Fine-grained culture-aware music recommender systems
Fine-grained culture-aware music recommender systems
Disciplines
Other Humanities (15%); Computer Sciences (60%); Sociology (25%)
Keywords
-
Music Recommender Systems,
Cultural Aspects,
Personalization,
Context Awareness
Having tens of millions of musical works available at a listeners fingertips requires novel recommendation and interaction techniques for music consumption. Thereby the success of a music recommender system, a system that proposes users what to explore or listen to next, depends on its ability to propose the right music, to the right user, at the right moment (i.e., in the right context). However, this task is extremely complex, as various factors influence a users music preferences. Amongst others, cultural aspects and characteristics (e.g., different requirements regarding diversity of a playlist or familiarity with its music tracks) have been shown to affect music perception, preferences, and listening behavior. Calling on this, the project entitled Fine-grained culture-aware music recommender systems investigates how music recommender systems could and should integrate cultural aspects in order to provide better recommendations. The research findings will answer the question how music recommender systems have to be designed to reflect cultural diversity and will provide insights into cross-cultural music perception, preferences, and listening behavior. Specifically, the project will investigate the cultural requirements on music recommender systems as concerns what listeners in different cultures expect with regard to the recommended music. Thereby, we postulate that different granularity levels of culture (e.g., individual, regional, national, or global level) have to be considered to improve music recommender systems. We hypothesize that the various cultural levels of different granularities have to be combined in a comprehensive way to transcend limitations of current music recommender systems. And we will investigate its impact on recommendation quality in cross-cultural studies with users from Austria, the United States, and Korea. Our scientific approach comprises four methodological orientations: (i) a combination of surveys and user panels, (ii) user modeling, (iii) designing and implementing prototypes of culture-aware music recommender systems, and (iv) cross-cultural studies with users to investigate their performance. The samples will include users from the United States, Austria, and Korea; we will focus on national culture, but also consider regional cultures (e.g., urban vs. suburban vs. countryside areas). In contrast to past research in the field of culture-aware music information retrieval and recommendation, the project follows an approach that is driven by user needs and preferences. The project aims to design and implement music recommender systems that are able to meet those requirements by considering different granularity levels of cultural aspects in a comprehensive way.
The project "Fine-grained culture-aware music recommendation system" investigated how music recommendation systems could leverage cultural. The project analyzed culture- specific differences in music preferences, for which we relied on data on listening behavior on music platforms. These findings have been incorporated into algorithmic music recommendation approaches, whereby we have shown that the inclusion of culture-specific differences leads to lower error rates in the recommendations thus, delivering better results. The projects main findings are summarized below: 1. A users music preferences can be described in terms of the degree to which they prefer music items that are currently popular (the mainstream) or rather ignore such trends; termed a users mainstreaminess. Here, mainstream may be defined globally, but also on a country-specific level; thereby, the country-specific mainstream does not necessarily correspond to the global mainstream. 2. With regard to artist popularity, the country-specific music listening behavior may deviate from the global one. In some countries, the listening behavior corresponds to the global mainstream; some countries have developed their own country-specific mainstream in addition to the global mainstream; a third group of countries shows clear deviations from the global mainstream, although a country-specific mainstream is not clearly noticeable. 3. Comparing the top charts of different countries, it is typically the same artists who are represented. For considering the country-specific nuances in defining mainstreaminess, we require approaches that downweigh popular superstars or give more weight to country- specific artists. We found approaches based on the Kullback-Leibler divergence and approaches based on Kendall`s tau being suitable. In combination with matrix factorization, the approach based on Kendall`s rank correlation coefficients is particularly successful in music recommendations experiments. 4. For low-mainstreamy users, we achieve particularly strong improvements in recommendation results (measured in the error rate) when compared to a generic approach that does not consider mainstreaminess or country. 5. First results indicate that there are differences in music preferences between urban and rural regions in conglomerations worldwide. Furthermore, countries can be grouped based on similarities in the users music listening behavior. Including such information as input for music recommendation, results can be improved. Building on this, future research may investigate the similarities in listening behavior based on, for example, sociological or economic aspects. Findings could then flow back into novel music recommendation approaches. 6. In music playlist creation in groups, users show different behavior patterns when confronted with a majority opinion. With a favored song, a single counter-opinion is enough to change a users mind and vote against the song for the playlist. In case of a disliked song, however, a majority opinion in favor of this song is required to change the user`s mind.
