On relational learning and discovery in social networks: a survey
- PDF / 2,392,019 Bytes
- 18 Pages / 595.276 x 790.866 pts Page_size
- 2 Downloads / 208 Views
ORIGINAL ARTICLE
On relational learning and discovery in social networks: a survey Ji Zhang1 · Leonard Tan1 · Xiaohui Tao1 Received: 14 August 2017 / Accepted: 27 April 2018 © Springer-Verlag GmbH Germany, part of Springer Nature 2018
Abstract The social networking scene has evolved tremendously over the years. It has grown in relational complexities that extend a vast presence onto popular social media platforms on the internet. With the advance of sentimental computing and social complexity, relationships which were once thought to be simple have now become multi-dimensional and widespread in the online scene. This explosion in the online social scene has attracted much research attention. The main aims of this work revolve around the knowledge discovery and datamining processes of these feature-rich relations. In this paper, we provide a survey of relational learning and discovery through popular social analysis of different structure types which are integral to applications within the emerging field of sentimental and affective computing. It is hoped that this contribution will add to the clarity of how social networks are analyzed with the latest groundbreaking methods and provide certain directions for future improvements. Keywords Online social networks · Social internetworking scenarios · Homogeneous networks · Heterogeneous networks · Hybrid networks · Multi-dimensional relational learning
1 Introduction Networks today span wide areas of interest. These include, and are not limited to online social relationships, biological networks, marketing, politics, etc [1]. Information networks are formed from nodes with interconnecting links [1]. Complex schemas provide a realistic representation [e.g. Bespoke(star), multi-relation, bipartite, edge-node (multihub), etc] of how they have evolved over a temporal space [2–4]. Unique relationships between nodes are represented by high-dimensional, complex structures [1, 5]. Such complexities pre-define the co-existence of sub-structures commonly known as communities within these networks [1]. On a functional scale, these networks are capable of social and biological inferences by uncovering latent relational intelligence established between actors of a community. These * Ji Zhang [email protected] Leonard Tan [email protected] Xiaohui Tao [email protected] 1
Faculty of Health Engineering and Sciences, University of Southern Queensland, Darling Heights, QLD, Australia
inferences contain a rich source of detected emotions and feelings such as collaboration, prediction, reciprocities, status, etc. The multi-disciplinary applications of social networks have gained substantial recognition and scholarly interest over the past years in a vast variety of areas especially in the emerging field of sentimental and affective computing. Some of the more popular ones include link prediction, community detection, recommender systems, outlier and fraud detection, evolutionary processes, mood identification, depression detection, emotional disorder identification,
Data Loading...
