In a world where users constantly review products and services, both individuals and companies rely on various parameters to assess the quality of their offerings. One of the most commonly used evaluation methods is the star rating system. These stars serve as a key indicator of whether a product or service meets customer expectations.
However, even customers sometimes struggle to accurately assess how well a product met their needs, leading to inconsistencies in ratings—for example, assigning ⭐⭐⭐⭐⭐ when the experience was great or just ⭐ when it was terrible.
This project analyzes and predicts review ratings based on the Brazilian E-Commerce Public Dataset by Olist, which contains 100,000 orders with detailed information about products, customers, and reviews. By leveraging this dataset, the project explores classification algorithms to develop a system capable of predicting and suggesting appropriate star ratings based on the textual content of a user’s review.
Programming Language: Python
To use this project, follow these steps:
Clone the repository:
git clone https://github.com/AndersonIvanildo/star-classifier-predictor.git
Initialize Poetry:
poetry install
Run Streamlit:
streamlit run app.py
Enjoy!
This project is licensed under the MIT License.