COMING SOON! PQDT Open is getting a new home!

ProQuest Open Access Dissertations & Theses will remain freely available as part of a new and enhanced search experience at

Questions? Please refer to this FAQ.

Dissertation/Thesis Abstract

Identifying Product Defects by Applying a Predictive Model to Customer Reviews
by Fong, Titus Hei Yeung, D.Engr., The George Washington University, 2020, 146; 28087840
Abstract (Summary)

The challenge for consumer product engineering teams to manually explore their product’s defects from online customer reviews (OCR) delays product recall and recovery processes. In today's product life cycle, there is no practical method to automatically transfer the massive amount of valuable online customer reviews, such as design, performance, and serviceability feedback, to the product engineering teams. This lack of an early detection mechanism for problems often increases the risks of a product recall, potentially causing billions of dollars in economic loss, loss of company credibility, and loss of market penetration.

This research explores two different kinds of Recurrent Neural Network (RNN) models and one Latent Dirichlet Allocation (LDA) topic model to extract product defect information from OCRs. This research also proposes a novel approach, combined with RNN and LDA models, to provide engineers with an early view of product defects. The proposed approach first employs the RNN models for sentiment analysis on customer reviews to identify negative reviews and reviews that mention product defects, then applies the LDA model to retrieve a summary of key defect insight words from these reviews.

Results of this praxis show that engineering teams can discover early signs of potential defects and opportunities for improvement when using this novel approach on eight of the bestselling Amazon home furnishing products. This combined approach is able to locate the keywords of these products’ defects and issues that customers mentioned the most in their OCRs, which allows the engineering team to take required mitigation actions earlier and proactively stop the diffusion of the detective products.

Indexing (document details)
Advisor: Sarkani, Shahryar, Fossaceca, John
Commitee: Etemadi, Amir
School: The George Washington University
Department: Engineering Management
School Location: United States -- District of Columbia
Source: DAI-A 82/2(E), Dissertation Abstracts International
Subjects: Engineering, Computer science, Information science, Artificial intelligence
Keywords: Machine learning, Natural language processing, Neural network, Opinion mining, Product defect discovery, Topic model
Publication Number: 28087840
ISBN: 9798662589445
Copyright © 2021 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy