Tokopedia Review Scanner
A machine learning pipeline that reads Tokopedia app reviews and finds what users like and dislike.
- Status
- Finished and delivered. It does what it set out to do and no more work is planned.
- Kind
- Machine Learning
- Started
- Apr 2025

About it
The problem
An app like Tokopedia has thousands of Play Store reviews. Read one by one, they cannot tell a product team which problems are most common or what users value.
The approach
This is my submission for Dicoding's Machine Learning Intermediate course. A custom scraper pages through Google Play to collect up to 15,000 reviews, text is cleaned for Indonesian and English (case folding, tokenisation, stopwords, stemming with Sastrawi), the classes are balanced, and several feature extractors and models are compared.
- Pre-trained sentiment pipeline for the first labelling, with tqdm progress on large batches.
- Balanced positive, negative and neutral classes before training.
- A second project in the repository that trains and exports a model with TensorFlow.
The result
The pipeline turns raw reviews into sentiment scores and the themes behind them, so a team can see what to fix first.
What it does4
Review Scraper
Text Cleaning
Balanced Classes
Model Comparison
More work

Rone Arena API
A public FastAPI for Mobile Legends hero data, analytics and player tools, with a web playground and SDKs.

BeliMadu.com
An online honey shop on Next.js 16 and Cloudflare Workers, with a WhatsApp-checkout cart and a Vitest suite.

ridwaanhall.com
This site: a portfolio and blog on Next.js 16 with an admin, Markdown versions of every page and a CV generated from the About page.
Comments0
Signed-in readers can comment.