A Semantic Analysis of the User-Generated Content from Social Network Sites of Cashbuild Limited: Application of Text Mining, Machine Learning and Big Data Analytics toward the Development of a Customer-Centric Marketing Strategy

Abstract

Social Network Sites (SNS) have grown rapidly over the past 15 years, which is in line with the growth of smartmobile phones. A key phenomenon of SNSs is User-Generated Content (UGC). It enables social engagements between users and their followers. UGC shares various perspectives on news, entertainment, and fun, as well as their perspectives on brands like Customer Experience (CX) and Customer Satisfaction (CS). UGC stimulates the Brand Attitudes (BA) of the readers if the user is trusted and credible. BAs influence the Purchase Intentions (PI) of the readers of UGC. Marketers like that UGC influences PI. They learn about CX and CS, which users share on the UGC. This semantic study uses Text Mining (TM) and Big Data Analysis (BDA) to extract keywords from the UGC of a building materials retail company, Cashbuild Limited (CBL) from the Republic of South Africa (RSA). The UGC was analysed using Power BI (PBI) to identify its sources and sentiments. The majority of the UGC in this study was obtained from Facebook (94.51%), followed by X.com (3.95%). The rest of the UGC was obtained from Blogs (0.79%) and Instagram (0.76%). 65.63% of the UGC was neutral, 29.74% positive, and 4.46% negative. UGC influences PI by mediating hedonic and utilitarian Brand Equity. The generation of a high-quality UGC was encouraged by CS - an outcome of CX. CX comes from the touchpoints across the CJ. Marketers want to ensure a good customer experience (CX) to achieve customer satisfaction (CS). Ultimately, CS influences future customer expectations (CE) when shared through UGC. 84 top keywords were extracted out of 16 328 hit sentences (HS) from the UGC of CBL using the MELTWATER program. The keywords were ranked to 51 frequency positions. CONCOR analysis was used to determine the connectivity and centrality of the keywords using Freeman’s coefficient and the Eigenvector value for each keyword. The results of the CONCOR analysis were used to identify 41 significant keywords based on their higher connectivity and centrality. The 41 significant keywords were matched with the 16 328 HSs. 14 keywords that matched less than 100 HSs were excluded. The remaining 27 keywords were subjected to exploratory factor analysis EFA on Statistical Program for Social Sciences (SPSS). 21 keywords were loaded on 8 factors, and the model explained 68.363% of the variance with a Kaizer Meyer Olkin (KMO) of 0.736 above 0.6. The 8 categories were compared to input from a panel of industry experts. 7 categories proposed by experts matched 7 out of 8 categories from the statistical model. 7 key themes proposed to be used in the study to develop Customer-centric Marketing Strategies (CCMS) in the building materials retail industry (BMRI) are DIY Kings, House Proud, Project Master, Renovators, Interior Image, Building Materials Inventory, and Promotions. All 5 objectives of the study were met. The study adds value to the development of CCMS learning from the UGC.