https://github.com/rlvtick/topic-modeling-shopee-reviews

Topic modeling on Shopee's 1-star reviews to uncover insights and prevalent topics within the reviews.
https://github.com/rlvtick/topic-modeling-shopee-reviews

bertopic lda natural-language-processing nmf-matrix-factorization topic-modeling

Last synced: 3 months ago
JSON representation

Topic modeling on Shopee's 1-star reviews to uncover insights and prevalent topics within the reviews.

• Host: GitHub
• URL: https://github.com/rlvtick/topic-modeling-shopee-reviews
• Owner: Rlvtick
• Created: 2023-12-16T05:51:20.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-12-28T16:55:02.000Z (over 1 year ago)
• Last Synced: 2025-01-06T07:48:54.246Z (5 months ago)
• Topics: bertopic, lda, natural-language-processing, nmf-matrix-factorization, topic-modeling
• Language: Jupyter Notebook
• Homepage:
• Size: 4.63 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        


  

  # Topic Modeling 1-Star Shopee Reviews




This repository showcases my contribution to a project focused on Topic Modeling for Shopee's Star Reviews in the Indonesian language. The main goal is to uncover insights into the prevalent topics within each star review. I specifically undertook the challenge of conducting topic modeling for the 1-Star Reviews. Moreover, the project seeks to evaluate and pinpoint the most effective algorithm for this task. The three algorithms employed in this project are **Latent Dirichlet Allocation (LDA)**, **Non-Negative Matrix Factorization (NMF)**, and **BERTopic**. The evaluation metrics utilized encompass **Topic Diversity** and **Coherence Score**.

# Flow of Analysis