Social Networks Marketing and Consumer Purchase Behavior: The Combination of SEM and Unsupervised Machine Learning Approaches

Abstract

The purpose of this paper is to reveal how social network marketing (SNM) can affect consumers’ purchase behavior (CPB). We used the combination of structural equation modeling (SEM) and unsupervised machine learning approaches as an innovative method. The statistical population of the study concluded users who live in Hungary and use Facebook Marketplace. This research uses the convenience sampling approach to overcome bias. Out of 475 surveys distributed, a total of 466 respondents successfully filled out the entire survey with a response rate of 98.1%. The results showed that all dimensions of social network marketing, such as entertainment, customization, interaction, WoM and trend, had positively and significantly influenced consumer purchase behavior (CPB) in Facebook Marketplace. Furthermore, we used hierarchical clustering and K-means unsupervised algorithms to cluster consumers. The results show that respondents of this research can be clustered in nine different groups based on behavior regarding demographic attributes. It means that distinctive strategies can be used for different clusters. Meanwhile, marketing managers can provide different options, products and services for each group. This study is of high importance in that it has adopted and used plspm and Matrixpls packages in R to show the model predictive power. Meanwhile, we used unsupervised machine learning algorithms to cluster consumer behaviors.

Purchase Behavior of Energy-Efficient Appliances Contribute to Sustainable Energy Consumption in Developing Country: Moral Norms Extension of the Theory of Planned Behavior

“…We applied PLS-SEM (partial least square-SEM) for data analysis to measure the key constructs of the proposed model instead of covariance-based SEM (CB-SEM) approaches [83]. PLS-SEM could evaluate more complicated models, non-normal data, structural indicators, and facilitate theory building [84,85]. We applied SmartPLS 3.2.3 statistical software [86], which is very popular in the marketing and management field.…”

A New BAT and PageRank Algorithm for Propagation Probability in Social Networks

“…As mentioned in Section 2.1, many scholars have proved that social networks are scale-free networks. In a scale-free network, when a node has k connections, their degree distribution follows a power distribution [15], as in Equation (1).…”

“…Because the propagation state of each node is obtained by the BAT algorithm, propagation stops when all state vector coordinates are 1 during the exhaustive process so that the maximum propagation state of each node is the last state vector in the process of BAT algorithm. For example, the maximum state of node 0 is to propagate to node 1 and node 2 at the same time; that is, the binary state label is [1,1], and C(i) is used to present the total number of state combinations. Because it is a binary network model, C(i) = 2|Deg(i)|, and the value of k in the state label S k (i) is encoded from 1 so that k = 2|Deg(i)| − 1 for the maximum propagation state.…”

“…When l = 1, node 1 starts from state S 0 (1), S 0 (1) is a new empty set and does not satisfy |T * ∪ T l | ≥ 3, so probability R 1 cannot be added to probability R. Similarly, l = 2. When l = 3, node 1 reaches state S 2 (1); that is, it propagates to node 2. At this time, T * adds a new node 2, which satisfies | T * ∪T l | 3, so the probability R 3 is added to the probability R = Pr (s = 0, N page = 3).…”

“…With the commercial effect of viral marketing and word-of-mouth marketing, social networks are regarded as a medium for propagating information, ideas and influence between nodes [1][2][3][4]. The propagated influence of information propagation in social networks, which use the behavior of user information propagation in social networks to evaluate propagated influence and find the key nodes in order to achieve the greatest influence on social networks during the propagation of these nodes [1,5], is a hot research area [1,[5][6][7][8][9]. In other words, investors focus on the high connectivity and high propagation of social networks and accurately invest information in the source nodes of propagation rather than invest many resources in many nodes.…”