing users information reflecting potential impact their decisions will have process. This way, can make more informed choices from options presented them system. Unlike most previous work in interaction where one-procedure-fits-all strategy was pursued, must be invoked when there for improvement. important as tedious an unfavorable experience. techniques selective show utility context two we developed. results that avoided vast number cases without much deterioration performance. User made productive optimally-sized set high quality options. efficient determine such set. When faced decision interact given particular query, it beneficial best technique suited query. solve problem obtaining implicit feedback user. By utilizing all interaction-related described thesis, through simulations studies obtain better less effort.