Skip to content

isislab-unisa/Are-Quality-Dimensions-Correlated

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

32 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Are quality dimensions correlated? 🔎

This repository contains the code to reproduce the results presented in the publication Are quality dimensions correlated? An empirical investigation, accepted as research paper to ISWC 2025. From the following GitHub pages you can directly view the corrrelation matrices (as heatmaps) for each tool and summary tables for the 4 tools analyzed:

In the folder /data/inferential_statistics_results/, the correlation matrices are already available as CSV files. Meanwhile, in /data/charts/heatmap, heatmaps created from the CSV files are provided for a graphical visualization of the correlation matrices.

If, instead, you want to regenerate the matrices and graphs using ther provided quality data, refer to section How to reproduce the correlation matrices.

How to reproduce the correlation matrices 🔬

Download the quality data computed by KGHeartBeat here: https://doi.org/10.5281/zenodo.16419915. Move the CSVs file downloaded into /data/quality_analysis_results.

Run the code 🚀

Requirements

  • Python 3.13 or later.
  • pip installed on your system.
  • zip on linux to extract compressed files (on Windows, any software capable of decompressing a .zip file is suitable).

Linux and MacOS users

A shell script has been created to simplify and expedite the process of reproducing the results. Make sure to grant execution permission to the script.

chmod +x run_correlation_analysis.sh

Then, execute it

./run_correlation_analysis.sh

This script will create and activate a Python virtual environment, install the required dependencies using pip install, and extract the files containing the KGHeartBeattBeat quality data. At the end, the main.py file is executed, which calculates the correlation on the quality data from the four tools. The correlation matrices will be saved in /data/inferential_statistics_results/, while the heatmaps will be stored in /data/charts/heatmap

Windows users

  1. Create and activate a Python Virtual Environment (Optional but Recommended)
# Create a Python venv
python -m venv venv
# Activate it
.\venv\Scripts\activate
  1. Install the requirements
pip install -r requirements.txt
  1. Unzip the KGHeartBeat quality data with any software capable of decompressing a .zip file is suitable. The file to be decompressed are located in the folder data/quality_analysis_results

  2. Run the main.py file

python main.py