Segmental Analysis and Evaluation of User Focused Search Process

摘要: In general, IR systems assist searchers by predicting or assuming what could be useful for their information needs providing query suggestions pseudo-relevance feedback. Most of these approaches are based on analyzing objects (documents, queries) seen used in the past and then proposing other related that may relevant. Such often ignore underlying process seeking guides how a searcher performs during episode, thus forgoing opportunities making process-based recommendations. order to address this, we propose search analysis discovering different segments, which leads action features evaluating performance each stage. Further, recommendation strategy improve low performing user stage, shows proposed overall model yields effective improvements above 90% most cases. This lead better recommendations optimizations within segment enhance user.