Scholar clustering-oriented research interest mining method and device and storage medium

Abstract

The invention provides a scholar clustering-oriented research interest mining method and device and a storage medium. The method comprises the following steps of constructing an academic metadata set based on multi-source scholar related academic data; serving the academic metadata as input data to be input into a pre-established research interest mining model, sampling the topic model to obtain scholar interest semantic representation, wherein the scholar interest semantic representation comprises professional field-topic distribution, topic-English word distribution, topic-Chinese word distribution and topic-scholar distribution; performing scholar clustering based on the obtained scholar interest semantic representation to obtain a scholar clustering result; enabling the study interest mining model to share the same subject distribution for data of scholars from the same data source and belonging to the same professional field, and in the study interest mining model, the professional field-subject distribution is modeled as Dirichlet distribution; and modeling the subject-English word distribution, the subject-Chinese word distribution, and the subject-scholar distribution as polynomial distributions.

Description

technical field [0001] The invention relates to the field of big data technology, in particular to a research interest mining method, device and storage medium for scholars clustering. Background technique [0002] Academic data such as scholars, research projects, and papers all have their own areas of expertise. For example, some data belongs to software engineering and some data belongs to artificial intelligence. The research content of different professional fields is different, and the data of the same professional field often have a common theme distribution. For academic data of scholars, discovering research interests of scholars from academic data and clustering scholars according to their research interests are important for many tasks, such as selecting collaborators for scholars, reviewers for journals, and selection for governments expert. Different from general data, scholarly interest-related academic data has its unique properties. On the one hand, it is...

AI Technical Summary

Problems solved by technology

However, none of these dynamic representation models can track scholars' research interests from academic data

On the one hand, the publication time of papers and project application time are discontinuous, which is not suitable for online processing of academic data

On the other hand, existing batch methods are only suitable for single-source or monolingual data, and thus cannot be directly used to obtain dynamic semantic representations of scholars' research interests.

Images