Personalized recommendations for music genre exploration

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Citation (Scopus)
1 Downloads (Pure)

Abstract

Most recommender systems generate recommendations to match the user's current preference. However, users sometimes might have the goal to develop new preferences away from their current preference and use the recommender to guide them towards it. In this paper, we asked users to select a new genre to explore and studied what kind of recommendations would be more helpful for users to start exploring this new music taste. Three different recommendation methods are tested: one non-personalized which recommends the most representative tracks of the genre, one personalized method which considers songs from the new genre that best matches users' current preferences, and one mixed method which makes a trade-off between the two approaches. A comparative design was used in a user experiment in which participants were asked to evaluate the differences between the personalized method/mixed method and the non-personalized baseline. The mixed method results in recommendations that are more accurate and representative for the new genre than the personalized method. Users' perceived helpfulness for exploring the new genre is positively related to both perceived accuracy and perceived representativeness of the recommended items. Besides, recommendations from the mixed method are perceived more helpful for users high on Musical Sophistication Index for Active Engagement (MSAE). To our knowledge, this is one of the first studies using a recommender system to support users' preference development, and provides insights in how recommender systems can help users attain new goals and tastes.

Original languageEnglish
Title of host publicationACM UMAP 2019 - Proceedings of the 27th ACM Conference on User Modeling, Adaptation and Personalization
Place of PublicationNew York
PublisherAssociation for Computing Machinery, Inc
Pages276-284
Number of pages9
ISBN (Electronic)978-1-4503-6021-0
DOIs
Publication statusPublished - 7 Jun 2019
Event27th ACM Conference on User Modeling, Adaptation and Personalization, UMAP 2019 - Larnaca, Cyprus
Duration: 9 Jun 201912 Jun 2019

Conference

Conference27th ACM Conference on User Modeling, Adaptation and Personalization, UMAP 2019
CountryCyprus
CityLarnaca
Period9/06/1912/06/19

Fingerprint

Recommender systems
Experiments

Keywords

  • Content-based music recommendation
  • Exploration
  • Personalization
  • Preference developing
  • User goals
  • User-centric evaluation

Cite this

Liang, Y., & Willemsen, M. C. (2019). Personalized recommendations for music genre exploration. In ACM UMAP 2019 - Proceedings of the 27th ACM Conference on User Modeling, Adaptation and Personalization (pp. 276-284). New York: Association for Computing Machinery, Inc. https://doi.org/10.1145/3320435.3320455
Liang, Yu ; Willemsen, Martijn C. / Personalized recommendations for music genre exploration. ACM UMAP 2019 - Proceedings of the 27th ACM Conference on User Modeling, Adaptation and Personalization. New York : Association for Computing Machinery, Inc, 2019. pp. 276-284
@inproceedings{4ebb6687793c41de9cdb1bbb4404d7c2,
title = "Personalized recommendations for music genre exploration",
abstract = "Most recommender systems generate recommendations to match the user's current preference. However, users sometimes might have the goal to develop new preferences away from their current preference and use the recommender to guide them towards it. In this paper, we asked users to select a new genre to explore and studied what kind of recommendations would be more helpful for users to start exploring this new music taste. Three different recommendation methods are tested: one non-personalized which recommends the most representative tracks of the genre, one personalized method which considers songs from the new genre that best matches users' current preferences, and one mixed method which makes a trade-off between the two approaches. A comparative design was used in a user experiment in which participants were asked to evaluate the differences between the personalized method/mixed method and the non-personalized baseline. The mixed method results in recommendations that are more accurate and representative for the new genre than the personalized method. Users' perceived helpfulness for exploring the new genre is positively related to both perceived accuracy and perceived representativeness of the recommended items. Besides, recommendations from the mixed method are perceived more helpful for users high on Musical Sophistication Index for Active Engagement (MSAE). To our knowledge, this is one of the first studies using a recommender system to support users' preference development, and provides insights in how recommender systems can help users attain new goals and tastes.",
keywords = "Content-based music recommendation, Exploration, Personalization, Preference developing, User goals, User-centric evaluation",
author = "Yu Liang and Willemsen, {Martijn C.}",
year = "2019",
month = "6",
day = "7",
doi = "10.1145/3320435.3320455",
language = "English",
pages = "276--284",
booktitle = "ACM UMAP 2019 - Proceedings of the 27th ACM Conference on User Modeling, Adaptation and Personalization",
publisher = "Association for Computing Machinery, Inc",
address = "United States",

