Sourcing product innovation intelligence from online reviews

In recent years, online reviews have offered a rich new medium for consumers to express their opinions and feedback. Product designers frequently aim to consider consumer preferences in their work, but many firms are unsure of how best to harness this online feedback given that textual data is both unstructured and voluminous. In this study, we use text mining tools to propose a method for rapid prioritization of online reviews, differentiating the reviews pertaining to innovation opportunities that are most useful for firms. We draw from the innovation and entrepreneurship literature and provide an empirical basis for the widely accepted attribute mapping framework, which delineates between desirable product attributes that firms may want to capitalize upon and undesirable attributes that they may need to remedy. Based on a large sample of reviews in the countertop appliances industry, we demonstrate the performance of our technique, which offers statistically significant improvements relative to existing methods. We validate the usefulness of our technique by asking senior managers at a large manufacturing firm to rate a selection of online reviews, and we show that the selected attribute types are more useful than alternative reviews. Our results offer insight in how firms may use online reviews to harness vital consumer feedback.

Automated summary

In recent years, online reviews have become an important way for consumers to express their opinions and feedback. However, the unstructured and voluminous nature of textual data makes it challenging for companies to effectively utilize this feedback. This study proposes a method for prioritizing online reviews by using text mining tools, focusing on identifying the most useful reviews pertaining to innovation opportunities for firms. The results demonstrate the effectiveness of the proposed technique in improving upon existing methods, and senior managers at a large manufacturing firm also validate the usefulness of the selected attribute types in online reviews.