Loading...

Snappfood UGC Classification Using Machine Learning and Comparison of SVM and NB Methods

Honarvar, Mohsen | 2020

260 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 54392 (44)
  4. University: Sharif University of Technology
  5. Department: Management and Economics
  6. Advisor(s): Najmi, Manoochehr
  7. Abstract:
  8. One way for businesses to grow and compete, in any age (especially the digital age), is to create a Brand Relevance through creating or finding, and then owning new categories or subcategories. In this way, instead of beating competitors; they become irrelevant by enticing customers to buy a new category or subcategory for which other alternative brands are not considered relevant. Firms traditionally rely on interviews and focus groups to identify these subcategories and customer needs. Nowadays, with the growth of social media, user-generated content (UGC) is also a good alternative source. However, Due to the large size of UGC and the non-informative or repetitive data it contains, established methods for UGC analysis are neither efficient nor effective. Machine learning concepts are best for such data analysis. In this study, inspired by the proposed models, we propose a step-by-step machine learning based model to facilitate Persian UGC qualitative analysis and the process of identifying new categories or subcategories, by filtering out noninformative content and classifying informative ones. In this model, we focused on both technical and managerial aspects of UGC analysis with the help of machine learning concepts. Then, the model was executed on our case study. The performance of the machines used in the model to eliminate inefficient Persian texts and classify efficient ones was measured and then based on better performance and f1-score of 91 percent, the machine trained with the SVM method was chosen. Examining and dealing with the challenges of Persian content analysis, measuring the performance of the proposed model to identify subcategories and extracting the key success factors of online food ordering industry were other outputs of this study
  9. Keywords:
  10. Text Mining ; Machine Learning ; Text Classification ; Support Vector Machine (SVM) ; User Generated Content ; Naive Bayes

 Digital Object List

 Bookmark

No TOC