Product Feature Driven Personalization of Online Consumer Reviews
Loading...
Links to Files
Permanent Link
Author/Creator
Author/Creator ORCID
Date
2018-01-01
Type of Work
Department
Information Systems
Program
Information Systems
Citation of Original Publication
Rights
Distribution Rights granted to UMBC by the author.
Access limited to the UMBC community. Item may possibly be obtained via Interlibrary Loan thorugh a local library, pending author/copyright holder's permission.
This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
Access limited to the UMBC community. Item may possibly be obtained via Interlibrary Loan thorugh a local library, pending author/copyright holder's permission.
This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
Abstract
Many consumers rely on online product reviews for learning other consumers' opinions in favor of or against purchasing a product. With many people writing product reviews, there is an overwhelming number of reviews available online for a consumer to go through, causing navigation of those reviews tedious and ineffective. More importantly, despite that consumers have different information preferences for certain products of their interest, the existing online review platforms do not provide a personalized presentation of product reviews based on consumers' product feature preferences. There is a lack of theoretical frameworks for building personalized review rankings that can help consumers locate relevant and helpful reviews efficiently. Also, there is little empirical evidence available to demonstrate the effectiveness of personalizing review ranking systems. To address these issues, this research proposes, implements, and evaluates a product-feature driven framework to personalize the presentation of online product reviews. The proposed product feature driven personalization of online product reviews (FDPPR) framework presents product reviews based on a consumer's product feature preferences. The research involves characterizing a large number of product reviews using natural language processing techniques. A latent class regression (LCR) model is then developed to present a unique personalized order of reviews to a prospective consumer based on his/her product feature preferences. In addition, an online user study is conducted to evaluate the performance of the proposed framework. The results show that the participants find the reviews clustered and presented by FDPPR to be relevant and satisfactory and provide better knowledge about a product than the baseline online review platform. The major contributions of this research are (1) predicting helpfulness of product reviews based on individual product features, (2) reducing information overload for prospective consumers by providing personalized review ranking, and (3) developing a user evaluation methodology to measure the effectiveness of the personalization framework. The practical implications of the research include (1) helping retailers present the most relevant reviews to the consumers first, (2) assisting consumers to quickly get the essence of a lot of reviews based on their product feature preferences, and (3) helping manufacturers of the products understand consumers' expressed needs.