Ridderprint

Chapter 2 36 2014b). The normalized network data of the included papers was loaded into Gephi (Bastian et al., 2009), and visualized with a forced-directed layout (Hu, 2005). 2.5.1 Results The 211 primary documents in the bibliographic coupling network formed eight clusters. Table 2.4 provides an overview of the clusters and the most important articles (by weighted degree) per cluster. Based on the full text of their most important articles, we named the clusters (1) Risk and Customer Predictions, (2) Strategic BDA, (3) Information and Knowledge Management, (4) Text and Genetic Algorithms, (5) CSR, (6) Clustering, (7) Sports Analytics, (8) BCI. Three large clusters arose in the network. The largest cluster (N = 74) includes several papers predicting the financial risk of credit applicants (Abellán & Castellano, 2017; Florez-Lopez & Ramon-Jeronimo, 2015; Twala, 2010; Wang et al., 2011), the likelihood of customers leaving or staying (i.e., customer churn; Ballings & Poel, 2012; Moeyersoms & Martens, 2015; Morales & Wang, 2010), and more niche prediction topics, such as social media usage (Ballings & Van den Poel, 2015). Papers in the second cluster (N = 56) examined what organizational characteristics affect firm performance in the era of BDA (Akter et al., 2016; Ji-fan Ren et al., 2017; Wamba et al., 2017) and how BDA improved decision-making and value creation in organizations (Cao, Duan, & Li, 2015; Chae, Olson, & Sheu, 2014; Chae, Yang, Olson, & Sheu, 2014; Chen, Preston, & Swink, 2015; Coltman, Devinney, & Midgley, 2011). A closely connected third cluster (N = 40) focused on how knowledge and information can be strategically developed, managed and leveraged in organizations (e.g., Erickson & Rothberg, 2013), and the role of BDA therein (Rothberg & Erickson, 2017; Tsui et al., 2014; Wang et al., 2013). Five smaller clusters were also identified. Cluster four (N = 19) examined how text analytics and sentiment analysis of social media data can, for instance, predict stock markets (Kim & Kim, 2014; Nguyen, Shirai, & Velcin, 2015; Van de Kauter, Breesch, & Hoste, 2015), criminal activities (Gerber, 2014), or optimal product design and marketing strategies (Lau, Li, & Liao, 2014). Other papers in this fourth cluster explore genetic algorithms in relation to stock markets predictions (Esfahanipour & Mousavi, 2011) and production line optimization (Balakrishnan, Gupta, & Jacob, 2006). Cluster five (N = 10) examined corporate social responsibility research that used the ratings of Kinder, Lyndenberg, Domini Research and Analytics (e.g., Lucas & Noordewier, 2016; Nandy & Lodh, 2012). Cluster six (N = 6) examined how clusters can be identified and ranked in order to improve recommendation engines and other business processes (e.g., Chen, Cheng, & Hsu, 2013; Song, Yang, Siadat, & Pechenizkiy, 2013). Studies in cluster seven used BDA in sports to analyse the evolution of gameplay in Australian football (Woods, Robertson, & Collier, 2017), the relationship between practice and injury in American football (Wilkerson et al., 2016), and the possession value (Kempton, Kennedy, & Coutts, 2016) and match demands in rugby football (Hogarth, Burkett, & McKean, 2016). Finally, the two studies in cluster eight used machine learning to predict the performance of brain-computer interfaces (Halder et al., 2013; Hammer et al., 2014).