Scholar research interest label mining and evolution analysis method and system and medium

Abstract

The invention discloses a scholar research interest label mining and evolution analysis method and system and a medium, and relates to the field of text mining and data mining. The main process involved in the invention comprises the following steps: collecting and storing academic achievement information of scholars; preprocessing academic achievement information; mining academic research keywords on each time slice in academic career of the scholar; establishing a research keyword co-occurrence graph on each time slice; identifying a research keyword community on each time slice; and extracting research interest labels on each time slice. On the basis, the evolution condition of the study interest of the scholar can be obtained according to the study interest label of the scholar in each time slice. According to the scholar research interest label mining and evolution analysis method provided by the invention, intelligent extraction of the scholar research interest label and intelligent analysis of the research interest evolution process in the scholar academic career can be realized on the premise of no prior information.

Description

technical field [0001] The invention relates to the fields of text mining and data mining, in particular to a method, system and medium for mining and evolution analysis of tags of scholar's research interest. Background technique [0002] In the context of a powerful country in science and technology, more and more scholars have devoted themselves to scientific research. In order to find the scholars they need, enterprises with intellectual support needs of scholars need to consider the research interests of scholars in order to find scholars with the most relevant knowledge in the research field. [0003] The research interests of scholars are often reflected in the academic achievements produced by scholars. Subject extraction of the textual content of academic achievements of scholars can largely obtain the research interests of scholars. Topic extraction of text content goes through three stages. The first stage is the text topic description stage based on keyword ex...

AI Technical Summary

Problems solved by technology

At present, most of the unsupervised scholar's research interest label extraction work, represented by the paper "Identification of Scholars' Main Research Interests Based on Three-word Co-occurrence Analysis and the Realization of Personalized Foreign Language Recommendation Service", focuses on the non-time-varying scholar's research interest label extraction. Ignoring the temporal dynamics of scholars' research interests over time

Images