Special Issue on Social Network Analysis

1. Introduction

Social network analysis (SNA) is a research area of computer science with the purpose to represent people and their social interactions as graphs, and then, analyze these graphs using network and graph theory. SNA research is highly interdisciplinary: the best results have been obtained thanks to the collaboration with scientists from other disciplines, such as, for example, sociology, psychology, medicine, and management theory, among others. The objective of this Special Issue is to collect contributions centered on innovative algorithms in the field of computer science and network theory that are clearly linked to contributions from other disciplines.

Thus far, 15 papers have been published in this Special Issue out of a total of 37 submitted. The following sections provide a summary of each of the papers published.

2. Interaction Strength Analysis to Model Retweet Cascade Graphs

Zola et al. [1] introduce interaction strength, a novel metric used to model retweet cascade graphs by exploring users’ interactions. In their initial findings, the authors show the soundness of the approaches based on this new metric, with respect to the state-of-the-art model, and its ability to generate a denser graph, revealing crucial nodes that participated in the retweet propagation.

3. On Investigating Both Effectiveness and Efficiency of Embedding Methods in Task of Similarity Computation of Nodes in Graphs

Although embedding methods have been used for experimentation in a variety of applications, Reyhani Hamedani and Kim [2] presented a study on the effectiveness and efficiency of embedding methods in the task of graph node similarity. Results are discussed based on extensive experiments with five well-known and publicly available datasets.

4. Topology of the World Tourism Web

Kostelić and Turk [3] cope with the scarcity of investigations about social network analysis applications on world tourism networks. In their research, the authors examine the topology of a large tourism network (representing 1,448,285,894 travels) and discuss the meaning of its characteristics considering the current situation.

5. Framework for Social Media Analysis Based on Hashtag Research

In [4], Pilař et al. describe the Social Media Analysis based on Hashtag Research (SMAHR) framework, which uses social network analysis methods to explore social media communication through a network of hashtags. In their findings, the authors provide evidence of the fact that social media analysis based on hashtags provides information applicable to theoretical research and practical strategic marketing and management applications.

6. ALPINE: Active Link Prediction Using Network Embedding

Chen et al. [5] present ALPINE (Active Link Prediction usIng Network Embedding), a framework that identifies the most useful link status by estimating the improvement in link prediction accuracy to be gained by querying it. Results on real data show both the scalability and the boosted link prediction accuracy of the presented approach.

7. ADVO: A System to Manage Influencer Marketing Campaigns on Social Networks

Huynh et al. [6] propose ADVO, a management system for the influencer marketing campaign. Their system provides a tool for collecting data on a social network and detecting potential brand influencers for the marketing campaign. The system includes measures such as amplification factors for evaluating information propagation, the passion point to measure a user’s favorite brand, and the content creation score for determining the ability of post-content creating.

8. Geometric Deep Lean Learning: Evaluation Using a Twitter Social Network

Villalba-Diez et al. [7] describe and evaluate a deep learning algorithm that was designed to predict the topological evolution of dynamic complex non-Euclidean graphs in discrete time, in which links are labeled with communicative messages. The study includes a methodology to systematically mine the data generated on Twitter. Results show that the algorithm provides high accuracy in the link prediction of a retweet social network.

9. An Enterprise Social Analytics Dashboard to Support Competence Valorization and Diversity Management

Di Tommaso et al. [8] describe an Enterprise Social Analytics Dashboard to support human capital management, competence valorization, diversity management, and the early detection of potential problems within large, networked organizations. In their study, the authors show that Enterprise Social Networks are a favorable environment to highlight women’s leadership qualities and intermediary abilities.

10. An Approach to Exploring Non-Governmental Development Organizations Interest Groups on Facebook

In [9], Galiano-Coronil et al. present an approach for analyzing the stakeholders of various organizations based on their Facebook activity. The purpose of the research is to describe the management of marketing activities on Facebook; to identify the network stakeholders, their roles in communication, and community generating factors; and to position organizations according to their leadership, activity, and popularity in the network.

11. I Explain, You Collaborate, He Cheats: An Empirical Study with Social Network Analysis of Study Groups in a Computer Programming Subject

Barros et al. [10] propose a system to identify dishonest computer science students’ behaviors. This article aimed to quantitatively discern between different cases. The authors collected code similarity measures from students over four academic years and analyzed them using statistical and social network analyses. The study includes a discussion of different analyses, including knowledge flow analysis, social organization analysis, and the assessment of the relationship between successful students and social behavior.

12. FONDUE: A Framework for Node Disambiguation and Deduplication Using Network Embeddings

Mel et al. [11] present FONDUE, a framework for utilizing network embedding methods for data-driven disambiguation and deduplication of nodes. The authors provide an in-depth experimental setting including several social networks, such as a dataset of a Facebook Social Circles network, a collaboration network extracted from the PubMed database, and more. The discussion of the results includes promising further research directions.

13. An Information Diffusion Model Based on Explosion Shock Wave Theory on Online Social Networks

In [12], Zhang et al. propose the Information Diffusion Model based on the Explosion Shock Wave Theory. The Information Diffusion Model compares the propagation process to the explosion of an information bomb at the source, with the information shock waves progressively spreading from near to far. The authors additionally establish rules of information transmission between pairs of individuals.

14. A Novel Deep Neural Network-Based Approach to Measure Scholarly Research Dissemination Using Citations Network

Aljohani et al. [13] investigate scientific research dissemination by analyzing publications and citation data. Their model implements a convolutional neural network (CNN) with fastText-based pre-trained embedding vectors and utilizes only the citation context as its input to distinguish between important and non-important citations. The authors discuss a case study to measure the model comprehensiveness on a dataset of 3100 K citations taken from the ACL Anthology Reference Corpus.

15. Deep Link Entropy for Quantifying Edge Significance in Social Networks

Yurtcicek Ozaydin et al. [14] propose the Deep Link Entropy (DLE) method for a more precise quantification by considering the uncertainty distributions of adjacent nodes. They show experimentally that DLE significantly outperforms LE, especially in a large-scale complex network with several groups or communities. The authors believe that the proposed method contributes to a wide range of fields, from biology to quantum networks.

16. Leveraging Social Network Analysis for Crowdsourced Software Engineering Research

Alabduljabbar et al. [15] analyze publications on crowdsourced software engineering (CSE) using social network analysis (SNA). A total of 509 CSE publications from six popular databases were analyzed to determine the characteristics of the collaborative networks of co-authorship of the research (i.e., the co-authors, institutions involved in co-authorship, and countries involved in co-authorship) and of the citation networks on which the publications of the studies are listed. The findings help identify CSE research productivity, trends, performance, community structures, and relationships between various collaborative patterns to provide a more complete picture of CSE research.