Feature-based service and product feedback analysis model via social media data mining

• Author / Creator

  Varudharajulu,Anish

• The growth of an organization in the market relies on customer’s satisfaction towards its products and services. Due to the dynamic nature of the internet, and increasing blogs, forums, and customer feedback, it usually remains a key issue in any industry to identify and extract data attributes manually. However, the effort required to collect the data and analyze it is cumbersome. To overcome these difficulties, organizations need to use big data processes to focus on customers by automating their information processing with good qualification to improve product quality, and customer satisfaction. Starting with discussions on the need for Concurrent and Collaborative Engineering (CCE) and the impact of Virtual Enterprise (VE) based product models on networked business and management, this research then describes a theoretical framework that creates a system linking the customers’ perspective of product features directly to the enterprise management. It has been shown that customer feedback information sharing across the organization can be achieved and useful using state-of-the-art data mining technologies. This framework demonstrates how data mining could enhance enterprise management through improved information sharing, efficient feedback utilization, and improved feature performance tracking along the lifecycle of the product and services, as well as the reduced lead time for improvement. The significant components of the proposed framework are social media data collection module, the data preprocessing module where data is filtered and formatted to an acceptable format, and the module of classifying and clustering where the data collected is visualized after being processed and analyzed using big data analytical tools to identify product features and their performances. Finally, the ability of the framework to discover customer satisfaction towards the key service and product features is demonstrated in a real-life case study. Observations and insights from this research could provide prototyping experience and case studies for academic, business ventures, and industry practitioners to implement the discussed big data techniques in related fields.

• Subjects / Keywords

  • Classification
  • Features
  • Data Mining
  • Clustering

• Graduation date

  Fall 2019

• Type of Item

  Thesis

• Degree

  Master of Science

• DOI

  https://doi.org/10.7939/r3-80av-f498

• License

  Permission is hereby granted to the University of Alberta Libraries to reproduce single copies of this thesis and to lend or sell such copies for private, scholarly or scientific research purposes only. Where the thesis is converted to, or otherwise made available in digital form, the University of Alberta will advise potential users of the thesis of these terms. The author reserves all other publication and other rights in association with the copyright in the thesis and, except as herein before provided, neither the thesis nor any substantial portion thereof may be printed or otherwise reproduced in any material form whatsoever without the author's prior written permission.