gender-recs

https://github.com/andrebola/gender-recs

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
✓
DOI references
Found 2 DOI reference(s) in README
✓
Academic publication links
Links to: zenodo.org
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (6.8%) to scientific vocabulary

Last synced: 10 months ago · JSON representation ·

Repository

Basic Info

Host: GitHub
Owner: andrebola
Language: Python
Default Branch: master
Size: 26.4 KB

Statistics

Stars: 3
Watchers: 1
Forks: 2
Open Issues: 0
Releases: 0

Created over 5 years ago · Last pushed over 1 year ago

Metadata Files

Readme Citation

Description

This repository contains the code to reproduce the results of the paper entitled "Break the Loop: Gender Imbalance in Music Recommenders", by Andres Ferraro, Xavier Serra, and Christine Bauer.

Instructions

Step 1

Download the datasets and locate them in the folder ./data. The artist information should be also located in the same folder; it can be downloaded from here.

Install dependencies specified in requirements.txt

Step 2

Before starting to generate recommendations the data has to be processed and formatted:

python generate_mtrx.py : Generate matrix for artists using the LFM-1b dataset
python generate_mtrx_360k.py: Generate matrix for artists using LFM-360k dataset
python generate_mtrx_tracks.py: Genrate matrix with tracks using LFM-1b dataset

Step 3

To run the first experiment (generate artist recommendations) the following scprits must be executed:

python model_predict.py : Generate recommendations for artists using the LFM-1b dataset
python model_predict_360k.py: Generate artist recommendations using the LFM-360k dataset

To run the second experiment (generate track recommendations) the following script must be executed:

python model_predict_tracks.py: Genrate track recommendations using the LFM-1b dataset

Step 4

Finally, to run the last experiment (simulations) the following script must be executed:

python model_simualte_artist.py -l 0: Generate simulation with artist recommendations using LFM-1b dataset indicating the value of lambda

Cite

Andrés Ferraro, Xavier Serra, and Christine Bauer (2021). Break the Loop: Gender Imbalance in Music Recommenders. In Proceedings of the 2021 ACM SIGIR Conference on Human Information Interaction and Retrieval (CHIIR ’21), March 14–19, 2021, Canberra, ACT, Australia. ACM, New York, NY, USA. https://doi.org/10.1145/3406522.3446033

Owner

Name: Andres Ferraro
Login: andrebola
Kind: user
Location: Barcelona
Company: Pandora-SiriusXM

Website: http://andrebola.github.io
Repositories: 29
Profile: https://github.com/andrebola

Citation (CITATION.cff)

cff-version: 1.2.0
message: If you use this code, please cite both the article from preferred-citation and the code itself.
authors:
  - family-names: Ferraro
    given-names: Andres
    orcid: "https://orcid.org/0000-0003-1236-2503"
  - family-names: Serra
    given-names: Xavier
    orcid: "https://orcid.org/0000-0003-1395-2345"
  - family-names: Bauer
    given-names: Christine
    orcid: "https://orcid.org/0000-0001-5724-1137"
title: 'Code for: Break the loop: gender imbalance in music recommenders'
version: 1.0.0
date-released: '2021-01-04'
url: "https://github.com/andrebola/gender-recs"
preferred-citation:
  authors:
    - family-names: Ferraro
      given-names: Andres
      orcid: "https://orcid.org/0000-0003-1236-2503"
    - family-names: Serra
      given-names: Xavier
      orcid: "https://orcid.org/0000-0003-1395-2345"
    - family-names: Bauer
      given-names: Christine
      orcid: "https://orcid.org/0000-0001-5724-1137"
  title: 'Break the loop: gender imbalance in music recommenders'
  doi: 10.1145/3406522.3446033
  type: conference-paper
  start: 249
  end: 254
  year: '2021'
  collection-title: "6th ACM SIGIR Conference on Human Information Interaction and Retrieval"
  conference:
    name: "CHIIR ‘21"
  publisher:
    name: "ACM"
    address: "New York, NY, USA"

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science