Diagnosing Bias in Recommender Systems

Welcome to the Diagnosing Bias in Recommender Systems repository! In this project, we experiment with detecting popularity bias in recommender systems using the frameworks Lenskit and Cornac, and testing the algorithms UserKNN and BMF. By following the steps below, you can set up the environment and run the provided Jupyter notebooks to conduct popularity bias analysis.

Table of Contents

• Getting Started
  • Prerequisites
  • Installation
• Usage

Getting Started

To get started with the Diagnosing Bias in Recommender Systems project, follow the instructions below.

Prerequisites

Make sure you have the following software installed:

• Python 3.8

Installation

1. Create and activate a conda virtual environment:

   conda create --name biasenv python=3.8
   conda activate biasenv

2. Clone the repository:

   git clone https://github.com/SavvinaDaniil/DiagnosingBiasRecSys.git
   cd DiagnosingBiasRecSys

3. Install the required Python packages:

   pip install -r requirements.txt

Usage

Once you have completed the installation steps, you can now run the bias analysis experiment using the provided Jupyter notebook.

1. Start the Jupyter notebook server:

   jupyter notebook

   Make sure that jupyter points to the jupyter installed from the requirements file. You may need to deactivate and activate the environment again.

2. Open the notebooks from the project directory. Each notebook performs a different process by calling the appropriate widget. You can select which algorithm and which dataset you wish to perform the process on.