Did you find this content helpful? Linking brand specific review contents to helpfulness of a product review.
(A2019-5969)

AUTHORS

Nadine Schröder, WU Wien

KEYWORDS

review content; review helpfulness; count models

ABSTRACT

For marketers it is important to know what their customers think about their products and services and whether or not these opinions are shared by many other (potential) customers. One readily available source of customer opinions about a product is online customer review data. We investigate how various topics of reviews affect the number of helpful votes of reviews for tablet computer brands. Topics are identified by a text mining approach and classified into different content categories. These topics serve as predictors for various types of count models. Based on model criteria we identify the optimal model for each brand. Some topics (e.g., about usage behavior like reading) have a positive impact on helpfulness for one brand but no effect for another brand. Marketers may benefit from knowing helpful topics by, e.g., adjusting their product description or even future product development. Reviews with helpful topics might also be displayed more prominently.