Use of Sentiment Analysis in Marketing : The Factors Enabling or Preventing Adoption by Organizations
Abstract
The purpose of this study is to identify the factors that most directly influence a firm's decision of whether to include the practice of sentiment analysis in their practices. Sentiment analysis, a relatively new data analysis technique, is a natural language processing task that uses an algorithm to identify opinionated content within text-based data and categorize it into positive, negative, or neutral in polarity in order to identify people's attitudes, thoughts, judgments, and emotions on a specific subject. The essential connection that makes this relevant for business operations is that sentiment analysis can help generate meaningful insights into consumer perceptions of one's brand, products, or any other significant aspects that are discussed online from publicly available consumer-generated content (social media, consumer reviews, company blogs, customer support interactions). To explore this end, 8 professionals in the marketing industry were interviewed within a semi-structured format. Questions focused on their experience/perceptions of consumer sentiment and their perceptions of key performance metrics in general. It was found that most the subjects' interest in consumer sentiment measurement came from its ability to both act as a proof of performance and as a way of measuring overall brand health. However, there exists a significant amount of concern regarding the accuracy of automated algorithms in measuring sentiment and the correlation between UGC and the actual thoughts and perceptions of consumers.