Personalizing online reviews for better customer decision making

Chen, Tao (2020) Personalizing online reviews for better customer decision making. Doctoral (PhD) thesis, Memorial University of Newfoundland.

[English] PDF - Accepted Version Available under License - The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission. Download (3MB)

Abstract

Online consumer reviews have become an important source of information for understanding markets and customer preferences. When making purchase decisions, customers increasingly rely on user-generated online reviews; some even consider the information in online reviews more credible and trustworthy than information provided by vendors. Many studies have revealed that online reviews influence demand and sales. Others have shown the possibility of identifying customer interest in product attributes. However, little work has been done to address customer and review diversity in the process of examining reviews. This research intends to answer the research question: how can we solve the problem of customer and review diversity in the context of online reviews to recommend useful reviews based on customer preferences and improve product recommendation? Our approach to the question is through personalization. Similar to other personalization research, we use an attribute-based model to represent products and customer preferences. Unlike existing personalization research that uses a set of pre-defined product attributes, we explore the possibility of a data-driven approach for identifying more comprehensive product attributes from online reviews to model products and customer preferences. Specifically, we introduce a new topic model for product attribute identification and sentiment analysis. By differentiating word co-occurrences at the sentence level from at the document level, the model better identifies interpretable topics. The use of an inference network with shared structure enables the model to predict product attribute ratings accurately. Based on this topic model, we develop attribute-based representations of products, reviews and customer preferences and use them to construct the personalization of online reviews. We examine personalization from the lens of consumer search theory and human information processing theory and test the hypotheses with an experiment. The personalization of online reviews can 1) recommend products matching customer's preferences; 2) improve custom's intention towards recommended products; 3) best distinguish recommended products from products that do not match customer's preferences; and 4) reduce decision effort.

Actions (login required)

View Item