Information Types in Product Reviews

TL;DR

This paper introduces a typology of 24 information types in product reviews and uses a zero-shot classifier to analyze review content, revealing insights into review helpfulness, sentiment, and rhetorical structure.

Contribution

It presents a novel typology of review sentence types and applies a zero-shot classifier for large-scale analysis, enabling better understanding of review content and intent.

Findings

Typology predicts review helpfulness and sentiment.

Typology explains review decisions and intent.

Analysis of review rhetorical structure.

Abstract

Information in text is communicated in a way that supports a goal for its reader. Product reviews, for example, contain opinions, tips, product descriptions, and many other types of information that provide both direct insights, as well as unexpected signals for downstream applications. We devise a typology of 24 communicative goals in sentences from the product review domain, and employ a zero-shot multi-label classifier that facilitates large-scale analyses of review data. In our experiments, we find that the combination of classes in the typology forecasts helpfulness and sentiment of reviews, while supplying explanations for these decisions. In addition, our typology enables analysis of review intent, effectiveness and rhetorical structure. Characterizing the types of information in reviews unlocks many opportunities for more effective consumption of this genre.