Using method of Latent Dirichlet Allocation (LDA) topic modeling to deliver business insight for Italian retail clothing company - Diesel S.p.A.
Original Dataset: Amazon Product Data from Prof. Julian McAuley at UC-San Diego(~80gb).
To remedy this, Prof. Vargo has picked to two smaller datasets that only contain
(1) meta-data about products that are in categorized as “Clothing, Shoes & Jewelry” and
(2) reviews about products that are in the “Clothing, Shoes & Jewelry” category.
Live Demo: https://silentsingerz.github.io/topicmodeling/
Code.py: Python project script.
alldieselreviews.json: All product reviews for Diesel on Amazon.
classified_reviews.jsonl: Classified reviews from SUPER REVIEWERS (Top 5%)
lda_topics.txt: Topic Model from LDA modeling
pyBestLDAvis.html: Interactive Visualization from PyLDAvis