Identifying authoritative researchers in digital libraries using external a priori knowledge

Abstract

Numereous digital library projects mine heterogeneous data from different sources to provide expert finding services. However, a variety of models seek experts as simple sources of information and neglect authority signals. In this paper we address the issue of modelling the authority of researchers in academic networks. A model, RAC, is proposed that merges several graph representations and incorporate external knowledge about the authority of some major scientific conferences to improve the identification of authoritative researchers. Based on the provided structural model a biased label propagation algorithm aimed to strenghten the scores calculation of the labelled entities and their neighbors is developped. Both quantitative and qualitative analyses validate the effectiveness of the proposal. Indeed, RAC outperforms state-of-the-art models on a real-world graph containing more than 5 million nodes constructed using Microsoft Academic Search, AMiner and Core.edu databases.

An Explanatory Query-Based Framework for Exploring Academic Expertise

“…number of papers per year), textual similarity features, and features based on citation patterns. Others focused on algorithms using ranking [Brochier et al, 2020] or graph-based models including collaborators, papers, citations, conferences [de La Robertie et al, 2017;Ammar et al, 2018]. In this paper, we use textual data only (i.e.…”