- Universität Linz - 100%
- Lee Kyoto, Seoul National University - Republic of Korea
- Paul Lamere, The Echo Nest - USA
Research Output
- 137 Citations
- 34 Publications
- 1 Policies
- 2 Datasets & models
- 1 Software
- 13 Disseminations
- 4 Scientific Awards
- 2 Fundings
-
2020
Title Multi-Method Evaluation DOI 10.1145/3343413.3378015 Type Conference Proceeding Abstract Author Bauer C Pages 472-474 Link Publication -
2020
Title Conformity Behavior in Group Playlist Creation DOI 10.1145/3334480.3382942 Type Conference Proceeding Abstract Author Bauer C Pages 1-10 Link Publication -
2021
Title Support the Underground: Characteristics of Beyond-Mainstream Music Listeners DOI 10.48550/arxiv.2102.12188 Type Preprint Author Kowald D -
2022
Title To Flip or Not to Flip: Conformity Effect Across Cultures DOI 10.1145/3491101.3519662 Type Conference Proceeding Abstract Author Ferwerda B Pages 1-7 Link Publication -
2021
Title Listener Modeling and Context-Aware Music Recommendation Based on Country Archetypes DOI 10.3389/frai.2020.508725 Type Journal Article Author Schedl M Journal Frontiers in Artificial Intelligence Pages 508725 Link Publication -
2021
Title Support the underground: characteristics of beyond-mainstream music listeners DOI 10.1140/epjds/s13688-021-00268-9 Type Journal Article Author Kowald D Journal EPJ Data Science Pages 14 Link Publication -
2019
Title The Potential of the Confluence of Theoretical and Algorithmic Modeling in Music Recommendation DOI 10.48550/arxiv.1911.07328 Type Preprint Author Bauer C -
2019
Title Allowing for equal opportunities for artists in music recommendation DOI 10.48550/arxiv.1911.05395 Type Preprint Author Bauer C -
2019
Title Online Music Listening Culture of Kids and Adolescents: Listening Analysis and Music Recommendation Tailored to the Young DOI 10.48550/arxiv.1912.11564 Type Other Author Bauer C -
2019
Title Leveraging Multi-Method Evaluation for Multi-Stakeholder Settings Type Conference Proceeding Abstract Author Bauer C Conference 1st Workshop on the Impact of Recommender Systems (ImpactRS 2019) -
2019
Title Leveraging Multi-Method Evaluation for Multi-Stakeholder Settings Type Conference Proceeding Abstract Author Bauer C Conference 1st Workshop on the Impact of Recommender Systems (ImpactRS 2019) -
2023
Title The Effect of Ingroup Identification on Conformity Behavior in Group Decision-Making: The Flipping Direction Matters Type Other Author Bauer C. Pages 2242-2251 -
2020
Title An Open Model for Researching the Role of Culture in Online Self-Disclosure DOI 10.48550/arxiv.2003.08942 Type Other Author Bauer C -
2018
Title The Effects of Real-world Events on Music Listening Behavior DOI 10.1145/3184558.3186936 Type Conference Proceeding Abstract Author Schedl M Pages 75-76 Link Publication -
2018
Title An Analysis of Global and RegionalMainstreaminess for Personalized MusicRecommender Systems DOI 10.13052/jmm1550-4646.1415 Type Journal Article Author Schedl M Journal Journal of Mobile Multimedia Pages 95-112 Link Publication -
2018
Title An Analysis of Global and Regional Mainstreaminess for Personalized Music Recommender Systems DOI 10.13052/1550-4646.1415 Type Journal Article Author Bauer C Journal Journal of Mobile Multimedia -
2018
Title Investigating Cross-Country Relationship between Users' Social Ties and Music Mainstreaminess DOI 10.5281/zenodo.1492506 Type Other Author Bauer C -
2019
Title A cross-country investigation of user connection patterns in online social networks Type Other Author Bauer C. Pages 2166-2175 -
2019
Title Leveraging multi-method evaluation for multi-stakeholder settings Type Other Author Bauer C. Pages - -
2019
Title Leveraging Multi-Method Evaluation for Multi-Stakeholder Settings Type Conference Proceeding Abstract -
2017
Title Introducing Global and Regional Mainstreaminess for Improving Personalized Music Recommendation DOI 10.1145/3151848.3151849 Type Conference Proceeding Abstract Author Schedl M Pages 74-81 Link Publication -
2017
Title Introducing Surprise and Opposition by Design in Recommender Systems DOI 10.1145/3099023.3099099 Type Conference Proceeding Abstract Author Bauer C Pages 350-353 Link Publication -
2017
