NLP-Course-Project - Review Analysis and Topic-Modeling with LDA (Latent Dirichlet Allocation)

Review Analysis (Mobile Lenovo K8) Topic modelling - Ransom Kumar

Note: This is an academic project completed by me as part of my PG Data Science programme

DESCRIPTION

Help a leading mobile brand understand the voice of the customer by analyzing the reviews of their product on Amazon and the topics that customers are talking about. You will perform topic modeling on specific parts of speech. You’ll finally interpret the emerging topics.

Problem Statement:

A popular mobile phone brand, Lenovo has launched their budget smartphone in the Indian market. The client wants to understand the VOC (voice of the customer) on the product. This will be useful to not just evaluate the current product, but to also get some direction for developing the product pipeline. The client is particularly interested in the different aspects that customers care about. Product reviews by customers on a leading e-commerce site should provide a good view.

Domain: Amazon reviews for a leading phone brand

Analysis to be done: POS tagging, topic modeling using LDA, and topic interpretation

Columns:

Sentiment: The sentiment against the review (4,5 star reviews are positive, 1,2 are negative)

Reviews: The main text of the review

Steps to perform:

Discover the topics in the reviews and present it to business in a consumable format. Employ techniques in syntactic processing and topic modeling.

Perform specific cleanup, POS tagging, and restricting to relevant POS tags, then, perform topic modeling using LDA. Finally, give business-friendly names to the topics and make a table for business.