The Semantic Brand Score (SBS) is a new measure of brand importance calculated on text data, combining methods of social network and semantic analysis. This metric is flexible as it can be used in different contexts and across products, markets and languages. It is applicable not only to brands, but also to multiple sets of words. The SBS, described together with its three dimensions of brand prevalence, diversity and connectivity, represents a contribution to the research on brand equity and on word co-occurrence networks. It can be used to support decision-making processes within companies; for example, it can be applied to forecast a company’s stock price or to assess brand importance with respect to competitors. On the one side, the SBS relates to familiar constructs of brand equity, on the other, it offers new perspectives for effective strategic management of brands in the era of big data.

Introduction

Nowadays text data is ubiquitous and often freely accessible from multiple sources: examples are the well-known social media platforms Facebook and Twitter, thematic forums such as TripAdvisor, traditional media such as major newspapers and survey data collected by researchers. Consumers express their feelings and opinions with respect to products in multiple ways, and their attitude towards brands can often be inferred from social media (Fan, Che, & Chen, 2017; Mostafa, 2013). Consumers’ interactions among themselves and with companies can influence prospective customers, firm performance and development of future products (e.g., Wang & Sengupta, 2016). The increase in availability of text data has raised the interest of many scholars who have been working towards the development of new automatized approaches to analyze large text corpora and extract meaning from them (Blei, 2012). At the same time, there has been significant interest in studying the value and importance of brands, considering both company and consumer-oriented definitions (Chatzipanagiotou, Veloutsou, & Christodoulides, 2016; de Oliveira, Silveira, & Luce, 2015; Keller, 2016; Pappu & Christodoulides, 2017; Wood, 2000). Customer-based brand equity was defined by Keller (1993, p. 1) as ‘the differential effect of brand knowledge on consumer response to the marketing of the brand’; the author also presented brand image and awareness as the two main dimensions of brand knowledge. These dimensions are in many cases assessed using surveys, case studies, interviews and/or focus groups (Aaker, 1996; Keller, 1993; Lassar, Mittal, & Sharma, 1995). Such approaches can be time-consuming for large samples and are sometimes biased, due to the fact that consumers often know to be observed and studied (making their expressions less natural and spontaneous). Another problem of past models is that brand equity dimensions are often many, heterogeneous and sometimes not easy to integrate in the final assessment. Among many factors affecting consumer-based brand equity, attention paid to consumers’ feedback has proved to play a major role (Battistoni, Fronzetti Colladon, & Mercorelli, 2013). Therefore, in the era of big data, it seems relevant to investigate the opinions of consumers and other stakeholders in their spontaneous expressions – while, for instance, discussing the characteristics of a product, or their user experience, without them having the perception of being monitored. Nowadays, social media and online reviews represent a common method of feedback. However, dealing with very large datasets usually requires rapid and automatized assessments that would be unfeasible when relying on traditional surveys. This work presents a new measure of brand importance – the Semantic Brand Score (SBS) – which overcomes some of these limitations, being automatable and relatively fast to compute even on big text data, without the need to administer surveys or to inform those who generate contents (such as social media users). The Semantic Brand Score (SBS) can be calculated for any set of text documents, either customer-based or related to the opinions and experience of other stakeholders of a company; it can be applied to different contexts: newspapers, social media platforms, consumers’ interviews, etc… Indeed, a good measure of brand importance should be sensitive to its variations and should be applicable across markets, products and brands (Aaker, 1996).