Skip to content

Latest commit

 

History

History
32 lines (18 loc) · 1.61 KB

README.md

File metadata and controls

32 lines (18 loc) · 1.61 KB

Predict users product reviews sentiment


Semester project for the Machine Learning class of the MSc in Artificial Intelligence by NCSR Demokritos and University of Piraeus

The project evaluates the performance of different Machine Learning Classification algorithms over predicting the correct sentiment (Positive or Negative) of the given review in Greek language.

The Amazon Cell Phones Reviews reviews CSV file from Kaggle was the initial dataset. After preprocessing and artificially translating the data, more dataset files were created.

  • Used datasets can be found here. You can load them directly via the notebook as well.

Trained model is tested against actual product reviews taken from Skroutz

You can clone the project from repository using the following command:
git clone https://github.com/JoKoum/Machine-Learning-Project.git
You can create a new virtual environment and install the dependencies using the requirements.txt file:

On macOS and Linux:

python3 -m venv <env>

On Windows:

py - m venv <env>

Package installation using requirements.txt file:

pip install -r requirements.txt

Jupyter Notebook Viewer link