Title Distance- and Rank-based Music Mainstreaminess Measurement DOI 10.1145/3099023.3099098 Type Conference Proceeding Abstract Author Schedl M Pages 364-367 -
2019
Title Tastalyzer DOI 10.1145/3343031.3350585 Type Conference Proceeding Abstract Author Bauer C Pages 1044-1046 -
2019
Title Cross-country User Connections in an Online Social Network for Music DOI 10.1145/3290607.3312831 Type Conference Proceeding Abstract Author Bauer C Pages 1-6 Link Publication -
2019
Title A Cross-Country Investigation of User Connection Patterns in Online Social Networks DOI 10.24251/hicss.2019.263 Type Conference Proceeding Abstract Author Bauer C Link Publication -
2019
Title Global and country-specific mainstreaminess measures: Definitions, analysis, and usage for improving personalized music recommendation systems DOI 10.1371/journal.pone.0217389 Type Journal Article Author Bauer C Journal PLOS ONE Link Publication -
2018
Title Musikwirtschaftsforschung DOI 10.1007/978-3-658-19399-7_6 Type Book Chapter Publisher Springer Fachmedien Wiesbaden -
2018
Title Investigating cross-country relationship between users' social ties and music mainstreamines Type Conference Proceeding Abstract Author Bauer C Conference 19th International Society for Music Information Retrieval Conference (ISMIR 2018) Pages 678-686 -
2018
Title UMAP 2018 Intelligent User-Adapted Interfaces DOI 10.1145/3213586.3226202 Type Conference Proceeding Abstract Author Celik I Pages 137-139 Link Publication -
0
DOI 10.1145/3491101 Type Other -
0
DOI 10.1145/3334480 Type Other -
0
DOI 10.1145/3290607 Type Other -
2018
Title On the Importance of Considering Country-specific Aspects on the Online-Market: An Example of Music Recommendation Considering Country-Specific Mainstream DOI 10.24251/hicss.2018.461 Type Conference Proceeding Abstract Author Bauer C Link Publication
-
2020
Link
Title The dataset used in the article "Listener Modeling and Context-aware Music Recommendation Based on Country Archetypes" DOI 10.5281/zenodo.3907362 Type Database/Collection of data Public Access Link Link -
2020
Link
Title LFM-BeyMS DOI 10.5281/zenodo.3784765 Type Database/Collection of data Public Access Link Link
-
2019
Link
Title Tastalyzer DOI 10.1145/3343031.3350585 Link Link
-
2018
Title KinderUni Linz 2018 Type Participation in an activity, workshop or similar -
2018
Link
Title Blog at DERSTANDARD Type Engagement focused website, blog or social media channel Link Link -
2018
Link
Title Visibility in Press and Media Type A magazine, newsletter or online publication Link Link -
2018
Link
Title WiMIR mentoring Type A formal working group, expert panel or dialogue Link Link -
2018
Link
Title Management Committee Substitute Member, European Cooperation for Statistics of Network Data Science (COSTNET), CA COST Action CA15109 Type A formal working group, expert panel or dialogue Link Link -
2017
Link
Title Service to the community Type A formal working group, expert panel or dialogue Link Link -
2018
Link
Title multhimethods.info Type Engagement focused website, blog or social media channel Link Link -
2019
Link
Title PrivacyWeek 2019 Type A talk or presentation Link Link -
2019
Title Talk at AI x Music Festival 2019 ( collocated with 2019 Ars Electronica Festival) Type A talk or presentation -
2019
Link
Title NGI Talk #3: AI and beyond Type A talk or presentation Link Link
-
2019
Title Best Reviewer Award (13th ACM Conference on Recommender Systems, RecSys 2019) Type Research prize Level of Recognition Continental/International -
2019
Title Outstanding Reviewer (Honorable Mention) (27th ACM Conference on User Modeling, Adaptation and Personalization, UMAP 2019) Type Research prize Level of Recognition Continental/International -
2018
Title Best Reviewer - Runner-up (12th ACM Conference on Recommender Systems, RecSys 2018) Type Research prize Level of Recognition Continental/International -
2017
Title Best Paper Award at MoMM 2017 Type Research prize DOI 10.1145/3151848.3151849 Level of Recognition Continental/International
-
2018
Title ÖFG Projekt 06 / 15515 Type Travel/small personal Start of Funding 2018 Funder Austrian Research Community -
2019
Title Projekt 06 / 15831 Type Travel/small personal Start of Funding 2019 Funder Austrian Research Community