Incorporating Quality Measurement into Scientific Document Retrieval –

 One of the challenges facing today's researchers is how to find qualitative information that meets their needs. In scientific research, the quality of information is very important for institution quality improvement and research validation. The main purpose of the paper is the proposal of a scientometric annotation approach to improve retrieval system performance and meet researchers’ needs. In this work, we discuss how to use scientometrics in document annotation to improve information quality. One possible solution to this problem is to automate and facilitate the selection of qualitative scientific documents by enriching the document annotation process with scientometric criterion. Our approach provided better performance for retrieval system compared to BM25 retrieval model. The best performance was supplied by the integration of document citation number and journal or conference ranking. The best improvement rate was 34.21% in F-measure, 52.22% in nDCG, 27.45% in MAP and 83.33% in P(k). An important implication of this finding is the existence of correlation between research paper quality and paper relevance.