A literature recommendation method based on the number of citations

Abstract

The invention discloses a literature recommendation method based on citation times, which comprises the following steps: firstly, selecting a literature group range in a literature database; secondly,constructing a citation network model according to the mutual citation relationship among the literatures in the selected literature group, and counting the gold citation times of the literatures; secondly, clustering and grouping the literatures based on the reference network model; and finally, recommending the literature to the user according to the gold citation frequency and the literature clustering grouping sorting. The gold citation times of literatures are defined, self-citation interference in the literature citation relationship is eliminated, the influence of low-quality and low-efficiency citation is weakened, and literature clustering division is performed on the research field based on the literature citation network, a user can quickly and accurately lock high-quality literatures in the specific research field.

Description

technical field [0001] The invention belongs to the technical field of document retrieval, and in particular relates to a document recommendation method based on the number of citations. Background technique [0002] The citation relationship of documents reflects the intrinsic and essential connection between documents. The mutual citation between documents directly reflects the inheritance and internal connection between two independent research individuals, and the common citation record of a certain document to multiple documents also implies the correlation between multiple documents. Making full use of the characteristic information of citation relationship between documents can improve the validity and reliability of document clustering calculation. In the contemporary era of rapid growth in the number of academic documents, tens of thousands of academic achievements are published every day. Through document clustering, similar documents can be gathered together and ...

AI Technical Summary

Problems solved by technology

However, this method constructs the word vector space and semantic dictionary of a specific professional literature database with huge data and cumbersome calculations.

Secondly, in this method, the use of isolated words without complete semantics to calculate the similarity between documents will cause distortion errors because the matching factor is "too large" or "too small". Computing in emerging disciplines will inevitably lead to biased results

Images