Scholar name ambiguity elimination method of fusing academic influence.

Abstract

The invention discloses a scholar name ambiguity elimination method of fusing academic influence. The method comprises: constructing a social network by a disambiguation data sub-set and a source dataset according to coauthoring and citation relationships thereof, and calculating influence of each node in the disambiguation data sub-set according to the network relationships; respectively constructing three network relationships of scholars and scholars, scholars and literature and literature and literature inside the disambiguation data sub-set according to node relationships, and using a sorting-based loss function and combining node influence similarity to jointly learn similarity among scholar nodes in the multiple networks; and constructing a clustering function on the basis of the node similarity and the node influence, and thus realizing a better disambiguation effect. According to the method, the problem of information missing in academic data is overcome while personal privacy is protected, social-network features are fully utilized, the node influence and the node similarity are fused, and the scholar name disambiguation effect is effectively improved.

Description

technical field [0001] The invention relates to the technical field of entity disambiguation, in particular to a method for disambiguating names of scholars with academic influence. Background technique [0002] Nowadays, the vast majority of academic materials are stored in network databases in the form of electronic resources, and scientific research activities are increasingly dependent on the literature system, through which scholar information and research literature can be obtained. The ambiguity of scholars' names includes: (1) the same scholar's name is recorded in different forms in different documents; (2) different scholars have the same name in documents. Since there may be a large number of scholars with the same name, and there are abbreviations in scientific and technological literature, the literature server maintaining these data may wrongly aggregate the literature of multiple scholars, and the accuracy of the information will directly affect the effectiven...

AI Technical Summary

Problems solved by technology

The academic influence of scholars is a very distinguishing feature among scholars. However, the existing methods for disambiguating scholars’ names mostly start from the perspective of a single node of a scholar, according to the characteristics of a single node, and do not consider the scholar’s ​​identity from the perspective of the overall network. academic influence

Images