}

Liang, Y & Willemsen, MC 2019, Personalized recommendations for music genre exploration. in ACM UMAP 2019 - Proceedings of the 27th ACM Conference on User Modeling, Adaptation and Personalization. Association for Computing Machinery, Inc, New York, pp. 276-284, 27th ACM Conference on User Modeling, Adaptation and Personalization, UMAP 2019, Larnaca, Cyprus, 9/06/19. https://doi.org/10.1145/3320435.3320455

Personalized recommendations for music genre exploration. / Liang, Yu; Willemsen, Martijn C.

ACM UMAP 2019 - Proceedings of the 27th ACM Conference on User Modeling, Adaptation and Personalization. New York : Association for Computing Machinery, Inc, 2019. p. 276-284.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Personalized recommendations for music genre exploration

AU - Liang, Yu

AU - Willemsen, Martijn C.

PY - 2019/6/7

Y1 - 2019/6/7

N2 - Most recommender systems generate recommendations to match the user's current preference. However, users sometimes might have the goal to develop new preferences away from their current preference and use the recommender to guide them towards it. In this paper, we asked users to select a new genre to explore and studied what kind of recommendations would be more helpful for users to start exploring this new music taste. Three different recommendation methods are tested: one non-personalized which recommends the most representative tracks of the genre, one personalized method which considers songs from the new genre that best matches users' current preferences, and one mixed method which makes a trade-off between the two approaches. A comparative design was used in a user experiment in which participants were asked to evaluate the differences between the personalized method/mixed method and the non-personalized baseline. The mixed method results in recommendations that are more accurate and representative for the new genre than the personalized method. Users' perceived helpfulness for exploring the new genre is positively related to both perceived accuracy and perceived representativeness of the recommended items. Besides, recommendations from the mixed method are perceived more helpful for users high on Musical Sophistication Index for Active Engagement (MSAE). To our knowledge, this is one of the first studies using a recommender system to support users' preference development, and provides insights in how recommender systems can help users attain new goals and tastes.

AB - Most recommender systems generate recommendations to match the user's current preference. However, users sometimes might have the goal to develop new preferences away from their current preference and use the recommender to guide them towards it. In this paper, we asked users to select a new genre to explore and studied what kind of recommendations would be more helpful for users to start exploring this new music taste. Three different recommendation methods are tested: one non-personalized which recommends the most representative tracks of the genre, one personalized method which considers songs from the new genre that best matches users' current preferences, and one mixed method which makes a trade-off between the two approaches. A comparative design was used in a user experiment in which participants were asked to evaluate the differences between the personalized method/mixed method and the non-personalized baseline. The mixed method results in recommendations that are more accurate and representative for the new genre than the personalized method. Users' perceived helpfulness for exploring the new genre is positively related to both perceived accuracy and perceived representativeness of the recommended items. Besides, recommendations from the mixed method are perceived more helpful for users high on Musical Sophistication Index for Active Engagement (MSAE). To our knowledge, this is one of the first studies using a recommender system to support users' preference development, and provides insights in how recommender systems can help users attain new goals and tastes.

KW - Content-based music recommendation

KW - Exploration

KW - Personalization

KW - Preference developing

KW - User goals

KW - User-centric evaluation

UR - http://www.scopus.com/inward/record.url?scp=85068080900&partnerID=8YFLogxK

U2 - 10.1145/3320435.3320455

DO - 10.1145/3320435.3320455

M3 - Conference contribution

AN - SCOPUS:85068080900

SP - 276

EP - 284

BT - ACM UMAP 2019 - Proceedings of the 27th ACM Conference on User Modeling, Adaptation and Personalization

PB - Association for Computing Machinery, Inc

CY - New York

ER -

Liang Y, Willemsen MC. Personalized recommendations for music genre exploration. In ACM UMAP 2019 - Proceedings of the 27th ACM Conference on User Modeling, Adaptation and Personalization. New York: Association for Computing Machinery, Inc. 2019. p. 276-284 https://doi.org/10.1145/3320435.3320455