Loading...
Search
Search in this resource
sort by

A Framework for Redesign of Product Development Processes using Social Networks Based on Machine Learning Techniques

Ekhlasi, Ali | 2022

275 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 56772 (01)
  4. University: Sharif University of Technology
  5. Department: Industrial Engineering
  6. Advisor(s): Houshmand, Mahmoud; Fatahi Valilai, Omid
  7. Abstract:
  8. Today, developing existing products or introducing new services faces many challenges, as manufacturers/developers invest considerable time and money but often fail. One solution to overcome this problem is to use feedback from users across social networks. This method is more efficient than traditional methods and involves a larger user base, usually with a higher level of literacy. However, it poses certain challenges:
    - The volume of information in social networks surpasses traditional methods.
    - It is difficult to extract real emotions and concepts (especially when multiple emotions are intertwined) from user comments.
    In general, two basic questions are raised in this field:
    - How to turn User Generated Content (UGC) into interpretable concepts applicable to product engineering units?
    - How can user feedback be used to determine redesign priorities for products?
    The solutions provided in this field are divided into three main stages: pre-processing, post-processing and simultaneous processing. This includes evaluating user opinions or expectations before product release and evaluating user satisfaction after deployment. Evaluation methods include extracting keywords from platforms such as YouTube, Facebook, and Instagram, analyzing the correlation of keywords in sentences, extracting emojis from comments, and using predefined hashtags with weighted importance. This thesis begins with a comprehensive literature review of social network data analysis and its applications in product redesign. Based on the data analysis capabilities of unstructured social networks, a framework for determining redesign priorities will be presented. This framework enables the identification of priorities for the next generation of product design in the design department. One of the achievements of this framework is especially reducing the time needed to determine redesign priorities based on extensive social network data. The purpose of this study is to investigate the capabilities of the proposed framework in reducing the cost and time of product redesign evaluations.
  9. Keywords:
  10. Natural Language Processing ; Social Networks ; New Product Development ; Machine Learning ; Product Redesign ; Data Analysis

 Digital Object List

 Bookmark

No TOC