Multi-view Navigation in a Personalized Scientometric Retrieval System

Given the large number of scientific productions, it becomes difficult to select those that meet the needs of researchers in scientific information and from certain sources of trust. One of the challenges facing researchers is finding quality scientific information that meets their research needs. In order to guarantee a quality result, a research method based on scientific quality is required. The quality of scientific information is measured by scientometrics based on a set of metrics and measures called scientometric indicators. In this paper we propose a new personalized information retrieval approach taking into account the researcher quality requirements. The proposed approach includes a scientometric document annotator, a scientometric user model, a scientometric ranking approach and different results visualization methods. We discuss the feasibility of this approach by performing different experimentations on its different parts. The incorporation of scientometric indicators into the different parts of our approach has significantly improved retrieval performance which is rated for 41.66% in terms of F-measure. An important implication of this finding is the existence of correlation between research paper quality and paper relevance. The revelation of this correlation implies better retrieval performance.