Essay 1: How Helpful Are Those Helpful Reviews? The Effect of Helpfulness Votes of Reviews on Product Essay 2: MicroSales level Linguistic Analysis of Marketing Text

  • Ziru Alex BAO (Speaker)

Activity: Talks or PresentationsOther Invited Talks or Presentations


[Essay 1: How Helpful Are Those Helpful Reviews? The Effect of Helpfulness Votes of Reviews on Product Sales]

Previous studies on review helpfulness focus on what makes a review helpful and how to predict review helpfulness. In so doing, researchers hope to identify the most helpful reviews for consumers and improve the recommendation system. However, little is known about the effect of these helpful reviews on product performance. Thus, this paper investigates how helpful reviews or the helpfulness votes influence product sales. Since product sales are only available at the group (product) level, estimating the effect of helpfulness votes presents a challenging multilevel problem. This research considers both the disaggregating (individual) and the aggregating (group) approaches and compares four competing models in their parameter estimates and model fitness. The results suggest that the average number of votes performs the worst while the mean-adjusted model slightly improves predictive power. Among them, the total number of helpfulness votes renders the best predictive performance.

[Essay 2: Micro-level Linguistic Analysis of Marketing Text]

As crowdfunding has become a popular source of funding for new ventures, budding entrepreneurs struggle to make a convincing pitch to raise backers’ interest. Existing studies find that linguistic styles such as narrative tone, use of informational or emotional appeals, concreteness, precision, and interactivity are signals of project quality. Yet missing from this body of research is the evidence of the effect of micro-level linguistic elements on crowdfunding success. We conduct two studies to investigate the effect of word-level and topic-level linguistic characteristics on crowdfunding outcome.

In Study One, we adopt a multimethod approach including N-gram natural language model, penalized logistic regression, and linguistic analysis to analyze the narratives of over 21,000 film projects released between 2015 and 2020 on Kickstarter. Consistent with the language expectancy theory, we find that “speaking the same language” and careful choice of words are key to crowdfunding success. We uncover the psychological meanings of words and phrases associated with crowdfunding success and failure and generate findings that provide valuable insight for entrepreneurs. In Study Two, we focus on topic mining of these marketing texts. We construct a measure of topic entropy to assess the topic complexity for each project pitch and examine how it affects crowdfunding success. We find that lower topic entropy enhances the probability project success. The product type (i.e., the movie genre) significantly moderates the effect of words and topics on project success. This study is among the first to apply advanced text analysis to investigate the effect of micro-level linguistic elements on message persuasiveness in marketing research and highlights the power of language in effective marketing communications.
Period16 Mar 2022
Event titlePostgraduate Seminar Series
Event typePublic Lecture