Mining Texts to Understand Customers' Image of Brands

Abstract

Text mining is becoming increasingly important in understanding customers and markets these days. This paper presents a method of mining texts about customer sentiments using a network analysis technique. A data set collected about two global mobile device manufactures were used for testing the method. The analysis results show that the method can be effectively used to extract key sentiments in the customers' texts.

Listen to Your Customers: Insights into Brand Image Using Online Consumer-Generated Product Reviews

“…Finally, the well-specified measures derived from network analysis ensure that different people eliciting the brand image communicated in online product reviews would obtain the same result, which is a critical criterion when measuring brand image [4]. Previous approaches to elicit brand association networks have not been able to utilize the rich information that is available in online product reviews (e.g., 3,32,35,66), and existing marketing studies that employ text mining methodologies do not take the network of brand associations into account (e.g., 14,57,67). Thus, we contribute to both the stream of research on brand image and the upcoming stream of research on text mining in marketing.…”

“…Consumers appear to have become more aware of the nutrition facts during this period, which makes intuitive sense because McDonald's also promotes this information in its advertising campaigns. 3 The normalized, weighted degree centrality of the two favorable brand associations, "healthy" and "fresh," does not change substantially (from 0.43 to 0.545 and 1.01 to 1.020, respectively). Thus, McDonald's image seems to have become slightly healthier in the after-event period than before the movie and marketing response.…”

“…Researchers then aggregate these individual networks to [71] This paper produce a consensus network [35,66,71]. Analytical mapping techniques also elicit brand associations from consumers using methods such as repertory grids, but then apply analytical methods, such as network analysis, to identify the links between these associations and how these associations relate to the brand [3,32,33]. Thus, the consumers do not provide information about the links explicitly.…”

“…However, data about the pre-event period may not always be available and cannot be collected afterward, especially when the study aims at assessing the effects of events outside the manager's control. 3. Brand association networks across consumers.…”

Social Media Sentimental Analysis in Exhibition’s Visitor Engagement Prediction

“…Ahn (2013) [6] used text mining on some customers' perception of brand images. Users share their experiences and sentiments about both an event and brands which as a result of a data analysis, provides an understanding of the market in real-time.…”