Abstract
We present a study on co-authorship network representation based on network embedding together with additional information on topic modeling of research papers and new edge embedding operator. We use the link prediction (LP) model for constructing a recommender system for searching collaborators with similar research interests. Extracting topics for each paper, we construct keywords co-occurrence network and use its embedding for further generalizing author attributes. Standard graph feature engineering and network embedding methods were combined for constructing co-author recommender system formulated as LP problem and prediction of future graph structure. We evaluate our survey on the dataset containing temporal information on National Research University Higher School of Economics over 25 years of research articles indexed in Russian Science Citation Index and Scopus. Our model of network representation shows better performance for stated binary classification tasks on several co-authorship networks.
Highlights
Nowadays, researchers struggle to find relevant scientific contributions among large variety of international conferences and journal articles
We focus on the link prediction (LP) problem (Liben-Nowell & Kleinberg, 2007) in order to predict links in temporal networks and restore missing edges in complex networks constructed over noisy data
We study a co-authorship recommender system based on co-authorship network where one or more of the coauthors belong to the National Research University Higher School of Economics (NRU HSE) and the co-authored publications are only those indexed in Scopus
Summary
Researchers struggle to find relevant scientific contributions among large variety of international conferences and journal articles. One of the solutions is to search for the most “important” articles taking into account citation or centrality metrics of the paper and the authors with high influence on specific research field (Liang, Li & Qian, 2011). Such method does not include collaborative patterns and previous history of research publications in co-authorship. It does not measure the author professional skills and the ability to publish research results according to paper influence metrics, for example, journal impact factor.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have