Contextualizing Spotify's Audiobook List Recommendations with Descriptive Shelves
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916696182226944 |
|---|---|
| author | Penha, Gustavo Wang, Alice Achenbach, Martin Sheets, Kristen Mantravadi, Sahitya Galvez, Remi Guetta-Jeanrenaud, Nico Narayanan, Divya Kalaydzhyan, Ofeliya Bouchard, Hugues |
| author_facet | Penha, Gustavo Wang, Alice Achenbach, Martin Sheets, Kristen Mantravadi, Sahitya Galvez, Remi Guetta-Jeanrenaud, Nico Narayanan, Divya Kalaydzhyan, Ofeliya Bouchard, Hugues |
| contents | In this paper, we propose a pipeline to generate contextualized list recommendations with descriptive shelves in the domain of audiobooks. By creating several shelves for topics the user has an affinity to, e.g. Uplifting Women's Fiction, we can help them explore their recommendations according to their interests and at the same time recommend a diverse set of items. To do so, we use Large Language Models (LLMs) to enrich each item's metadata based on a taxonomy created for this domain. Then we create diverse descriptive shelves for each user. A/B tests show improvements in user engagement and audiobook discovery metrics, demonstrating benefits for users and content creators. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_13572 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Contextualizing Spotify's Audiobook List Recommendations with Descriptive Shelves Penha, Gustavo Wang, Alice Achenbach, Martin Sheets, Kristen Mantravadi, Sahitya Galvez, Remi Guetta-Jeanrenaud, Nico Narayanan, Divya Kalaydzhyan, Ofeliya Bouchard, Hugues Information Retrieval In this paper, we propose a pipeline to generate contextualized list recommendations with descriptive shelves in the domain of audiobooks. By creating several shelves for topics the user has an affinity to, e.g. Uplifting Women's Fiction, we can help them explore their recommendations according to their interests and at the same time recommend a diverse set of items. To do so, we use Large Language Models (LLMs) to enrich each item's metadata based on a taxonomy created for this domain. Then we create diverse descriptive shelves for each user. A/B tests show improvements in user engagement and audiobook discovery metrics, demonstrating benefits for users and content creators. |
| title | Contextualizing Spotify's Audiobook List Recommendations with Descriptive Shelves |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2504.13572 |