Metaphor-Enabled Marketplace Sentiment Analysis

Textual data require an analytical trade-off between breadth and depth. Automated approaches locate patterns across large swaths of data points but sacrifice qualitative insight because they are not well equipped to deal with context-determined ways to express meaning, like figurative language. To strengthen the power of automated text analysis, researchers seek hybrid methodologies that combine computer-augmented analysis with sociocultural researcher insights based on qualitative textual interpretation. This article demonstrates a new method, which the authors term metaphor-enabled marketplace sentiment analysis (MEMSA). Building on existing automated text analysis methodologies linking word lists to sentiments, MEMSA adds metaphors that associate topics with sentiments across domains. Using MEMSA, researchers can leverage the sentiment potential of these located metaphors and scale insights to the level of big textual data by employing a dictionary approach enhanced by a specific and useful linguistic property of metaphors: their predictable structure in text (something is something else). This article shows that metaphors add associative detail to sentiments, revealing the targets and sources of sentiments that underlie the associations. Understanding nuanced market sentiments enables marketers to identify sentiment-based trends embedded in market discourse, so they can better formulate, target, position, and communicate value propositions for products and services.

• 저널Journal of Marketing Research · 61(3) · 496–516
• 토픽Sentiment Analysis and Opinion Mining · Artificial Intelligence
• DOI10.1177/00222437231191526
• 저자Ignacio Luri, Hope Jensen Schau, Bikram Ghosh