mlsanityData to 7 Oct 2026

Flow Moods: Recommending Music by Moods on Deezer

arXiv 2207.11229 ↗First posted 15 Jul 2022cs.IR cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

The music streaming service Deezer extensively relies on its Flow algorithm, which generates personalized radio-style playlists of songs, to help users discover musical content. Nonetheless, despite promising results over the past years, Flow used to ignore the moods of users when providing recommendations. In this paper, we present Flow Moods, an improved version of Flow that addresses this limitation. Flow Moods leverages collaborative filtering, audio content analysis, and mood annotations from professional music curators to generate personalized mood-specific playlists at scale. We detail the motivations, the development, and the deployment of this system on Deezer. Since its release in 2021, Flow Moods has been recommending music by moods to millions of users every day.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 10 of its 22 references that are in the map. First posted on arXiv 15 Jul 2022.

Builds on

10 of 22 references.

References · 10

  1. 2017Billion-scale similarity search with GPUscited by 2,477
  2. 2019musicnn: Pre-trained convolutional neural networks for music audio taggingcited by 49
  3. 2017Current Challenges and Visions in Music Recommender Systems Researchcited by 42
  4. 2016Automatic tagging using deep convolutional neural networkscited by 39
  5. 2019Security and Privacy on Blockchaincited by 32
  6. 2020Carousel Personalization in Music Streaming Apps with Contextual Banditscited by 25
  7. 2021A Semi-Personalized System for User Cold Start Recommendation on Music Streaming Appscited by 21
  8. 2022Explainability in Music Recommender Systemscited by 15
  9. 2018Music Mood Detection Based On Audio And Lyrics With Deep Neural Netcited by 14
  10. 2021Cold Start Similar Artists Ranking with Gravity-Inspired Graph Autoencoderscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 2; 2025: 2; 2026: 1.

11 papers.

  1. 2023Attention Mixtures for Time-Aware Sequential Recommendationcited by 13
  2. 2023A Scalable Framework for Automatic Playlist Continuation on Music Streaming Servicescited by 7
  3. 2023A Human Subject Study of Named Entity Recognition (NER) in Conversational Music Recommendation Queriescited by 6
  4. 2023Track Mix Generation on Music Streaming Services using Transformerscited by 6
  5. 2024Let's Get It Started: Fostering the Discoverability of New Releases on Deezercited by 5
  6. 2025Exploring Large Action Sets with Hyperspherical Embeddings using von Mises-Fisher Samplingcited by 3
  7. 2023Fairness Through Domain Awareness: Mitigating Popularity Bias For Music Discoverycited by 2
  8. 2024Emotion-aware Personalized Music Recommendation with a Heterogeneity-aware Deep Bayesian Networkcited by 2
  9. 2023Search Engine and Recommendation System for the Music Industry built with JinaAIcited by 1
  10. 2026Music Playlist Captioning at Scale with Large Language Modelscited by 1
  11. 2025Twenty-Five Years of MIR Research: Achievements, Practices, Evaluations, and Future Challengescited by 0