Artificial Neural Network Research in Online Social Networks

Artificial Neural Network Research in Online Social Networks

Steven Walczak
Copyright: © 2018 |Pages: 15
DOI: 10.4018/IJVCSN.2018100101
(Individual Articles)
No Current Special Offers


Artificial neural networks are a machine learning method ideal for solving classification and prediction problems using Big Data. Online social networks and virtual communities provide a plethora of data. Artificial neural networks have been used to determine the emotional meaning of virtual community posts, determine age and sex of users, classify types of messages, and make recommendations for additional content. This article reviews and examines the utilization of artificial neural networks in online social network and virtual community research. An artificial neural network to predict the maintenance of online social network “friends” is developed to demonstrate the applicability of artificial neural networks for virtual community research.
Article Preview


The origins of computer-based (online) social networking go back to the 1970’s when communities of users interested in a specific topic would gather on a Bulletin Board System (BBS) (Rafaeli, 1984), but these systems were limited by the ability to access computer systems at that time. Modern electronic social network sites began in 1997 and generated numerous specialized as well as general communities (boyd & Ellison, 2008). Social networking sites continued to gain in popularity and expanded rapidly in the early 21st century (Thelwall, 2009).

Online social networks have become the new norm for communication between individuals and also between individuals and organizations (Cheung et al., 2011; Culnan et al., 2010; Dijkmans et al., 2015; Loader et al., 2014). Gen Z and millennials prefer to perform research online and communicate through online social networks (Hampton & Keys, 2016; Riordan et al., 2018). Prior research has found that in 2011, 70% of teens used social media at least once per day and 25% of these did it at least 10 times daily (Ali & Senan, 2016). Not only do millennials prefer to perform research through online social networks, but they are more engaged as participants and more likely to respond to research survey requests when approached via Twitter (Guillory et al., 2016) or other online social networks.

It is estimated that over one third of the world’s population will be social network users, with a projected 2.62 billion users, by the end of 2018, and a growth rate of 6.5-7.9% annually (, 2018). Online social networking applications produce enormous quantities of data. Mayer-Schönberger and Cukier (2013) claim that Facebook, LinkedIn, Twitter, and other online social network applications have datafied our experiences as humans, including both personal and business information. As an example, Facebook generates over 3 billion pieces of data content every day (Chen & Zhang, 2014). These big data resources from online social networks provide a vast resource for performing research, which includes: academic, customer relationship management, marketing, medical, and political research, to name a few.

Machine learning provides a solution for performing research with big data (Landset et al., 2015; Wu et al., 2014), including data generated from online social networks. Artificial neural networks (ANNs) is a subfield of machine learning, sometimes referred to as soft computing methods that also includes genetic algorithms. ANNs are a popular solution method in numerous domains including: business (Tkáč & Verner, 2016; Wong et al., 2000), engineering (Ali et al., 2015; Bansal, 2006), and medicine (Reggia, 1993; Yardimci, 2009). Research and development with ANNs continues to be highly productive with the quantity of articles published in this subfield increasing annually (Walczak, 2017). ANNs are already being applied in online social network research.

Complete Article List

Search this Journal:
Open Access Articles: Forthcoming
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing