In network analysis, the prediction of the connections or associations between entities or nodes within the network becomes important. Link Prediction is the problem of predicting or identifying the existence of a link between two entities in a network. However, it still the main issue in the complex network data application field, particularly in the type of analysis related to co-authorship networks despite its wide usage. Topological methods and content-based methods are the two different approaches that have been proposed for the link prediction in collaboration networks. However, topological methods are based on the structural analysis of the network, and content-based approaches rely on textual information from academic papers in the network. In this paper, we introduce the Content and Graph-Based Link Prediction (CGLP) approach, which integrates topological and content-based features from networks in a hybrid manner for predicting links in co-authorship networks. The efficacy of the proposed approach was already tested using three academic datasets: Hep-th, Hep-lat, and AMC by applying various machine learning models. Results indicated that all models showed almost the same efficiency on all three datasets and outperformed the state-of-the-art approach with a maximum F1 score of 98.05% and ROC AUC of 98.74%. ZANCO Journal of Pure and Applied Sciences KEYWORDS: Link Prediction; Co-authorship Networks; Social Network Analysis; Graph Mining; Text Mining TYPE Original article DOI http://dx.doi.org/10.21271/ZJPAS.

Besides social network analysis, the Link-Prediction (LP) problem has useful applications in information retrieval, bioinformatics, telecommunications, microbiology, and e-commerce as a forecast of future links in a given context to find what possible connections are based on a local and global statistical analysis of the given graph data. However, in Academic Social Networks (ASNs), the LP issue has recently attracted a lot of attention in academia and called for a variety of link prediction techniques to predict co-authorship among researchers and to examine the rich structural and associated data. As a result, this study investigates the problem of LP in ASNs to forecast the upcoming co-authorships among researchers. In a systematic approach, this review presents, analyses, and compares the primary taxonomies of topological-based, content-based, and hybrid-based approaches, which are used for computing similar scores for each pair of unconnected nodes. Then, this study ends with findings on challenges and open problems for the community to work on for further development of the LP problem of scholarly social networks.