Hebein Gunther Cyrill;
Most recommender systems work on data from one big single user session and rarely take into account different sessions for different goals.In real life,users split up their search into several sub-searchtasks for easier handling of their anomalous state of knowledge(ASK).This poster presents an idea of an easy algorithm which takes this observation into account and could help improving the quality of recommending unseen information objects(IO) and,as a consequence,shortening the time it takes to normalize an anomalous state of knowledge is normalized and to answer a topical question.This algorithm has not been fully implemented yet.
Information retrieval;;Recommender;;Relevance feedback;;Sub-searchtask
To explore the background and basis of the node document
Documents that have the similar content to the node document